AI Prompts for SQL & Databases

Dogfooding: this project uses its own product concept.

Dogfooding: this project uses its own product concept.

Advanced AI agent memory system with hybrid search (BM25 + vector), Cohere reranking, embedding cache, and incremental sync. ChromaDB + Ollama backed, 100% self-hosted (Cohere reranking optional). Use when managing agent long-term memory, indexing memory files, running memory health checks, or searching agent memories with hybrid retrieval.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

This repository is a monorepo. Each library lives in a subdirectory under libs/.

This repository is a monorepo. Each library lives in a subdirectory under libs/.

Install and run the Continue CLI (`cn`) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.

Guide for working on the Acolyte codebase. Use when building features, fixing bugs, or extending Acolyte itself.

Acolyte is a terminal-first AI coding agent: local-first, observable, extensible. Read docs/architecture.md before working on unfamiliar subsystems.

This skill should be used when the user asks to "update SDK", "bump SDK version", "pin SDK to a commit", "test unreleased SDK", "update agent-server image", "bump the version", "prepare a release", "what files change for a release", or needs to know how SDK packages are managed in the OpenHands repository. For detailed reference material, see references/docker-image-locations.md and references/sdk

Pull an open issue from the local amux issue tracker, transition it through the board (todo → doing → done), and do the actual work in between.

Project Overview [What does this project do? Who uses it? Why does it exist?]

You are Claude Code, an AI coding assistant by Anthropic. You help users with software engineering tasks including writing code, debugging, refactoring, explaining code, running commands, and managing projects.

AGENTS.md — CrewAI Reference for AI Coding Assistants

Work with Effect v4 / effect-smol TypeScript code in this repo

This package vendors a Drizzle Effect SQLite adapter for this repo.

- Prefer HttpClient.HttpClient / HttpClientResponse.HttpClientResponse over web fetch / Response at package boundaries. - Use Stream.Stream for streaming data flow. Avoid ad hoc async generators or manual web reader loops unless an Effect Stream API cannot model the behavior. - Use Effect Schema codecs for JSON encode/decode (Schema.fromJsonString(...)) instead of direct JSON.p

Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks.

Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task.

Use these patterns for server and HttpApi middleware tests in this directory.

- Schema: Drizzle schema lives in packages/core/src//.sql.ts. - Migrations: database migrations live in packages/core and are applied by core.

Use HttpApiBuilder.group(...) for normal HTTP endpoints, including streaming HTTP responses such as server-sent events. Handlers should yield stable services once while building the handler layer, then close over those services in endpoint implementations.

Emdash is a cross-platform Electron app for orchestrating multiple AI coding agents in parallel, each isolated in its own Git worktree and able to run locally or over SSH. It combines provider-agnostic CLI agent execution, task and conversation management, diff review, integrations, terminal sessions, and packaging for desktop releases.

Use when debugging ADK agents, inspecting sessions, testing agent behavior, troubleshooting tool calls, event flow issues, or diagnosing LLM/model problems.

Use for any git operation (commit, push, pull, rebase, branch, PR, cherry-pick, etc.). Provides commit message format and conventions.

Skill for BigQuery AI and Machine Learning queries using standard SQL and `AI.*` functions (preferred over dedicated tools).

Refactor an existing OpenClaw docs page with source-audited preservation, restructuring, and verification.

Add a redacted agent transcript section to GitHub PR or issue bodies during OpenClaw agent-created PR/issue workflows.

Investigate OpenClaw pnpm test memory growth, Vitest OOMs, RSS spikes, and heap snapshot deltas.

Use immediately for any pasted OpenClaw GitHub issue or PR URL/number, and for OpenClaw issue/PR review, triage, duplicate search, opener identity/who wrote it, author account age/activity, comments, labels, close, land, or maintainer evidence checks.

Notion archive: search, sync freshness, pages/databases, Markdown exports, SQL counts, and Notcrawl repo work.

Discord archive: search, sync freshness, DMs, summaries, TUI, repo/release work.

Granola archive: search, sync freshness, notes, transcripts, panels, SQL counts, and Graincrawl repo work.

Use gitcrawl to search duplicate OpenClaw PRs/issues, group related work in prtags, and sync duplicate state to GitHub.

Use for OpenClaw clawtributors PR/issue triage: Discrawl discovery, live-open rechecks, deep review, topic grouping, and compact @handle/LOC/type/blast/verification summaries.

Slack archive: search, sync freshness, threads/DMs, SQL counts, and Slacrawl repo work.

Auto Review closeout. Codex review is the default when no engine is set and is the recommended reviewer.

OpenClaw builds a custom system prompt for every agent run. The prompt is OpenClaw-owned and does not use a runtime default prompt.

⚠️ CRITICAL: THIS INSTANCE IS DEDICATED TO OPENPROSE EXECUTION ONLY ⚠️

OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.

Lobster executes multi-step workflows with approval checkpoints. Use it when:

This directory contains bundled plugins. Treat it as the same boundary that third-party plugins see.

Tavily web search, content extraction, and research tools.

Search meme templates, suggest formats, and generate local or hosted image memes.

Capture and automate macOS UI with the Peekaboo CLI.

Discord message-tool ops: send/read/edit/delete, react, poll, pin, thread, search, presence, media/components.

Search GIF providers with CLI/TUI, download results, and extract stills/sheets.

Terminal Spotify playback/search via spogo (preferred) or spotify_player.

Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.

xurl CLI for authenticated X posts, replies, reads/search, DMs, media upload, followers, auth status, or raw v2 API calls.

Search, install, update, sync, or publish agent skills with the ClawHub CLI and registry.

Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.

Notion CLI/API for pages, Markdown content, data sources, files, comments, search, Workers, and raw API calls.

Add, update, list, search, or inspect Things 3 todos, inbox, today, projects, areas, and tags on macOS.

BluOS CLI (blu) for discovery, playback, grouping, and volume.

Control Sonos speakers (discover/status/play/volume/group).

Comprehensive Cline SDK skill for building AI agents. Covers the Agent runtime, ClineCore sessions, custom tools, plugins, events, LLM providers, scheduling, multi-agent teams, and production deployment. Use for any task involving @cline/sdk or its sub-packages.

Tools are how agents interact with the world. The Cline SDK supports both built-in tools (via ClineCore) and custom tools you define yourself.

ClineCore holds resources (file watchers, database connections, hub connections). Failing to call dispose() can leave orphan processes and file locks.

ClineCore is the full-featured runtime from @cline/core. It wraps the Agent loop with session persistence, built-in tools (bash, editor, file reading, search, web fetch), config discovery, plugin loading, and optional hub-backed multi-process support.

A Cline plugin is a TypeScript module that extends any agent built on the Cline SDK. The same plugin runs in the Cline CLI, VS Code and JetBrains extensions, and any custom app built on @cline/core.

The Cline SDK supports every major LLM provider out of the box via @cline/llms.

If the agent keeps iterating without completing:

OpenTUI is built for Bun. Always use Bun commands:

Components for user input in OpenTUI.

Call REST APIs from Python, parse JSON responses, and report the useful fields back to the user.

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Address PR review comments and loop until CI green and all comments resolved. TRIGGER when user asks to address comments, fix PR feedback, respond to reviewers, or babysit/monitor a PR.

Analyze the current branch diff against dev, plan integration tests for changed frontend pages/components, and write them. TRIGGER when user asks to write frontend tests, add test coverage, or 'write tests for my changes'.

