# CAD Agent

Task tracking for async/multi-step work. Use dex to create, track, and complete tasks that span multiple sessions or require coordination (e.g., coding agent dispatches, PR reviews, background jobs). Tasks stored as JSON files in .dex/tasks/.

Extract conversation transcripts from AI coding session logs (Clawdbot, Claude Code, Codex). Use when asked to export prompt history, session logs, or transcripts from .jsonl session files.

Cache and restore agent data efficiently

# MCP Skill

# Apple Docs MCP Skill

Mistakenly published, don't know how to unpublish ;(

Drives iOS/Android mobile devices via Appium MCP. Use for verifying mobile bugs, E2E tests, and navigating real device clouds (LambdaTest/BrowserStack).

Append a structured learning entry to AGENTS_LEARNING.md whenever an AI agent makes a mistake. Auto-activates as a composite skill when: a pre-write skill violation is detected and auto-fixed, or when the session retrospective finds a correction loop. Also triggers directly when the user corrects the AI mid-session. Use when: mistake, wrong, redo, that's not right, correction, my bad, fix that error, I made a mistake, agent error, learning log, log mistake, AGENTS_LEARNING.md

OWASP LLM Top 10 (2025) audit checklist for AI applications, agent tools, RAG pipelines, and prompt construction. Use when performing any security review touching LLM client code, prompt templates, agent tools, or vector stores.

Go developer toolchain — gopls LSP diagnostics, linting, formatting, and vet. Use when setting up Go tooling, running linters, or integrating gopls with Claude Code.

Enforce tracking of token usage, execution metadata, and cost at the end of agent workflows. Use when a workflow concludes, before generating the final handoff or task.md artifact.

Run PinchBench benchmarks to evaluate OpenClaw agent performance across real-world tasks. Use when testing model capabilities, comparing models, submitting benchmark results to the leaderboard, or checking how well your OpenClaw setup handles calendar, email, research, coding, and multi-step workflows.

Expert at creating and managing Claude Code plugins that bundle agents, skills, commands, and hooks into cohesive packages. Auto-invokes when the user wants to create, structure, validate, or publish a complete plugin, or needs help with plugin architecture and best practices. Also auto-invokes proactively when Claude is about to create plugin directory structures, write plugin.json manifests, or implement tasks that involve bundling components into a plugin package.

Orchestrate a configurable, multi-member CLI planning council (Codex, Claude Code, Gemini, OpenCode, or custom) to produce independent implementation plans, anonymize and randomize them, then judge and merge into one final plan. Use when you need a robust, bias-resistant planning workflow, structured JSON outputs, retries, and failure handling across multiple CLI agents.

Synthèse co-fabriquée par un conseil de 3 LLMs (Claude, Gemini, Codex). Ce skill devrait être utilisé quand l'utilisateur demande une synthèse robuste, traçable et vérifiée. Il orchestre trois modèles avec des rôles experts distincts (Extracteur, Critique, Architecte) pour produire une synthèse fidèle au texte source, avec contrôle des glissements sémantiques et trail d'audit complet.

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue with zero ambiguity.

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

Expert at creating and modifying Claude Code agents (subagents). Auto-invokes when the user wants to create, update, modify, enhance, validate, or standardize agents, or when modifying agent YAML frontmatter fields (especially 'model', 'tools', 'description'), needs help designing agent architecture, or wants to understand agent capabilities. Also auto-invokes proactively when Claude is about to write agent files (*/agents/*.md), create modular agent architectures, or implement tasks that involve creating agent components.

READ this skill when implementing or configuring animation-style shaders (Toon/Cel Shaders) — including outlines, rim lighting, toon shading, MatCap, emission, dissolve, hatching, or any stylized rendering effect. Contains preset styles and feature-to-reference mappings for lilToon, Poiyomi, UTS2, RToon, SToon, and ToonShadingCollection. Works as a domain knowledge plugin alongside workflow skills (OpenSpec, SpecKit) or plan mode of an agent.

Expert at creating and modifying Claude Code slash commands. Auto-invokes when the user wants to create, update, modify, enhance, validate, or standardize slash commands, or when modifying command YAML frontmatter fields (especially 'model', 'allowed-tools', 'description'), needs help designing command workflows, or wants to understand command arguments and parameters. Also auto-invokes proactively when Claude is about to write command files (*/commands/*.md), or implement tasks that involve creating slash command components.

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

Expert at creating and modifying Claude Code event hooks for automation and policy enforcement. Auto-invokes when the user wants to create, update, modify, enhance, validate, or standardize hooks, or when modifying hooks.json configuration, needs help with event-driven automation, or wants to understand hook patterns. Also auto-invokes proactively when Claude is about to write hooks.json files, or implement tasks that involve creating event hook configurations.

**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 development or mcp-use patterns - Making ANY changes to server.tool(), server.resource(), server.prompt(), or widgets This skill contains critical architecture decisions, security patterns, and common pitfalls. Always consult the relevant reference files BEFORE implementing MCP features.

