Guides the agent through the Capgo CLI command surface and routes requests to more specific Capgo skills. Use when the user asks generally about the Capgo CLI, app setup, diagnostics, OTA operations, native builds, or organization commands. Do not use when a more specific Capgo skill already clearly matches the request.

Guides the agent through Capgo account lookup and organization administration. Use when listing organizations, managing members, changing security settings, or working with organization-level CLI commands. Do not use for OTA bundle uploads or native builds.

Guides the agent through Capgo OTA release workflows including bundle uploads, compatibility checks, channels, cleanup, and encryption key setup. Use when managing Capgo bundle and channel operations. Do not use for native build requests or organization administration.

Always search before starting any work across all coding agent session histories (Claude Code, Codex, Cursor, Gemini CLI, Aider, ChatGPT) to find whatever we've discussed before.

Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to `--slim` mode (MCP configuration).

# Claude Code Plugins Quick Reference

Charge la documentation Claude Code depuis docs.claude.com dans des fichiers markdown locaux

Run codex MCP plugins.

Create a custom agent (.agent.md) for a specific job.

Create a reusable prompt file (.prompt.md) for a common task.

Print a summary of the Cyrus setup and offer to start the agent.

Debug workflow execution issues including syntax errors, agent failures, variable problems, and execution errors. Use when workflows fail, produce unexpected results, or user asks for debugging help.

Debug workflow execution issues including syntax errors, agent failures, variable problems, and execution errors. Use when workflows fail, produce unexpected results, or user asks for debugging help.

Decomposes and reorganizes agent memory files into focused, single-purpose components. Use when memory has large multi-topic blocks, redundancy, or poor organization. Trigger phrases: "defrag memory", "reorganize memory", "clean up memory files", "split memory blocks".

Guides through adding new features, MCP tools, analyzers, and extending the patent creator system.

Internal format specification for the DLN system. Only relevant when preloaded by the dln-sync agent via the skills frontmatter field. Never activated by user prompts. Defines the re-anchor payload compression template that dln-sync uses to convert raw Notion page-body read-backs into compact structured summaries for DLN teaching skills.

Read and extract content from web pages through a locally connected Chrome browser using Dokobot local bridge only. Use when an agent needs JavaScript-rendered pages, logged-in browser content, or pages that block headless scrapers and should be handled entirely through the user's local browser.

Guide to spences10's Claude Code ecosystem tools. Use when user asks which tool to use, how tools relate, or needs help choosing between MCP servers, skills, or CLIs.

Orchestrate F1 test drives to validate the Cyrus agent system end-to-end across issue-tracker, EdgeWorker, and activity rendering.

Run the Gemini file processor on any folder — extracts content from PDF, PPTX, XLSX, DOCX, CSV, JSON, and any text format, then generates Obsidian-ready summaries. Use when asked to "summarise this folder", "run file intel", "process these files", or a folder path is provided and summaries are needed.

Gemini CLI for one-shot Q&A, summaries, and generation.

Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.

Gemini CLI for one-shot Q&A, summaries, and generation.

This skill should be used when invoking the Gemini CLI for code review, plan review, or any prompt-based task. It provides correct invocation patterns emphasizing stdin piping and @ syntax over shell variable gymnastics.

Analyse une codebase ou documentation avec Gemini (1M tokens)

Recherche temps réel via Google Search intégré à Gemini

Délègue un problème complexe à Gemini Deep Think

Run hooks and create clean, logical commits via the commit-craft agent.

Create and manage GitHub repositories, branches, commits, and PRs via local git commands and GitHub MCP. Use when the user asks to create a repo, push code, get repo info, manage branches, open PRs, or work with GitHub repositories.

Integrate GrepAI with Cursor IDE via MCP. Use this skill to enable semantic code search in Cursor.

Install and configure Ollama for local embeddings with GrepAI. Use this skill when setting up private, local embedding generation.

Compact the current conversation into a handoff document for another agent to pick up.

Compact the current conversation into a handoff document for another agent to pick up.

Create a handoff document for the current conversation, ready for another agent to pick up.

Compact the current conversation into a handoff document for another agent to pick up.