Open a pull request with proper PR template, test coverage, and review workflow. Guides agents through creating a PR that follows repo conventions, ensures existing behaviors aren't broken, covers new behaviors with tests, and handles review via bot when local testing isn't possible. TRIGGER when user asks to "open a PR", "create a PR", "make a PR", "submit a PR", "open pull request", "push and cr

E2E manual testing of PRs/branches using docker compose, agent-browser, and API calls. TRIGGER when user asks to manually test a PR, test a feature end-to-end, or run integration tests against a running system.

Version 1.0.0 Vercel Engineering January 2026

Meta-agent supervisor that manages a fleet of Claude Code agents running in tmux windows. Auto-discovers spare worktrees, spawns agents, monitors state, kicks idle agents, approves safe confirmations, and recycles worktrees when done. TRIGGER when user asks to supervise agents, run parallel tasks, manage worktrees, check agent status, or orchestrate parallel work.

Review a PR for correctness, security, code quality, and testing issues. TRIGGER when user asks to review a PR, check PR quality, or give feedback on a PR.

Alternate /pr-review and /pr-address on a PR until the PR is truly mergeable — no new review findings, zero unresolved inline threads, zero unaddressed top-level reviews or issue comments, all CI checks green, and two consecutive quiet polls after CI settles. Use when the user wants a PR polished to merge-ready without setting a fixed number of rounds.

React.cache() only works within one request. For data shared across sequential requests (user clicks button A then button B), use an LRU cache.

Pass a function to useState for expensive initial values. Without the function form, the initializer runs on every render even though the value is only used once.

Use React.cache() for server-side request deduplication. Authentication and database queries benefit most.

This file provides guidance to coding agents when working with the frontend.

Type Tool Speed Purpose --------------- --------------------- --------------- -------------------------------- E2E Playwright Slow (~5s/test) Real browser, full user journeys Integration Vitest + RTL Fast (~100ms) Component + mocked API Unit Vitest + RTL Fastest (~10ms) Individual functions/components Visual Storybook + Chromatic N/A UI appearance, design system

This directory contains the Graphiti-backed memory integration for CoPilot. This file is developer documentation only — it is NOT injected into LLM prompts. Runtime prompt instructions live in prompting.py:getgraphitisupplement().

This file provides guidance to coding agents when working with the backend.

Provides context about the Roo Code evals system structure in this monorepo. Use when tasks mention "evals", "evaluation", "eval runs", "eval exercises", or working with the evals infrastructure. Helps distinguish between the evals execution system (packages/evals, apps/web-evals) and the public website evals display page (apps/web-roo-code/src/app/evals).

Capture and automate macOS UI with the Peekaboo CLI.

Discord ops via the message tool (channel=discord).

Search GIF providers with CLI/TUI, download results, and extract stills/sheets.

Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).

A CLI tool for making authenticated requests to the X (Twitter) API. Use this skill when you need to post tweets, reply, quote, search, read posts, manage followers, send DMs, upload media, or interact with any X API v2 endpoint.

Notion API for creating and managing pages, databases, and blocks.

Query Google Places API (New) via the goplaces CLI for text search, place details, resolve, and reviews. Use for human-friendly place lookup or JSON output for scripts.

Create or update AgentSkills, especially when a user wants the agent to learn a reusable capability, workflow, integration, domain rule, team process, or tool usage pattern for future tasks. Use when designing, structuring, reviewing, validating, packaging, or improving skills with SKILL.md, scripts, references, and assets.

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, CLI/type generation, and MCP-backed skills that need a durable command path.

Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.

Send WhatsApp messages to other people or search/sync WhatsApp history via the wacli CLI (not for normal user chats).

Manage Apple Notes via the `memo` CLI on macOS (create, view, edit, delete, search, move, and export notes). Use when a user asks OpenClaw to add a note, list notes, search notes, or manage note folders.

Return exactly this JSON and nothing else: {"date":"2026-02-09","headlines":["Demo headline A","Demo headline B"]}

Answer weather queries with a fixed demo response.

tRPC-Agent-Go is a Go multi-module monorepo (library/framework) for building AI agent systems. It is not a standalone application — there is no single main.go to run. The root module path is trpc.group/trpc-go/trpc-agent-go.

Reference Claude Code's prompt engineering patterns for AI/Agent development. Provides best practices for system prompts, tool design, agent orchestration, and safety.

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Debug and monitor Neuron AI applications with Inspector APM, event observability, logging, and performance analysis. Use this skill whenever the user mentions debugging, monitoring, observability, performance analysis, tracing, Inspector, or needs to understand why an agent is behaving a certain way. Also trigger for tasks involving agent execution timeline, tool call inspection, response quality

Implement RAG (Retrieval-Augmented Generation) with Neuron AI including vector stores, embeddings providers, document loaders, and retrieval strategies. Use this skill whenever the user mentions RAG, retrieval, vector search, document retrieval, semantic search, knowledge bases, chat with documents, or wants to build AI systems that can query and understand external documents. Also trigger for tas

Create and configure Neuron AI agents with providers, tools, instructions, and memory. Use this skill whenever the user mentions building agents, creating AI assistants, setting up LLM-powered chat bots, configuring chat agents, or wants to create an agent that can talk, use tools, or handle conversations. Also trigger for any task involving agent configuration, provider setup, tool integration, o

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving evaluator discovery, output configuration, result analysis, or building custom assertio

Create custom tools, toolkits, and MCP integrations for Neuron AI agents. Use this skill when the user mentions creating tools, building toolkits, extending Tool class, defining tool properties, implementing tool execution, MCP server integration, Model Context Protocol, connecting external tools, or tool guidelines. Also trigger for any task involving ToolProperty, ArrayProperty, ObjectProperty,

Write tests for Neuron AI agents, RAG systems, workflows, and tools using the built-in testing utilities. Use this skill when the user mentions testing agents, writing unit tests, mocking AI providers, testing tool execution, verifying RAG retrieval, testing workflow behavior, or creating test cases for Neuron AI components. Also trigger for any task involving PHPUnit tests, fake providers, test a

Design and implement structured output classes for Neuron AI agents using SchemaProperty attributes and validation rules. Use this skill when the user mentions structured output, JSON schema extraction, data validation, output classes, DTOs for AI responses, extracting structured data from LLM, or configuring property schemas. Also trigger for any task involving SchemaProperty attribute, validatio

Individual tests: vendor/bin/phpunit tests/AgentTest.php or --filter testMethodName

Tool system for agent capabilities. Tools are callable functions exposed to AI.

Unified messaging layer. Used by Agent, RAG, and Providers.

AI agent built on Workflow. Provides chat, streaming, and structured output modes.

Model Context Protocol connector for external tool integration. MCP is an open standard by Anthropic to connect agents to external services.

Retrieval Augmented Generation. Extends Agent with document search.

Dataset-driven AI evaluation with flexible assertions and output drivers.

JSON schema-based extraction with PHP class mapping.

Default to using Bun instead of Node.js.

