This skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Guides discovery of local skills and enforces minimal documentation style.

AI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI, LangGraph, and custom agents. Use when designing or implementing AI agents.

Query Claude Code session analytics from ccrecall database. Use when user asks about token usage, session history, or wants to analyze their Claude Code usage patterns.

List all built-in Claude Code tools

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).

A skill restricted to Claude Code only

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human.

Use to generate or refresh a layered CLAUDE.md hierarchy (lean root + per-subdir) for a large codebase. "Set up CLAUDE.md files", "scaffold context files", "make this repo legible to Claude Code", "add directory-scoped conventions".

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, code review, or automated editing

This skill should be used when the user asks to "find codex session", "codex session context", "lookup codex session", "show codex history", "codex session summary", or provides a Codex session UUID. Finds and summarizes OpenAI Codex session files from ~/.codex/sessions/.

Systematic competitive intelligence with parallel agent analysis. Analyzes competitors thoroughly and synthesizes into actionable insights.

Compresses prompts/skills into minimal goal-focused instructions. Trusts the model, drops what it already knows, maximizes action space. Use when asked to compress, condense, or minimize a prompt.

Manage Claude Code sessions effectively. Use during long sessions, multi-step tasks, or when responses start degrading. Covers /clear, checklists, and subagents.

Convert GitHub issues to discussions using agent-browser. Use when asked to convert, move, or change an issue to a discussion. Requires agent-browser installed and user to log in via headed browser.

Create a new Claude Code agent with proper YAML frontmatter structure. Use when the user wants to add a specialized agent to a plugin. Handles agent file creation with name, description, tools, model selection, and color configuration.

Expert guide for defining, creating, and invoking custom subagents in Gemini CLI. Trigger this skill when the user wants to create a new specialist agent, define a custom subagent, or learn how to delegate tasks to specialist agents within the Gemini CLI environment.

Cross-post blog content to social platforms. Crier is MCP-native; the tools handle mechanics while this skill provides judgment context they can't: rewrite guidelines, platform culture, workflow tips.

Offloading tasks with a well-defined scope to sub-agents, for instance to use a sub-agent to implement a set of specs. Use this skill whenever a task should not need a broad knowledge of the whole project

Break down a Claude Code plan into Linear sub-issues with E2E test criteria. Use when: user says "decompose", "break down plan", "create issues from plan", or after completing a plan that needs to be tracked in Linear. Each sub-issue is self-contained (completable in one Claude Code session) and testable from the user's perspective.

Run a multi-agent review-readiness pass on a nearly finished change before commit; fan out parallel review agents across rule conformance, type safety, and overengineering, then synthesize and apply the worthwhile fixes.

Use when agent instruction files (AGENTS.md, rules/) need analysis, trimming, or restructuring. Orchestrates /imperatives → /policy-algebra → /visualize into a distillation pipeline.

Use when the user wants to export a Claude Code session transcript as a readable Markdown file — converts the current session (or a specified transcript path) into GitHub-flavored Markdown with metadata header, collapsible tool results, and thinking blocks

Use Gemini AI for research, analysis, summarization, web search, and complex reasoning. Use when you need AI-powered research, code analysis, content summarization, or web search with synthesis.

# GlobePilot AI Agent 2 - powered by Teneo Protocol

Define success criteria instead of step-by-step instructions. Enables autonomous LLM iteration toward testable goals.

Initialise a git repository with optional agent commit instructions and .gitignore. Use when users say "here be git", "init git", "initialise git", or otherwise indicate they want to set up version control in the current directory.

Build and query AI-powered knowledge bases from claude-mem observations. Use when users want to create focused "brains" from their observation history, ask questions about past work patterns, or compile expertise on specific topics.

Work with markdown-based task lists in .llm/todo.md files. Use when managing tasks, working with todo lists, extracting incomplete tasks, marking tasks complete, or implementing tasks from a task list.

Debug MCP server communication. Use for troubleshooting MCP integrations, viewing traffic, and analyzing latency.

Use when finishing a Pi, Codex, or other coding-agent session and wanting to save a lean Markdown session note into an Obsidian vault with decisions, code changes, validation, caveats, and follow-ups.

