doc-claude-md
Create and update CLAUDE.md and AGENTS.md files. Use when: (1) setting up Claude documentation for a project, (2) updating agent instructions after codebase…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-12 00:15
Agents & models
26,152 results
dev-skill-create
Guide for creating effective skills. Use when: creating a new skill, updating an existing skill, extending Claude's capabilities with specialized knowledge or…
fabric-advisor
Starts a persistent Pi Fabric peer advisor that reviews the main agent at decision points and surfaces only concrete, material advice. Use for ambient…
fabric-fusion
Multi-model deliberation. Two to 8 distinct models answer in parallel with web-capable tools, then a judge compares consensus, contradictions, coverage gaps,…
fabric-rlm
Recursively decomposes oversized tasks into bounded child Pi agents with fresh context windows. Use for whole-repo audits, massive-context analysis, and…
sample-plugin
Sample plugin demonstrating the Skills + Tools model. Includes a Python tool (greeting) and a TypeScript tool (calculator).
agent-core-review
Use ONLY for code review and test write/review guidance in `packages/agent-core-v2` (the DI × Scope agent engine). Does NOT apply to the legacy…
plan-quest
Scope, create, and publish a quest through an interactive grilling interview. Use when the user invokes /plan-quest, asks to plan a quest, or wants unsettled…
audit-mcp-tool-friction
Diagnose malformed calls, retries, and unusable results after an agent selects an MCP tool.
learn-from-math-agent-trajectories
Review mathematical agent trajectories for evidence-backed Jacobian improvements; do not resume solving.
agent-plugin-dev
Cross-platform Agent plugin development factory. When users need to create/develop Claude Code plugins (Agent/Skill/Hook), OpenCode plugins, PI extensions, or Codex plugins, this Skill must be used. Users say "want to develop a plugin", "make an Agent", "write a Skill", "configure…
booth
Booth coordinates parallel Claude Code sessions (decks) through a daemon. Provides signal meanings, check flow, report format, and deck lifecycle context.…
chrome-profile-bridge
Enhanced browser automation with Chrome profile targeting. Use this skill BEFORE playwright-cli when the user needs to work with a specific Chrome profile…
ctx
Sets up and orchestrates a ctx knowledge base — a lean, living single source of truth for multi-session AI-agent work — and classifies any doc or finding by…
ctx-merge
Converges many scattered sources — dated research notes, subagent outputs, audit reports, revision cycles — into one living source of truth without silently…
agent-email-inbox
Use when building any system where email content triggers actions — AI agent inboxes, automated support handlers, email-to-task pipelines, or any workflow…
openspec-brainstorm
You MUST use this before creative OpenSpec work - creating features, building components, adding functionality, or modifying behavior. Explores user intent,…
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…
conductor
Workflow architect that decomposes complex tasks, maximizing local Ollama model leverage via llm-orc while maintaining quality through reflective evaluation.
hyday-whiteboard
Create, edit, and lay out Hyday whiteboards through the hyday-whiteboard MCP server. Use when the user mentions whiteboard, canvas, board, sticky note, group,…
protect-mcp-server-with-policies
Protect an MCP server by applying a policy from the catalog. Handles multiple starting points: from an existing API Manager instance, from an MCP server…
run-agent-scan-and-view-results
Executes an agent scanner and views the discovered AI agents. Use when running an agent scan, checking scan status, viewing scan history, reviewing discovered…
agent-lens
Agent Lens: Real-time observability dashboard for multi-agent Claude Code sessions. Visualize agent interactions, tool usage, and session flows through a…
cc-pai-optimiser
Review and optimize PAI (Personal AI Infrastructure) codebases as Claude Code evolves. Use when analyzing PAI repositories against 12-factor agent principles,…