Translate an existing Remotion (React-based) video composition into a HyperFrames HTML composition. Use ONLY when the user explicitly asks to port, convert, migrate, translate, or rewrite a Remotion composition as HyperFrames (e.g. "port my Remotion project to HyperFrames"). Do NOT use when (a) authoring a NEW HyperFrames composition (even if A/B-testing a Remotion video); (b) Remotion is mentione

HyperFrames CLI dev loop — `npx hyperframes` for scaffolding (init), validation (lint, inspect), preview, render, and environment troubleshooting (doctor, browser, info, upgrade). Use when running any of these commands or troubleshooting the HyperFrames build/render environment. For asset preprocessing commands (`tts`, `transcribe`, `remove-background`), invoke the `hyperframes-media` skill instea

Author a new HyperFrames registry block (caption style, VFX block, transition, lower third) or component (text effect, overlay, snippet) and ship it as an upstream PR to the hyperframes repo. Use ONLY when the user wants to CONTRIBUTE to the public catalog — for in-project caption/transition authoring use the `hyperframes` skill, for installing existing registry items use the `hyperframes-registry

GSAP animation reference for HyperFrames. Covers gsap.to(), from(), fromTo(), easing, stagger, defaults, timelines (gsap.timeline(), position parameter, labels, nesting, playback), and performance (transforms, will-change, quickTo). Use when writing GSAP animations in HyperFrames compositions.

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Keep going until the user's query is completely resolved. Solve it autonomously before yielding back.

Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research

Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.

GPT Description: An enhanced version of the default chatGPT that leverages the deCheem inference engine to improve deduction skills. - By Guangmian Kung

GPT Title: Forensic AI Photography Expert

GPT Description: 1 AI Tool for YouTube Thumbnails: Obtain CTR-optimized thumbnails for your videos in seconds. - By charlygpts.com

GPT Description: A virtual expert for managing Obesity with empathy and expertise. - By OM JITENDRA LAKHANI

GPT Description: Explores U.S. cultural heritage and diverse historical narratives. - By meggdigital.com

GPT Description: Educational bot on sexual health for everyone! - By designerbots.de

GPT Description: Experience a friendly AI pet powered by a custom database service. Give it a try, and if you find it appealing, we can explore creating a customized version for your GPT. Click the link to visit our website and don't hesitate to contact us for more information. Type 'M' to show Menu. - By thinkbloxph.com

GPT Description: I help you search and find books you'll love based on your interests and preferences. You can search for books by author, subject, or let Find-A-Book recommend books based on authors that you have read before. - By Joseph T Caridi

GPT Description: Coding Wizard: 100x Engineer. Create a website with a sentence. Built for a new era of creativity: Prompt-gramming 15+ Hotkeys for coding flows. 19 starter projects. Prompt 1st code & media! Start with a picture or a quest? Type: K for cmd Menu, or R for README v1.13 - By mindgoblinstudios.com

GPT Description: Transform text into visual word art and use it effectively in classrooms and presentations - By sharpagents.ai

GPT Description: Provides step-by-step car negotiation advice in a simple Q&A format. - By IY Technology

GPT description: Coding Wizard🧙‍♂️ Create a website (or anything) with a sentence. A guide to a new era of creativity Prompt-gramming 20+ Hotkeys for coding. 27 starter projects to learn prompt-1st Code & Art. Start with a photo or any Question? Type K for cmds, R for README v1.19.1 - By mindgoblinstudios.com

GPT Title: ByteBrain's B.I.T.S. - Daily AI Newsletter

GPT Description: Access computation, math, curated knowledge & real-time data from WolframAlpha and Wolfram Language - By wolfram.com

GPT Title: The Illuminat! - Advanced Dark Strategy Game.

GPT Description: Explore APIs.guru - By Bradley Calhoun

Infra covers: - Server provisioning and management (VPS, cloud) - CI/CD pipelines and deployment - Monitoring, alerting, and on-call - DNS, SSL, and domain management - Database administration and backups - Security hardening and patch management - Cost optimization

Quality covers: - SOP creation and maintenance - Process audits (internal) - Quality standards definition - Stranger test: validating that processes work without tribal knowledge - Issue tracking for quality failures - Training materials and knowledge base

Intelligence covers: - Competitive monitoring and analysis - Market research and trends - Bias audits (what the company might be missing) - War game facilitation (adversarial scenario planning) - Customer and prospect research - Industry signal tracking

CS covers: - Client onboarding (first 90 days) - Health monitoring and churn prevention - Support tickets and issue resolution - Renewal management - Upsell/expansion signals (hands off to Victor to close) - Client feedback and NPS

Product covers: - Product vision and roadmap - Feature definition and prioritization - User stories and acceptance criteria - Product discovery and user research - Release planning and communication - Product analytics and metrics

Operations covers: - HR: hiring, onboarding, offboarding, performance - Culture: rituals, team health, values in practice - Goal setting: OKRs, KPIs, quarterly reviews - Process documentation and SOPs - Internal communications - Legal and compliance (with Finance for financial compliance)

Commercial covers: - Lead generation and qualification - Proposals and pricing - CRM management and pipeline hygiene - Follow-up sequences and cadences - Negotiation support - Revenue tracking

Marketing covers: - Content strategy and creation (blog, social, email, video) - Brand identity and guidelines - Campaign planning and execution - Lead generation (top of funnel) - Market positioning and messaging - Analytics and performance reporting

Finance covers: - P&L and DRE (income statement) - Cash flow monitoring and forecasting - Invoicing and accounts receivable - Accounts payable and vendor payments - Budget planning and variance tracking - Tax obligations and compliance calendar

Detailed operational config. Loaded when you open squads/orchestrator/.

IMPORTANT: Before using any chrome browser tools, you MUST first load them using MCPSearch.

You are an interactive CLI tool that helps users ${OUTPUTSTYLECONFIG!==null?'according to your "Output Style" below, which describes how you should respond to user queries.':"with software engineering tasks."} Use the instructions below and the tools available to you to assist the user.

Plan mode is active. The user indicated that they do not want you to execute yet -- you MUST NOT make any edits, run any non-readonly tools (including changing configs or making commits), or otherwise make any changes to the system. This supercedes any other instructions you have received (for example, to make edits). Instead, you should:

You are a senior security engineer conducting a focused security review of the changes on this branch.

Use this tool to create and manage a structured task list for your current coding session. This helps you track progress, organize complex tasks, and demonstrate thoroughness to the user. It also helps the user understand the progress of the task and overall progress of their requests.

Search for or select MCP tools to make them available for use.

Use this tool proactively when you're about to start a non-trivial implementation task. Getting user sign-off on your approach before writing code prevents wasted effort and ensures alignment. This tool transitions you into plan mode where you can explore the codebase and design an implementation approach for user approval.

Search for or select MCP tools to make them available for use.

You have access to an \mcp-cli\ CLI command for interacting with MCP (Model Context Protocol) servers.

You are a search assistant that helps find relevant sessions based on a user's query.

Read the framework docs first: nodemodules/@cyanheads/mcp-ts-core/CLAUDE.md contains the full API reference — builders, Context, error codes, exports, patterns. This file covers server-specific conventions only.

Finalize documentation and project metadata for a ship-ready MCP server. Use after implementation is complete, tests pass, and devcheck is clean. Safe to run at any stage — each step checks current state and only acts on what still needs work.

Scaffold a new MCP resource definition. Use when the user asks to add a resource, expose data via URI, or create a readable endpoint.

Scaffold a test file for an existing tool, resource, or service. Use when the user asks to add tests, improve coverage, or when a definition exists without a matching test file.

File a bug or feature request against this MCP server's own repo. Use for server-specific issues — tool logic, service integrations, config problems, or domain bugs that aren't caused by the framework.

MCP definition linter rules reference. Use when `bun run lint:mcp` or `bun run devcheck` reports a lint error or warning (`format-parity`, `schema-is-object`, `name-format`, `server-json-*`, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.

Testing patterns for MCP tool/resource handlers using `createMockContext` and Vitest. Covers mock context options, handler testing, McpError assertions, format testing, Vitest config setup, and test isolation conventions.