# Microsoft 365 Operations (MCP-by-Code)

Skills for querying ontologies using the Ontology Access Kit (OAK). This should only be used for complex ontology operations, for basic external ontology searching use the OLS MCP

Multi-agent ensemble planning with pl4n CLI. Use when discussing implementation plans, task planning, or when user mentions pl4n sessions. Knows pl4n CLI syntax and workflow.

A test skill with prompt injection patterns

Minify verbose prompts into semantically equivalent minimal prompts while preserving behavior. Supports configurable output modes (prompt-only or prompt + compression report).

Propose structured interpretations of underspecified requests. Use when a user's request is vague or incomplete but reasonable assumptions can be made. Rapidly prototypes intent by restating, structuring, and committing to a next action.

Download the persistent memory database from your self-hosted dashboard into the current repo. Use after cloning a repo on a new machine to restore accumulated sessions, knowledge, facts, and embeddings for RAG/context.

Multi-agent orchestration for Radicle plans — worktree isolation, task dispatch, CLAIM/SIGNAL conventions, and context feedback loops. Use when dispatching tasks to workers, launching worktree agents, or evaluating multi-agent progress.

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, ...

Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches cipherpowers:code-review-agent subagent to review implementation against plan or requirements before proceeding

Resume an interrupted research-agent run. Re-launches the researcher with instructions to read .research/state.md and log.md, reorient, and continue from the documented current focus. Use after a context compression, session restart, or explicit pause.

Collaborative code review using Agent Teams where reviewers discuss findings, challenge each other, and converge on a unified assessment. Evolves dm-work:review from isolated parallel reviewers to a review team.

Use when the user wants to review a Claude Code session for quality — analyzes the current session (or a specified transcript path) for prompting effectiveness, agent performance, and environment gaps, producing actionable recommendations

9 principles for writing effective rules that maximize LLM execution accuracy. Use when creating or modifying skills, agent prompts, or command instructions.

YAML frontmatter schemas for Claude Code agents and commands. Use when creating or validating agent/command files.

Auto-generates project.md from codebase analysis (package.json, README.md, git remote). Creates a 2-3 sentence project concept that is injected every prompt for drift prevention. Use when project.md doesn't exist or needs updating. Invoke with /setup-project.

Use the skill-hub CLI to search, install, update, and publish agent skills from skill-hub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed skill-hub CLI.

Route ordinary init, review, and security requests to Claude-native capabilities first; escalate to Octopus only when multi-LLM diversity adds value

Validates agent skill definitions against agentskills.io and AGENTS.md rules. Use when creating or modifying skills to ensure they are machine-readable and documentation-complete.

Add or update skills in a skills repository for Codex and/or Claude Code. Use when creating new skills, packaging .skill files for Codex, or converting a skill into a Claude Code plugin (marketplace.json + plugin.json).

Guide for efficient agent orchestration during implementation to conserve main agent context

This skill should be used when working with built-in TaskList tools (TaskCreate, TaskUpdate, TaskList, TaskGet) to track execution progress within and across Claude Code sessions.

Drucker-inspired leadership framework for managing agent teams. Invoke when coordinating multi-agent work, delegating tasks, or making strategic decisions as team lead.

Updates merge request descriptions in GitLab by summarizing MR changes into a bulleted list, excluding changes under docs/. Use when updating an MR description via glab MCP or glab CLI, or when the user asks to summarize MR changes for the description.

Use when researching library documentation with Context7 MCP tools for official patterns and best practices

Use when user has complex multi-agent workflows, needs to coordinate sequential or parallel agent execution, wants workflow visualization and control, or mentions automating repetitive multi-agent processes - guides discovery and usage of the orchestration system

Use when user has complex multi-agent workflows, needs to coordinate sequential or parallel agent execution, wants workflow visualization and control, or mentions automating repetitive multi-agent processes - guides discovery and usage of the orchestration system

Extract durable working preferences from recent Cursor chats and convert them into skills, rules, or workflow docs. Use when asked to learn preferences, mine feedback, personalize workflows, or generate team/person-specific agent guidance.

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

MUST be loaded before creating, editing, or reviewing any SKILL.md, agent markdown, or command markdown file. Contains formatting rules that prevent common mistakes like numbered steps, which cause git churn. Also use when the user asks about instruction formatting best practices, header structure, or how to avoid unnecessary diffs.

Create implementation plans with tasks grouped by subsystem. Related tasks share agent context; groups parallelize across subsystems.