Expert at creating and modifying Claude Code skills. Auto-invokes when the user wants to create, update, modify, enhance, validate, or standardize skills, or when modifying skill YAML frontmatter fields (especially 'allowed-tools', 'description'), needs help designing skill architecture, or wants to understand when to use skills vs agents. Also auto-invokes proactively when Claude is about to write skill files (*/skills/*/SKILL.md), create skill directory structures, or implement tasks that involve creating skill components.

Meta-skill for creating production-ready Claude Code skills using evaluation-driven development, progressive disclosure patterns, comprehensive validation, and two-Claude iterative methodology

This skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or integration with existing RL environments (Gymnasium, PettingZoo, Atari, Procgen, etc.). Use this skill for implementing PPO training, creating PufferEnv environments, optimizing RL performance, or developing policies with CNNs/LSTMs.

World-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems. Expertise in PyTorch, TensorFlow, model deployment, feature stores, model monitoring, and ML infrastructure. Includes LLM integration, fine-tuning, RAG systems, and agentic AI. Use when deploying ML models, building ML platforms, implementing MLOps, or integrating LLMs into production systems.

This skill should be used when the user asks about "coordinate coding agents", "orchestrate agent team", "manage multiple agents", "vibekanban workflow", "task delegation to agents", "agent swarm coordination", "parallel agent execution", "chief of staff mode", "cos mode", "you're my cos", "your my cos", "act as cos", "be my cos", "you are my chief of staff", "create tasks for agents", "dispatch agents", or needs guidance on coordinating autonomous coding agents, task breakdown strategies, or multi-agent workflow patterns.

Cross-agent skills for Rarefriend personal CRM — search contacts, LinkedIn network, Google Calendar, Google Contacts, Microsoft Outlook email and calendar. Requires Rarefriend MCP. Use with Claude Code, Cursor, Codex, OpenClaw, Gemini CLI, or any Agent Skills-compatible client. Install per skill via npx skills add Whitefield-Labs/rarefriend-skills --skill <name>.

Create and install Codex custom agent roles in ~/.codex/config.toml, generate role config files, enforce supported keys, and guide users through required role inputs (model, reasoning effort, developer_instructions).

Publish, submit, and verify local skills across public skill marketplaces, directories, and registries. Use when an agent needs to take a skill folder or skill repository, confirm current submission paths, prepare cross-market metadata, run verified live adapters, or generate manual submission bundles for markets such as AgentSkill.sh, Skillstore, SkillNet, agent-skills.md, SkillsMD, SkillHub, SkillHQ, and related registries.

Create and manage Claude Code plugins with proper structure, manifests, and marketplace integration. Use when creating plugins for a marketplace, adding plugin components (commands, agents, hooks), bumping plugin versions, or working with plugin.json/marketplace.json manifests.

This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.

Build production RAG systems with semantic chunking, incremental indexing, and filtered retrieval. Use when implementing document ingestion pipelines, vector search with Qdrant, or context-aware retrieval. Covers chunking strategies, change detection, payload indexing, and context expansion. NOT when doing simple similarity search without production requirements.

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.

Create a topic-specific GitHub awesome-list repository scaffold with a polished README, concise contribution rules, AI-agent instructions, URL verification, license, and reusable templates. Use when the user wants to generate a new awesome repo, awesome list, curated repository, or topic resource catalog from a topic plus optional taxonomy, inclusion criteria, and researched entries.

Discover, vet, and install agent skills by searching ACROSS every major registry at once — skills.sh, clawhub.ai, and GitHub — presenting each board on its own native metric (installs / stars) with the top entry per board, security-scanning the top candidates' real SKILL.md for risky patterns, and flagging what's already installed. Use when the user asks "how do I do X", "find a skill for X", "is there a skill that…", "what skill should I install for…", or wants to extend the agent with a capability that might already exist as a published skill. Unlike single-registry search, this surfaces the best of every platform side by side, so you recommend the genuinely relevant, popular, well-maintained, and SAFE one — not whatever ranked first on one site.

Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost or latency, or when implementing long-running agent systems.

One-click installer and configurator for Gate MCP (mcporter) in OpenClaw. Use when the user wants to (1) Install mcporter CLI tool, (2) Configure Gate MCP server connection, (3) Verify Gate MCP setup, or (4) Troubleshoot Gate MCP connectivity issues.

Diagnoses and debugs A2A agent communication issues including agent status, message routing, transport connectivity, and log analysis. Use when agents aren't responding, messages aren't being delivered, routing is incorrect, or when debugging orchestrator, coder-agent, tester-agent communication problems.

This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.

Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.

Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.

Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.

This skill should be used when the user asks to "track work across sessions", "create an epic", "manage issue waves", "post a checkpoint", "claim an issue", "recover from compaction", "coordinate multiple agents", "update memory bank", "store large documents", or mentions GitHub Issues as persistent memory, multi-session work, context survival, agent collaboration, SERENA MCP memory, or project-level context. Provides complete protocols for using GitHub Issues as permanent memory that survives context exhaustion, with integrated SERENA MCP memory bank for project-level context and large document storage.