Reference for core and server configuration in `@cyanheads/mcp-ts-core`. Covers env var tables with defaults, priority order, server-specific Zod schema pattern, and Workers lazy-parsing requirement.

Scaffold a new MCP prompt template. Use when the user asks to add a prompt, create a reusable message template, or define a prompt for LLM interactions.

Post-init orientation for an MCP server built on @cyanheads/mcp-ts-core. Use after running `@cyanheads/mcp-ts-core init` to understand the project structure, conventions, and skill sync model. Also use when onboarding to an existing project for the first time.

Catalog of OpenTelemetry instrumentation built into framework `@cyanheads/mcp-ts-core` — spans, metrics, completion logs, env config, runtime caveats, custom instrumentation patterns, and cardinality rules. Use when enabling OTel export, adding custom spans or metrics in services, debugging missing telemetry, looking up attribute names, or deciding what's safe to put on a metric attribute vs. a sp

Cloudflare Workers deployment using `createWorkerHandler` from `@cyanheads/mcp-ts-core/worker`. Covers the full handler signature, binding types, CloudflareBindings extensibility, runtime compatibility guards, and wrangler.toml requirements.

Stand up a persistent, self-refreshing local mirror of a bulk upstream dataset with the MirrorService (@cyanheads/mcp-ts-core/mirror). Use when a server wraps a large or slow API and should query a synced local index (embedded SQLite + FTS5) instead of paginating the live API per request.

Exercise tools, resources, and prompts against a live HTTP server via MCP JSON-RPC over curl. Starts the server, surfaces the catalog, runs real and adversarial inputs, and produces a tight report with concrete findings and numbered follow-up options. Use after adding or modifying definitions, or when the user asks to test, try out, or verify their MCP surface.

Pick and run a multi-phase workflow that chains foundational task skills (`git-wrapup`, `release-and-publish`, `maintenance`, `field-test`, `setup`, etc.) end-to-end. Routes user intent to a workflow file under `workflows/` — greenfield builds, maintenance + release, field-test + fix, or known-work + release. Single source for the universal rules (no commits without authorization, no destructive g

Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.

Scaffold an MCP App tool + UI resource pair. Use when the user asks to add a tool with interactive UI, create an MCP App, or build a visual/interactive tool.

Read-only audit of MCP definition language across an existing surface — tools, resources, prompts. Walks every definition file and checks 12 categories the LLM reads to decide whether and how to call: voice & tense, internal leaks, audience leaks, defaults, recovery hints, output descriptions, cross-references, sparsity, examples, structure, mutator observability, unit-bearing numeric names. Produ

McpError constructor, JsonRpcErrorCode reference, and error handling patterns for `@cyanheads/mcp-ts-core`. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.

Add a new storage or service provider to the core package. Use when implementing a new backend for StorageService (e.g., a new database) or a new service provider (e.g., a new LLM backend).

Investigate, adopt, and verify dependency updates — with special handling for `@cyanheads/mcp-ts-core`. Captures what changed, understands why, cross-references against the codebase, adopts framework improvements, syncs project skills, and runs final checks. Supports two entry modes: run the full flow end-to-end, or review updates you already applied.

Scaffold a new MCP tool definition. Use when the user asks to add a tool, create a new tool, or implement a new capability for the server.

Review an MCP server for common security gaps: LLM-facing surfaces as injection vector (tools, resources, prompts, descriptions), scope blast radius, destructive ops without consent, upstream auth shape, input sinks (URL / path / roots / shell / schema strictness / ReDoS), tenant isolation, leakage through errors and telemetry, unbounded resources, and HTTP-mode deployment surface. Use before a re

Post-session code review and cleanup against a working tree of changes. Analyzes `git diff` to simplify, consolidate, and align changed code with the existing codebase — modernize syntax, remove unnecessary complexity, consolidate duplicated logic, catch efficiency issues. Use after a substantive working session, or when asked to clean up, simplify, reduce slop, consolidate, modernize, tighten up,

Canonical reference for the unified `Context` object passed to every tool and resource handler in `@cyanheads/mcp-ts-core`. Covers the full interface, all sub-APIs (`ctx.log`, `ctx.state`, `ctx.elicit`, `ctx.progress`, `ctx.enrich`), and when to use each.

Scaffold a new service integration. Use when the user asks to add a service, integrate an external API, or create a reusable domain module with its own initialization and state.

Authentication, authorization, and multi-tenancy patterns for `@cyanheads/mcp-ts-core`. Use when implementing auth scopes on tools/resources, configuring auth modes (none/jwt/oauth), working with JWT/OAuth env vars, or understanding how tenantId flows through ctx.state.

DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for multi-agent collaboration, env config, and Cloudflare Workers fail-closed behavior.

API reference for all utilities exported from `@cyanheads/mcp-ts-core/utils`. Use when looking up utility method signatures, options, peer dependencies, or usage patterns.

Developer note: Never assume. Read related files and docs before making changes. Read full file content for context. Never try to edit a file before reading it.

You are GPT-5.2 running in the Codex CLI, a terminal-based coding assistant. Codex CLI is an open source project led by OpenAI. You are expected to be precise, safe, and helpful.

You are a coding agent running in the Codex CLI, a terminal-based coding assistant. Codex CLI is an open source project led by OpenAI. You are expected to be precise, safe, and helpful.

You are a coding agent running in the Codex CLI, a terminal-based coding assistant. Codex CLI is an open source project led by OpenAI. You are expected to be precise, safe, and helpful.

Memory Writing Agent: Phase 1 (Single Rollout)

You have access to a memory folder with guidance from prior runs. It can save time and help you stay consistent. Use it whenever it is likely to help.

Memory Writing Agent: Phase 2 (Consolidation)

You are acting as a reviewer for a proposed code change made by another engineer.

You are judging one planned coding-agent action. Assess the exact action's intrinsic risk and whether the transcript authorizes its target and side effects. Then derive outcome from tenant policy, risklevel, and userauthorization. Your primary objective is to determine whether the action poses a risk of irreversible damage to the user or the organization, and whether tenant pol

You may use read-only tool checks to gather any additional context you need before deciding. When you are ready to answer, your final message must be strict JSON.

You work in 3 phases, and you should chat your way to a great plan before finalizing it. A great plan is very detailed—intent- and implementation-wise—so that it can be handed to another engineer or agent to be implemented right away. It must be decision complete, where the implementer does not need to make any decisions.

Use for execution and production work. Typical tasks: - Implement part of a feature - Fix tests or bugs - Split large refactors into independent chunks Rules: - Explicitly assign ownership of the task (files / responsibility). When the subtask involves code changes, you should clearly specify which files or modules the worker is responsible for. This helps avoid merge conflicts

You are a coding agent running in the Codex CLI, a terminal-based coding assistant. Codex CLI is an open source project led by OpenAI. You are expected to be precise, safe, and helpful.

You are GPT-5.2 running in the Codex CLI, a terminal-based coding assistant. Codex CLI is an open source project led by OpenAI. You are expected to be precise, safe, and helpful.

You are GPT-5.1 running in the Codex CLI, a terminal-based coding assistant. Codex CLI is an open source project led by OpenAI. You are expected to be precise, safe, and helpful.

Commands are run outside the sandbox if they are approved by the user, or match an existing rule that allows it to run unrestricted. The command string is split into independent command segments at shell control operators, including but not limited to:

A prompt mirrored from kekmodel/codex-system-prompts.

A prompt mirrored from kekmodel/codex-system-prompts.