Publish static files or directories to wzrrd.sh. Use for sharing agent-built pages, demos, receipts, docs, diagrams, or static artifacts at https://<slug>.wzrrd.sh/.

Agent artifact placement conventions. Use when creating plans, tasks, research, reviews, brainstorms, or any agent-generated files. Ensures artifacts go to docs/.claude/ (gitignored) instead of polluting the repo.

ALWAYS check this skill before using grep, glob, Task tool, or doing any codebase exploration. Guides you to use specialized agents that are more efficient than basic tools.

Automates browser interactions for form filling and web page interaction. Used by the request-website command to submit website indexing requests.

Real-time monitoring of Claude Code sub-agent activity in a tabbed terminal interface. Auto-spawns as soon as any sub-agent starts running.

Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool ...

Calculate AI feature costs and challenge if you actually need it. Invokes ai-cost-analyzer agent for detailed economics modeling.

AI product engineering covering LLM integration patterns, RAG architecture, prompt engineering, and production AI systems. Use when building AI-powered product features or shipping LLM applications.

This skill should be used when the user asks to "consolidate notes", "summarize ainotes", "clean up notes", "ainotes", or wants to consolidate accumulated agent observations into a compact summary.

Deep code analysis using consultant agent. Identifies technical debt, risks, and improvement opportunities.

Use when reviewing permission prompt frequency, optimizing the allow-list, or resetting the audit log. Triggers on "audit permissions", "permission report", "allow list", "reduce prompts", "what's getting prompted".

# Autonomous Testing Agent

Task Analyzer for the Buddy orchestrator. Breaks a software task into structured sub-tasks, classifies task type, identifies technologies and affected files, and determines which MCP servers are needed.

Prompt Enhancer for the Buddy orchestrator. Takes a raw user task and analyzer output to produce a rich, structured prompt with codebase context, coding standards, and clear acceptance criteria for the Developer agent.

Researcher agent for the Buddy orchestrator. Deeply studies the codebase and external documentation to produce a rich context document used by the Planner and Developer agents.

# CAD Agent

Discover agent-native CLIs for professional software. Access the live catalog to find tools for creative workflows, productivity, AI, and more.

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing

Detects passive-approval streaks in Claude Code sessions and prints a short checkpoint nudge so you notice when you may be rubber-stamping AI suggestions. The hook runs automatically on every UserPromptSubmit; this skill exists for documentation and runtime tuning.

View what all active Claude Code sessions are doing and optionally send instructions to them via inbox

Use for systematic debugging and root cause analysis with both Codex and Gemini. Triggers on "council debug", "council root cause", "have council investigate this bug", "council find the issue".

Use for deep multi-step investigation and analysis with both Codex and Gemini. Triggers on "council deep analysis", "investigate with council", "council thorough investigation", "have the council think deeply".

Use this skill when you need to set up validation for AI agent skills in a Dart project for the first time. Adds the linter as a dev_dependency, creates a configuration file, and generates a baseline for legacy repos.

Use this skill when you need to validate AI agent skills with dart_skills_lint — running the linter, interpreting failures, fixing violations, and authoring custom rules.

Calculate weighted risk scores from specialist agent reports. Use when synthesizing multiple due diligence reports into an overall investment risk assessment.

Export RepoPrompt context for external LLM review (ChatGPT, Claude web, etc.). Use when you want to review code or plans with an external model. Triggers on /flow-next:export-context.

Guide on how to control a Flutter app using flutter_driver via MCP and capture screenshots.

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

Manage GitHub issues, PRs, branches, and repositories via OAuth (3LO). For reading issues or PR details, not for deep code analysis — delegate that to code-agent.

Search real-time news with bias scoring, get live stock/ETF/crypto data with AI analysis, ML options pricing, balanced news synthesis, and meme search via the Helium MCP server.

Show MCP integration status. Use when: checking active connectors, available integrations, or skill unlocks.

LLM fine-tuning expert for LoRA, QLoRA, dataset preparation, and training optimization

LLM-powered quality verification using prompt hooks. Validates commit messages, code patterns, and conventions using AI before allowing operations. Use to set up intelligent guardrails.

Use when the user wants to set up Ollama for SiftCoder, reduce token costs, or troubleshoot local-LLM drain/embedding issues. Covers install, model selection, env wiring, and verification.

Skills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions directly about the code docs.