Internal helper contract for calling the hermes-companion runtime from Claude Code

Orchestrate implementation of spec-workflow tasks. Use when user says "implement the spec", "execute spec tasks", "run the spec workflow", "implement spec-name tasks", or needs to coordinate agent execution for spec-workflow documents.

Initialize a new Ruflo project with MCP tools, hooks, and agent configuration

Register a Cognitum Seed device by endpoint and establish agent bridge

Document both INPUT and OUTPUT JSON schemas for LLM-driven features to prevent data flow confusion

Run Ruflo background workers using Claude Code native /loop scheduling

Use Apify Actors for scraping/data acquisition pipelines. Use when data collection from websites is required and needs repeatable runs.

Defragment and reorganize agent memory files: split bloated files, merge duplicates, remove stale information, and restructure the memory hierarchy. Use when memory files have grown unwieldy, contain redundancies, or need reorganization. Run periodically (weekly) or on demand.

Use when you need to query SiftCoder's persistent project memory across sessions. Provides MCP tools mem_search, mem_get, mem_timeline, mem_why, mem_drain. Triggers when the user asks "what did we decide about X", "why is X this way", "find prior discussion of X", "show me the history of Y".

Run the PinchTab cold-start test. Spawns a subagent that follows tests/coldstart/subagent-context.md to validate the documented first-install user journey. Use when asked to 'run cold start', 'cold-start test', or 'test the agent onboarding flow'.

Transcribe podcast episodes from RSS feeds using Gemini Flash

Run the full pre-PR verification routine (format, lint, tests, type/package checks, coverage) in an isolated subagent so the main thread stays clean. Invoke this after a gh pr create is blocked by the pre-tool-use hook; report ready or unready back to the main thread.

PUA flavor alias for Codex. Codex subcommand mapping for Claude Code /pua:flavor style usage; invoke with $pua-flavor.

PUA KPI alias for Codex. Codex subcommand mapping for Claude Code /pua:kpi style usage; invoke with $pua-kpi.

PUA Loop alias for Codex. Codex subcommand mapping for Claude Code /pua:loop style usage; invoke with $pua-loop.

PUA mama alias for Codex. Codex subcommand mapping for Claude Code /pua:mama style usage; invoke with $pua-mama.

PUA off alias for Codex. Codex subcommand mapping for Claude Code /pua:off style usage; invoke with $pua-off.

PUA offline alias for Codex. Codex subcommand mapping for Claude Code /pua:offline style usage; invoke with $pua-offline.

PUA on alias for Codex. Codex subcommand mapping for Claude Code /pua:on style usage; invoke with $pua-on.

PUA P10 alias for Codex. Codex subcommand mapping for Claude Code /pua:p10 style usage; invoke with $pua-p10.

PUA P7 alias for Codex. Codex subcommand mapping for Claude Code /pua:p7 style usage; invoke with $pua-p7.

PUA P9 alias for Codex. Codex subcommand mapping for Claude Code /pua:p9 style usage; invoke with $pua-p9.

PUA Pro alias for Codex. Codex subcommand mapping for Claude Code /pua:pro style usage; invoke with $pua-pro.

PUA reap-orphans alias for Codex. Codex subcommand mapping for Claude Code /pua:reap-orphans style usage; invoke with $pua-reap-orphans.

PUA survey alias for Codex. Codex subcommand mapping for Claude Code /pua:survey style usage; invoke with $pua-survey.

PUA team status alias for Codex. Codex subcommand mapping for Claude Code /pua:team-status style usage; invoke with $pua-team-status.

PUA teardown alias for Codex. Codex subcommand mapping for Claude Code /pua:teardown-all style usage; invoke with $pua-teardown-all.

PUA yes alias for Codex. Codex subcommand mapping for Claude Code /pua:yes style usage; invoke with $pua-yes.

Create PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents, creating chat systems, or integrating LLMs with Pydantic validation.

RAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval optimization. Use when building RAG systems.

Structured remediation loop for code review findings. After a reviewer agent returns HIGH+ severity findings, dispatch a targeted fix agent, then re-review. Bounded to 2 cycles to prevent infinite loops. Use when code review or verification surfaces issues that need fixing before completion.

Deep research with structured reports and charts. ONLY use when the user explicitly requests research/analysis, or needs data visualization with charts, or quantitative/comparative analysis across multiple sources. Do NOT use for simple questions or quick lookups.