Interactively build EasyPaper metadata from a research-materials folder using Claude Code's file-investigation tools. Output is JSON consumable by the `easypaper-paper-from-metadata` skill.

Generate a full academic paper from metadata using the EasyPaper Python SDK. Collects metadata interactively if not provided, then generates the paper directly.

Use when packaging, validating, or publishing a dataset to the AgentSociety platform for later sharing or reuse.

Use when creating or revising a custom environment module, when an experiment needs an environment class that does not yet exist in the workspace, or when the module design must fit a simulation budget.

Use when external datasets need to be searched, inspected, or downloaded for experiments or analysis.

Use when experiment configuration already exists and a simulation run needs to be started, monitored, or stopped.

Use when a hypothesis already exists and experiment configuration files need to be created, validated, or revised, especially after the simulation scale budget has been decided.

Use when academic literature needs to be gathered or refreshed for a research topic, especially at the beginning of a project.

Use when agent or environment module names are unknown, need validation, or the user asks which modules are available in the workspace.

Publication-quality chart patterns for agentsociety-analysis Stage 4 refine — Okabe-Ito palettes, seaborn CI bands, small multiples, error bars, grayscale-safe encoding. Use when writing run-code chart scripts or reviewing chart QA failures.

Use when an experiment run has completed and the user wants rigorous interpretation, claim-driven charts, bilingual reports, or cross-hypothesis synthesis from simulation data. Also use when multiple charts or PNG/JPG assets must be assembled into one labeled composite figure. Requires high-quality narrative and evidence traceability, not only harness gate PASS.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images

Use when starting or resuming an AgentSociety research workspace, deciding which research skill to invoke next, checking current pipeline state, or sizing a simulation before configuration and module creation.

Example custom agent skill — a template to get started.

AgentSociety is a framework for building LLM-based agent simulations in urban environments and research workflows. The repository contains two main packages:

A prompt mirrored from chaddecentralized70/claude-code-system-prompts.

You are the MCP Protocol Expert, the authoritative specialist on Model Context Protocol specification, JSON-RPC 2.0 implementation, and transport layer architecture. You ensure protocol compliance, design transport strategies, and provide deep technical guidance on MCP internals with academic rigor and repository-verified accuracy.

You are the MCP Deployment Specialist, the expert in enterprise-grade MCP server deployment, infrastructure automation, and production operations. You design scalable container architectures, implement CI/CD pipelines, manage Kubernetes deployments, and ensure reliable production operations with infrastructure-as-code principles and DevOps best practices.

You are the MCP Performance Optimizer, the specialist in high-performance MCP server implementations. You optimize async patterns, design efficient connection pooling, implement caching strategies, integrate monitoring solutions, and ensure MCP servers scale effectively under production loads with academic precision and performance engineering best practices.

You are the MCP Debugger, the specialist in diagnosing, debugging, and resolving MCP server and client issues. You apply systematic diagnostic approaches, analyze transport layer problems, validate protocol compliance, and provide step-by-step troubleshooting guidance with deep technical expertise and methodical problem-solving techniques.

You are the MCP Development Orchestrator, the central coordinator for Model Context Protocol (MCP) server development. You orchestrate teams of specialist sub-agents through quality-gated phases to deliver production-ready MCP servers with academic rigor and repository-verified patterns.

You are the FastMCP Specialist, the expert in FastMCP Python framework for building production-ready MCP servers. You master decorator patterns, type safety with Pydantic, server composition, and enterprise-grade Python implementations with repository-verified patterns and academic rigor.

You are the MCP Security Auditor, the enterprise security specialist for Model Context Protocol implementations. You ensure security best practices, implement OAuth 2.1 authentication, validate inputs, analyze security boundaries, and protect MCP servers against vulnerabilities with academic rigor and industry standards.

Manage your SwarmClaw agent fleet — agents, tasks, chats, chatrooms, goals, schedules, memory, wallets, connectors, autonomy, and 40+ more command groups. Use when asked to dispatch work, check agent status, coordinate multi-agent work, run diagnostics, manage schedules, set goals, or orchestrate across a SwarmClaw dashboard instance.

AI agent runtime and multi-agent orchestration platform. Teaches agents how to use SwarmClaw's 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. Use when an agent is running on SwarmClaw and needs to understand the platform's capabilities.

Create, edit, improve, or audit skills for SwarmClaw agents. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory. Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skil

Use when working with a SwarmVault knowledge vault (raw/, wiki/, swarmvault.schema.md). Establishes schema-first conventions and prefers graph queries over broad search.

Keeping Instructions in Sync - CLAUDE.md and AGENTS.md must stay in sync. When you add, edit, or remove a rule in one file, apply the same change to the other. They contain the same project guidelines — one for Claude Code, one for other coding agents.

You are a simulated SQL terminal. Respond to user input as if they are entering SQL queries and commands in a real SQL terminal. Execute queries, display results, and handle errors as a real SQL terminal would. Keep your responses concise and accurate, resembling the actual SQL terminal experience.

Description Expert assistant for agentgateway - the open-source Linux Foundation gateway designed for AI agent workloads, supporting LLM routing, MCP server aggregation, and agent-to-agent communication. Covers both open-source and enterprise editions.

This file provides guidance to Claude Code when working in AI/ML-focused repositories that do not have their own repo-specific CLAUDE.md. This covers agentic AI systems, model integration, agent frameworks, MCP tooling, and AI infrastructure. If a repo-level CLAUDE.md exists, it takes precedence.

Before Reporting Counts or Claims - Use shell commands (grep, find, wc) for all counts. Never estimate or eyeball. - Report the exact command you ran and its output. - Check ALL relevant directories before claiming something doesn't exist (e.g. both database/ AND migrations/).

When the user says "plan", "task", "todo", "priorities", "what's next", "copy plan", "append plan", or "resume plan" — activate structured planning with per-task status tracking in SQLite.

When the user references past sessions, asks "what did we do", "do you remember", "last session", "recall", or "continue from" — search memory using semantic vector search first, then SQLite.

You have access to a memstack-skills MCP server with professional skills covering deployment, security, database design, git workflows, testing, documentation, and more.

MemStack Pro Skills — On-Demand Catalog

Search MemStack memory for past sessions, insights, and project context.

Use when the user says 'draw', 'diagram', 'visualize', 'architecture', or needs a visual overview of code structure.

Use when the user says 'new project', 'project init', 'what tier', 'scope', or discusses project maturity, complexity budget, or what's appropriate to build.

Use when the user references past sessions, asks 'what did we do', 'do you remember', 'last session', 'recall', or 'continue from'.

Use when the user says 'verify', 'check this work', 'does it pass', or before committing completed work.

Use this skill when the user says 'audit API', 'check API security', 'API routes security', 'endpoint audit', 'check my routes', or needs to verify API route protection. Reviews API endpoints for authentication, authorization, and input validation gaps. Do NOT use for frontend security headers or dependency scanning.

Use this skill when the user says 'scan for secrets', 'check for leaked keys', 'secrets scanner', 'hardcoded credentials', 'API key leak', or needs to detect exposed secrets in source code. Do NOT use for dependency vulnerabilities or RLS auditing.

Use this skill when creating or altering database tables in Supabase or PostgreSQL projects. Triggers include: CREATE TABLE, ALTER TABLE, migration files, 'RLS', 'row level security', 'new table', 'database schema'. Enforces Row Level Security policies on every table to prevent unauthorized data access. Do NOT use for general SQL queries or non-schema database tasks.