Review and analyze LLM prompts against prompt-engineering principles. Provides detailed assessment without modifying files.

Safety/risk review for agent actions — the backpressure layer that gates side effects (secrets, external publishing, destructive repo changes, expensive ops) behind human approval inside a Smithers workflow. Use when a workflow performs outward-facing or irreversible actions.

Scan repositories and identify issues that Claude Code can efficiently handle

Search via Firecrawl MCP using mcporter.

Use when setting up shell environment for Claude Code - installs zsh, Oh My Zsh, Powerlevel10k theme, MesloLGS NF fonts, Claude CLI completions, and productivity aliases

This skill should be used when the user asks to "share this session", "upload transcript", "create gist", "share conversation", or wants to publish the current Claude Code session as a GitHub Gist.

Use when the user says "silly sausage", "silly-sausage", invokes /silly-sausage, or expresses lighthearted exasperation at a mistake the agent made. Also triggers on the phrase appearing anywhere in user input — no slash required.

Identifies and manages execution dependencies between agent skills by analyzing their inputs and outputs. Use when building multi-step agent workflows to ensure skills are executed in the correct order and that all required data is available.

Create, update, and manage Claude Code skills. Use when working with SKILL.md files, slash commands, or extending Claude's capabilities.

Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.

Audit locally installed agent skills for security/policy issues using the SkillLens CLI (`skilllens scan`, `skilllens config`). Use when asked to scan a skills directory (Codex/Claude) and produce a risk-focused audit report based on each skill's `SKILL.md` and bundled resources.

Start the Wasp dev server and set up full debugging visibility. This includes running the server (with access to logs), and connecting browser console access so the agent can see client-side errors. Essential for any development or debugging work.

Initialize a multi-agent swarm with anti-drift configuration

Multi-agent swarm coordination for large tasks

Force a research-agent run to conclude. Launches the researcher in synthesis mode: it reads state.md and log.md, writes .research/synthesis.md with outcome, key findings, failed approaches, open questions, and recommendations, then exits. Use when current results are good enough or the agent is stalling.

Socratic teaching loop for any Claude Code session — quiz yourself on what actually happened, confirm mastery item by item, and don't finish until everything's locked in

Activate when you are a teammate in an Agent Teams configuration. Establishes teammate protocol with file ownership, self-claiming tasks, inter-agent communication, quality gates, and escalation.

Deep multi-framework reasoning using Gemini. Use for complex problem analysis, challenging ideas, and evaluating multiple options with structured thinking.

Toggle Claude Code plugins enabled/disabled per project.

Diagnoses and resolves MCP server registration failures, GPU detection, BigQuery authentication, index build failures, import errors, search quality issues, and performance problems.

Use to decide what kind of generic agent you should use

Educational agent for WCAG 3.0 (W3C Accessibility Guidelines). Explains methodology changes, outcome-based conformance, the APCA contrast algorithm, functional needs categories, and new cognitive/task-based criteria. Helps teams plan for the transition from WCAG 2.2 to 3.0. WCAG 3.0 is in early draft — this agent clearly communicates its draft status.

Add, review, or remove inline custom scripts on a Webflow site (up to 10,000 chars). Use for analytics, tracking pixels, chat widgets, or any custom JavaScript. Also manages page-level scripts.

Why build on Ethereum specifically. The AI agent angle — ERC-8004, x402, composability, permissionless deployment. Use when a user asks "should I build on Ethereum?", "why blockchain?", or when an agent needs to recommend a chain for a project.

Use when executing multi-step processes requiring state persistence and agent coordination - defines two-tier protocol where subagents report PASS/FAIL status and main agent handles dispatch, advancement, and failure troubleshooting

Guide and workflow for WorldArchitect.AI MCP Server Usage. Use when you need WorldArchitect.AI MCP Server Usage.

Transcribe YouTube videos and playlists using Gemini Flash

Facilitates a single point of ingress for any and all tasks. Used when pulling a new `inbox` task from the 33god plane workspace, or any prompt that explicitly or implicitly describes a non-trivial task. Triggered by `add a feature`, `task.inbox.new` event.

Shared agent context — work attribution, safety rules, and development principles. Loaded by all plugin agents via skills: frontmatter.