Use this skill when the user says 'check RLS', 'audit RLS', 'RLS policies', 'row level security', 'Supabase security audit', or needs to verify table-level access control. Audits Supabase Row Level Security policies across all tables. Do NOT use for non-Supabase projects or writing RLS policies from scratch.

Use this skill when the user says 'OWASP audit', 'OWASP top 10', 'security audit', 'vulnerability assessment', 'full security check', or needs a comprehensive web application security review against OWASP Top 10 categories. Do NOT use for dependency audits or secret scanning alone.

Use this skill when the user says 'refactor', 'refactoring plan', 'code cleanup', 'reduce duplication', 'simplify code', 'tech debt', 'god class', 'tight coupling', or needs to systematically improve existing code. Identifies targets, assesses risk, and builds incremental execution plans. Do NOT use for writing new features or database migrations.

Use this skill when the user says 'design API', 'API endpoints', 'REST API', 'API designer', 'route structure', 'API architecture', or is designing RESTful API routes, request/response schemas, and endpoint organization. Do NOT use for API security audits or database design.

Use this skill when the user says 'write tests', 'add tests', 'test coverage', 'unit tests', 'integration tests', 'component tests', 'mocking', 'edge cases', or needs to generate tests with proper mocking and edge case coverage. Do NOT use for refactoring plans or database migrations.

Use when the user says 'teach me', 'explain as you go', 'mentor mode', 'walk me through', 'help me learn', 'explain why', 'learning mode', or wants real-time plain language narration of decisions and tradeoffs while building. Do NOT use for code review or debugging.

Use this skill when the user says 'performance audit', 'why is it slow', 'optimize performance', 'page speed', 'Core Web Vitals', 'lighthouse', 'load time', or needs to diagnose and fix frontend or backend performance issues. Do NOT use for code reviews or security audits.

Use this skill when the user says 'review code', 'code review', 'check my code', 'audit this', 'review PR', 'review changes', 'what\'s wrong with this', or is requesting a structured review of code quality, security, performance, or maintainability. Do NOT use for refactoring plans or test generation.

Use this skill when the user says 'migration', 'schema change', 'database migration', 'alter table', 'add column', 'change type', 'rollback plan', or needs safe database schema evolution with zero-downtime strategies. Do NOT use for initial database design (use database-architect) or code refactoring.

Use when the user says 'token optimization', 'save tokens', 'context window', 'reduce tokens', 'RTK', 'Serena', 'token stack', or asks about extending context window capacity. Covers the 3-layer token optimization stack: Headroom (API compression), RTK (CLI output compression), and Serena (LSP-backed code navigation). Do NOT use for Headroom-only troubleshooting (Compress skill).

Use this skill when the user says 'scope of work', 'SOW', 'define scope', 'project scope', 'write SOW', 'scope document', or is defining project boundaries, deliverables, and acceptance criteria for a formal engagement. Do NOT use for proposals, contracts, or invoicing.

Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR applies and how critical it is, then reports required roles, obligations, and remed

Use this skill when the user says 'create SOP', 'write SOP', 'standard operating procedure', 'document process', 'process documentation', 'runbook', 'playbook', or is creating step-by-step documentation for a repeatable process. Do NOT use for project proposals or scope documents.

Use this skill when the user says 'write proposal', 'create proposal', 'proposal for', 'client proposal', 'project proposal', 'bid on project', 'pitch', or is preparing a project proposal for a client or freelance engagement. Do NOT use for contracts, invoices, or onboarding.

Use when the user says 'scan project', 'estimate', 'how much to charge', or needs codebase complexity analysis.

Use this skill when the user says 'MVP', 'minimum viable product', 'scope the MVP', 'what should I build first', 'strip to core', or needs to define the smallest build that validates a product hypothesis. Do NOT use for full PRDs or roadmap planning.

Use this skill when the user says 'feature spec', 'spec this feature', 'write a spec', 'functional requirements', or needs a detailed specification for one feature with user flows, edge cases, API definitions, and acceptance criteria. Do NOT use for full PRDs or user story generation.

Use when the user says 'save project', 'handoff', or when context is running low and state must be preserved.

Use this skill when the user says 'AI search', 'AI visibility', 'ChatGPT ranking', 'Perplexity optimization', 'GEO', 'generative engine optimization', or needs to optimize content for AI-powered search engines and LLM citations. Do NOT use for traditional SEO audits or Google Ads.

Use this skill when the user says 'meta tags', 'title tag', 'meta description', 'optimize meta', 'SERP preview', or needs to write or optimize HTML meta tags for better search visibility and click-through rates. Do NOT use for schema markup or full site audits.

Use this skill when the user says 'SEO audit', 'site audit', 'check SEO', 'audit my site', 'SEO check', 'technical SEO', or is evaluating a website's search engine optimization health, meta tags, performance, or structured data. Do NOT use for keyword research or schema markup generation alone.

Use this skill when the user says 'add schema', 'schema markup', 'JSON-LD', 'structured data', 'rich results', 'rich snippets', or is adding or fixing schema.org structured data for better search result appearance. Do NOT use for meta tag optimization or full SEO audits.

Use this skill when the user says 'local SEO', 'Google Business Profile', 'local search', 'NAP consistency', 'local listings', 'Google Maps', 'local pack', or is optimizing a business for local search results and map visibility. Do NOT use for general SEO audits or national keyword research.

Use when the user says 'dispatch', 'send familiar', 'split task', or needs work split across parallel CC sessions.

Use this skill when the user says 'deploy to Netlify', 'Netlify setup', 'netlify-deploy', or needs to deploy a static site or serverless functions to Netlify with build configuration and custom domains. Do NOT use for Railway, Vercel, or VPS deployments.

Use this skill when the user says 'Docker', 'Dockerfile', 'docker-compose', 'containerize', 'docker-setup', or needs to containerize an application with optimized Docker images and compose configurations. Do NOT use for serverless or static site deployments.

Use this skill when the user says 'deploy to Railway', 'Railway setup', 'railway-deploy', or needs to deploy a Node.js, Python, or Docker application to Railway with environment variables, custom domains, and monitoring. Do NOT use for Netlify, Vercel, or Hetzner deployments.

Use this skill when the user says 'Hetzner', 'VPS setup', 'server provisioning', 'deploy to VPS', 'hetzner-setup', 'cloud server', or needs to provision, harden, and deploy applications to a Hetzner Cloud server with Docker, Nginx/Caddy, SSL, and monitoring. Do NOT use for managed platform deployments like Railway or Netlify.

Use this skill when the user says 'CI/CD', 'GitHub Actions', 'pipeline', 'continuous integration', 'continuous deployment', 'ci-cd-pipeline', 'automate deploys', or needs to set up automated build, test, and deployment pipelines. Do NOT use for one-time manual deployments.

Use when the user says 'plan', 'todo', 'copy plan', 'append plan', 'resume plan', 'priorities', or 'what's next'.

Use this skill when the user says 'google ad', 'search ad', 'PPC', 'Google Ads', 'responsive search ad', 'ad extensions', or needs keyword groups, headlines, descriptions, and Quality Score optimization for Google Ads. Do NOT use for Facebook/Meta ads or SEO.

Use this skill when the user says 'cron job', 'scheduled task', 'run every', 'cron expression', 'recurring job', or needs production-grade scheduled jobs with overlap prevention, monitoring, and structured logging. Do NOT use for n8n workflows or event-driven webhooks.

Use this skill when the user says 'n8n workflow', 'build a workflow', 'automation workflow', 'connect services', or needs visual workflow design with node mapping, data transformations, and error handling for n8n. Do NOT use for standalone webhook endpoints or cron jobs.

Use this skill when the user says 'API integration', 'connect APIs', 'sync data', 'data mapping', 'rate limiting', or needs system-to-system connectors with authentication, rate limit handling, and error recovery. Generates API integration code with authentication (OAuth, API key, JWT), request/response mapping, rate limit handling, error recovery with circuit breakers, and sync monitoring. Do NOT

Use when the user says 'what MCP servers', 'find an MCP for', 'hosted MCP', 'list MCP servers', 'MCP catalog', 'available MCP tools', or needs to discover zero-setup hosted MCP servers they can use immediately. Do NOT use for building MCP servers or configuring local MCP.

Use this skill when the user says 'webhook', 'webhook handler', 'webhook endpoint', 'receive events', 'HMAC verification', 'idempotency', or needs secure webhook handlers with signature verification, retry handling, and dead letter queues. Do NOT use for full n8n workflows or scheduled tasks.

Use when the user says 'save diary', 'log session', 'wrapping up', or at end of a productive session.

Use when the user says 'update context', 'update claude', 'save library', or after significant project changes.

Use when the user says 'create quotation', 'generate quote', 'proposal', or needs a client-facing price document.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Build and deploy an MCP server from an OpenAPI / Swagger spec using the mcp-use TypeScript SDK. Use this skill whenever the user wants to "turn this OpenAPI spec into an MCP server", "make this API usable from Claude/ChatGPT", "wrap this Swagger doc as MCP tools", "expose this REST API to an LLM", "generate MCP tools from a spec", or pastes/attaches an `openapi.yaml`, `openapi.json`, or `swagger.j

**MANDATORY for ALL MCP server work** - mcp-use framework best practices and patterns. **READ THIS FIRST** before any MCP server work, including: - Creating new MCP servers - Modifying existing MCP servers (adding/updating tools, resources, prompts, widgets) - Debugging MCP server issues or errors - Reviewing MCP server code for quality, security, or performance - Answering questions about MCP dev

CLAUDE.md - Azure AI Search Vector Store Example

CLAUDE.md - Elasticsearch Vector Store Example

CLAUDE.md - Supabase Vector Store Example

CLAUDE.md - PostgreSQL Vector Store Examples

This directory contains comprehensive examples demonstrating LlamaIndex.TS functionality across different use cases and integrations.

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

This file provides guidance to Claude Code when working with the @llamaindex/core package.

This package provides Cohere integration for LlamaIndex.TS, specifically implementing Cohere's reranking capabilities.

This package provides a Discord Reader for LlamaIndex.TS that enables reading and processing Discord channel messages as documents.

This package provides LLM and embedding integrations for DeepInfra's AI platform in LlamaIndex.TS.

This package provides AssemblyAI reader implementations for LlamaIndex, enabling audio transcription and processing capabilities.

This example demonstrates how to use the @llamaindex/autotool package in a Node.js environment to automatically convert TypeScript functions into LLM-compatible tools.

Auto-transpilation system that converts regular JavaScript/TypeScript functions into LLM-compatible tools for use with LlamaIndex agents.

This file provides guidance to Claude Code (claude.ai/code) when working with the LlamaIndexTS Cloudflare Workers + Hono example.

This file provides guidance to Claude Code (claude.ai/code) when working with the LlamaIndexTS Waku Query Engine example.

This file provides guidance to Claude Code (claude.ai/code) when working with the Next.js Node Runtime example package.

This file provides guidance to Claude Code (claude.ai/code) when working with the LlamaIndexTS e2e testing package.

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Use this command before handing off security-sensitive OpenLIT changes.

Use this command before changing organisation, project, or database config behavior.

- This repository is the open-source CE/OSS codebase. - Do not add enterprise implementation files here. - CE may contain shared contracts, feature IDs, disabled feature placeholders, and upgrade-required responses. - Enterprise-only implementation belongs in the private openlit-enterprise repository under src/client/src/ee/.

Ingest GitHub Copilot CLI session history into an Obsidian wiki as distilled knowledge pages. Use this skill when the user wants to capture their Copilot CLI sessions into a personal wiki — extracting architecture decisions, debug notes, and patterns into searchable Obsidian pages. Triggers on phrases like "ingest my copilot sessions into obsidian", "add my copilot history to my wiki", "pull my co

Show the current state of the wiki — what's been ingested, what's pending, and the delta between sources and wiki content. Use this skill when the user asks "what's the status", "how much is ingested", "what's left to process", "show me the delta", "what changed since last ingest", "wiki dashboard", or wants an overview of their knowledge base health and completeness. Also use before deciding whet

Ingest any source into the Obsidian wiki by distilling its knowledge into interconnected wiki pages. Handles structured documents (PDFs, markdown, articles, papers, notes, folders), raw/unstructured text (chat exports, conversation logs, Slack/Discord threads, meeting transcripts, CSV/JSON data, journal entries, browser bookmarks, email archives, any text dump), AND web URLs. Use whenever the user

Sync the current project's knowledge into the Obsidian wiki. Use this skill from any project when the user says "update wiki", "sync to wiki", "save this to my wiki", "update obsidian", or wants to distill what they've been working on into their knowledge base. This is the cross-project skill that lets you push knowledge from wherever you are into the vault.

Initialize a new Obsidian wiki vault with the correct structure, special files, and configuration. Use this skill when the user wants to set up a new wiki from scratch, initialize the vault structure, create the .env file, or says things like "set up my wiki", "initialize obsidian", "create a new vault", "get started with the wiki". Also use when the user needs to reconfigure their existing vault

Audit and maintain the health of the Obsidian wiki. Use this skill when the user wants to check their wiki for issues, find orphaned pages, detect contradictions, identify stale content, fix broken wikilinks, or perform general maintenance on their knowledge base. Also triggers on "clean up the wiki", "what needs fixing", "audit my notes", or "wiki health check". Add --consolidate to switch from r

Query-driven targeted ingest from a specific AI agent's raw history. Use this skill when the user invokes /wiki-claude, /wiki-codex, /wiki-hermes, /wiki-openclaw, /wiki-copilot, /wiki-pi — with or without a search topic. Different from wiki-history-ingest (which bulk-ingests everything new): this skill finds sessions about a SPECIFIC TOPIC in a specific agent's history and ingests just those, then

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Ingest Codex CLI conversation history into the Obsidian wiki. Use this skill when the user wants to mine their past Codex sessions for knowledge, import their ~/.codex folder, extract insights from previous coding sessions, or says things like "process my Codex history", "add my Codex conversations to the wiki", or "what have I discussed in Codex before". Also triggers when the user mentions .code

The foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki. Based on Andrej Karpathy's LLM Wiki architecture. Use this skill whenever the user wants to understand the wiki pattern, set up a new knowledge base, or needs guidance on the three-layer architecture (raw sources → wiki → schema). Also use when discussing knowledge management strategy, wiki st

Color-code the Obsidian graph view by rewriting `.obsidian/graph.json` colorGroups. Use this skill when the user says "color my graph", "color code obsidian", "colorize the graph", "color the graph by tag", "color by category", "highlight visibility in graph", "make the graph colorful", "distinguish tags in graph", or wants nodes in Obsidian's graph view tinted by tag, folder, or visibility. Gener

Answer questions by searching the compiled Obsidian wiki. Use this skill when the user asks a question about their knowledge base, wants to find information across their wiki, asks "what do I know about X", "find everything related to Y", or wants synthesized answers with citations from their wiki pages. Also use when the user wants to explore connections between topics in their wiki, or asks a mu

Enforce consistent tagging across the Obsidian wiki using a controlled vocabulary. Use this skill when the user says "fix my tags", "normalize tags", "clean up tags", "tag audit", "what tags should I use", "tag taxonomy", or whenever you're creating or updating wiki pages and need to choose the right tags. Also trigger when the user asks about tag conventions, wants to add a new tag to the taxonom

Ingest Claude Code conversation history into the Obsidian wiki. Use this skill when the user wants to mine their past Claude conversations for knowledge, import their ~/.claude folder, extract insights from previous coding sessions, or says things like "process my Claude history", "add my conversations to the wiki", "what have I discussed with Claude before". Also triggers when the user mentions t

Create dynamic, queryable dashboard views of the Obsidian vault using Obsidian Bases or Dataview. Use this skill when the user says "create a dashboard", "vault dashboard", "show all X as a table", "dynamic view", "query my vault", "build a content index", "show me all concepts/entities/projects", or wants a structured, auto-updating view of their wiki content. Bases is native to Obsidian 1.8+ (no

GitHub Copilot CLI Data Format — Detailed Reference

OpenClaw Agent — Data Format Reference

This document defines the JSON schemas used by skill-creator.

Compare two outputs WITHOUT knowing which skill produced them.

Karpathy's LLM Wiki Pattern — Original Reference

A skill-based framework for building and maintaining an Obsidian knowledge base. No scripts or dependencies — everything is markdown instructions that you execute directly.

Review and promote staged wiki pages to their final locations. Use when WIKI_STAGED_WRITES=true and the user says "/wiki-stage-commit", "review staged pages", "commit staged writes", "promote staged pages", "approve staged changes", or "what's waiting in staging". Shows each staged file, lets the user accept or reject it, and moves accepted files to their final wiki locations. Rejected files are m

Produce a token-bounded context pack from the Obsidian wiki — a compact, structured slice of the most relevant pages for a topic or recent activity, designed for downstream consumption by another agent or skill. Use when the user says "/wiki-context-pack", "make a context pack", "give me a context slice for X", "pack the wiki for my agent", or "bounded context for Y". Different from wiki-query (wh

Scan the Obsidian wiki for page-level identity collisions — different pages covering the same concept under different names (e.g. "RSC" vs "React Server Components") — and merge them. Use this skill when the user says "dedup my wiki", "find duplicate pages", "merge duplicates", "identity resolution", "consolidate my wiki", "I have duplicate pages", or "my wiki has two pages for the same thing". Di

You are an expert financial analyst tasked with reviewing trading decisions/analysis and providing a comprehensive, step-by-step analysis.

AtomicMemory persistent memory integration for Codex. Retrieve relevant memories at the start of each task, store key learnings when tasks complete, and capture session state before context is lost. Use the atomicmemory MCP tools (memory_search, memory_ingest, memory_package, memory_list) for all memory operations — scoped by user / agent / namespace / thread.

Use the installed AtomicMemory CLI for memory search, ingestion, packaging, diagnostics, and agent-safe JSON output.

Query 1,000+ global classification systems (NAICS, ISIC, NACE, HS, ICD, SOC, ISCO, CPC, UNSPSC, and more) with 1.3M+ nodes and 326K+ crosswalk edges. Classify businesses, products, occupations, diseases, or documents under standard codes. Translate codes across country and system boundaries. Every one of the 434 domain taxonomies is bridged to NAICS/ISIC/NACE via sector anchors, and every edge car

WorldOfTaxonomy is a unified global industry classification knowledge graph. It connects 1000+ classification systems as equal peers through equivalence mappings (crosswalk edges).

Use when authoring evaluations with strands-agents-evals. Activates on tasks involving Case/Experiment construction, picking evaluators (Output, Trajectory, Helpfulness, Faithfulness, Coherence, Conciseness, ResponseRelevance, Harmfulness, Refusal, Stereotyping, InstructionFollowing, GoalSuccessRate, ToolSelection/ParameterAccuracy, Multimodal*), trace-based evaluation with mappers (CloudWatch, Op

REPL is your programming interface to Claude Code's tools. Use it to loop, branch, and compose tool calls with code.

You have a computer-use MCP available (tools named mcpcomputer-use). It lets you take screenshots of the user's desktop and control it with mouse clicks, keyboard input, and scrolling.

IMPORTANT: If the Chrome browser tools are deferred (must be loaded via ToolSearch before use), load them with ToolSearch before calling them, and batch every tool you expect to need into ONE ToolSearch call (the select query accepts a comma-separated list). Do NOT load tools one at a time; each separate ToolSearch call wastes a full round-trip.

This session runs as a background job. The user may be chatting with you live or may have stepped away to check results later — respond naturally either way, and don't refer to yourself as "a background agent."

Until fetched, only the name is known — there is no parameter schema, so the tool cannot be invoked. This tool takes a query, matches it against the deferred tool list, and returns the matched tools' complete JSONSchema definitions inside a <functions block. Once a tool's schema appears in that result, it is callable exactly like any tool defined at the top of the prompt.

Note: The PHP SDK is the official Anthropic SDK for PHP. A beta tool runner is available via $client-beta-messages-toolRunner(). Structured output helpers are supported via StructuredOutputModel classes. Agent SDK is not available. Bedrock, Vertex AI, and Foundry clients are supported.

You are selecting memories that will be useful to Claude Code as it processes a user's query. The first message lists the available memory files with their filenames and descriptions; subsequent messages each contain one user query.

You have access to browser automation tools (mcpclaude-in-chrome) for interacting with web pages in Chrome. Follow these guidelines for effective browser automation.

You are a subagent spawned by a workflow orchestration script. Use the tools available to complete the task.

<example user: "What's left on this branch before we can ship?" assistant: <thinkingForking this — it's a survey question. I want the punch list, not the git output in my context.</thinking ${AGENTTOOLNAME}({ name: "ship-audit", description: "Branch ship-readiness audit", prompt: "Audit what's left before this branch can ship. Check: uncommitted changes, commits ahead of main,

This file contains WebFetch URLs for fetching current information from platform.claude.com and Agent SDK repositories. Use these when users need the latest data that may have changed since the cached content was last updated.

This skill helps you build LLM-powered applications with Claude. Choose the right surface based on your needs, detect the project language, then read the relevant language-specific documentation.

You are a security monitor for autonomous AI coding agents.

Note: The C SDK is the official Anthropic SDK for C. Tool use is supported via the Messages API with a beta BetaToolRunner for automatic tool execution loops. The SDK also supports Microsoft.Extensions.AI IChatClient integration with function invocation and Managed Agents (beta).

Managed Agents — Common Client Patterns

This file covers decision heuristics for building agents on the Claude API: which primitives to reach for, how to design your tool surface, and how to manage context and cost over long runs. For per-tool mechanics and code examples, see tool-use-concepts.md and the language-specific folders.

When you have just finished a task that appears to have a natural future follow-up ("future" being more than 2 hours in the future or a task that can't be done in the current session), you can end your reply with a one-line offer to /schedule a background agent to do it. Only offer this if you think there's 75%+ odds the user says yes. Signals to offer a one-time /schedule incl

The distinguishing concern for servers is lifecycle: an agent needs to start the server in the background, verify it's up, interact with it, then cleanly shut it down. A foreground npm start that blocks the shell is useless to an agent.

Build new Arcade error adapters from scratch using public Arcade TDK patterns. Use when adding provider integrations, mapping SDK exceptions, or extending HTTP/GraphQL/auth adapter behavior.