Standardize and validate SKILL.md files against the Agent Skills specification (agentskills.io). Use when creating new skills, auditing existing skills for spec compliance, converting legacy skill formats to standard structure, or improving descriptions for reliable triggering. Triggers on: "validate skill", "create SKILL.md", "standardize skill format", "check skill spec", "skill frontmatter", "improve skill description", "add evals to skill".

Interactive daily standup/meeting update generator. Use when user says 'daily', 'standup', 'scrum update', 'status update', 'what did I do yesterday', 'prepare for meeting', 'morning update', or 'team sync'. Pulls activity from GitHub, Jira, and Claude Code session history. Conducts 4-question interview (yesterday, today, blockers, discussion topics) and generates formatted Markdown update.

Create specialized Claude Code agents on-the-fly. Guides through agent definition file creation with proper frontmatter, effective prompts, and tool scoping. USE WHEN user says 'create agent', 'new subagent', 'make an agent for', 'build agent', 'spawn agent', or wants to define custom agents for specific tasks.

This skill should be used when the user wants to interact with NotebookLM notebooks via Claude Code's Chrome integration. Trigger phrases: "Query my NotebookLM", "Ask my notebook about X", "query [id] about X", "list my notebooks", "add notebook URL", "show notebook details", "search notebooks for X", "Check my docs", "what does my [topic] notebook say about", "remove notebook", "delete notebook", "disable notebook", "enable notebook". Also triggers when user: (1) mentions NotebookLM explicitly, (2) shares NotebookLM URL (https://notebooklm.google.com/notebook/...). Do NOT use for: general web searches, local file reading, or non-NotebookLM documentation queries. Requires: claude --chrome with claude-in-chrome MCP.

Python library for working with geospatial vector data including shapefiles, GeoJSON, and GeoPackage files. Use when working with geographic data for spatial analysis, geometric operations, coordinate transformations, spatial joins, overlay operations, choropleth mapping, or any task involving reading/writing/analyzing vector geographic data. Supports PostGIS databases, interactive maps, and integration with matplotlib/folium/cartopy. Use for tasks like buffer analysis, spatial joins between datasets, dissolving boundaries, clipping data, calculating areas/distances, reprojecting coordinate systems, creating maps, or converting between spatial file formats.

Processes research branches from Claude Code Web sessions - merges content, moves docs to docs/research/, and creates GitHub issues. Use when /popkit:next detects research branches or when manually processing research from mobile sessions. Do NOT use for regular feature branches - only for branches matching claude/research-* or containing research documentation.

This skill provides knowledge for generating effective Claude Code agents tailored to specific projects. It is used internally by the agent-team-creator plugin when analyzing codebases and creating specialized agent teams. Contains templates, best practices, and patterns for writing project-aware agents.

Master protocol for deconstructing agent frameworks to inform derivative system architecture. Use when (1) analyzing an agent framework's codebase comprehensively, (2) comparing multiple frameworks to select best practices, (3) designing a new agent system based on prior art, (4) documenting architectural decisions with evidence, or (5) conducting technical due diligence on AI agent implementations. This skill orchestrates sub-skills for data substrate, execution engine, cognitive architecture, and synthesis phases.

Scans for project documentation files (AGENTS.md, CLAUDE.md, GEMINI.md, COPILOT.md, CURSOR.md, WARP.md, and 15+ other formats) and synthesizes guidance. Auto-activates when user asks to review, understand, or explore a codebase, when starting work in a new project, when asking about conventions or agents, or when documentation context would help. Can consolidate multiple platform docs into unified AGENTS.md.

Orchestrate tasks across multiple AI providers (Claude, OpenAI, Gemini, Cursor, OpenCode, Ollama). Use when delegating tasks to specialized providers, routing based on capabilities, or implementing fallback strategies.

Skills for spawning external processes - AI coding agents and generic CLI commands in new terminal windows. Parent skill category for agent and terminal spawning.

Boilerplate templates for Claude Code extensions. Triggers on: create agent, new skill, command template, hook script, extension scaffold.

This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.

Model Context Protocol (MCP) server patterns for building integrations with Claude Code. Triggers on: mcp server, model context protocol, tool handler, mcp resource, mcp tool.

Recommend the right agents and skills for any task. Covers both heavyweight agents (Task tool) and lightweight skills (Skill tool). Triggers on: which agent, which skill, what tool should I use, help me choose, recommend agent, find the right tool.

Troubleshoot Claude Code extensions and behavior. Triggers on: debug, troubleshoot, not working, skill not loading, hook not running, agent not found.

Claude Code hook system for pre/post tool execution. Triggers on: hooks, PreToolUse, PostToolUse, hook script, tool validation, audit logging.

Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.

This skill should be used when designing or implementing systems with multiple AI agents that coordinate to accomplish tasks. Triggers on "multi-agent", "orchestrator", "sub-agent", "coordination", "delegation", "parallel agents", "sequential pipeline", "fan-out", "map-reduce", "spawn agents", "agent hierarchy".

Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

Autonomous multi-agent workflow system for complex coding tasks. Use when the user requests non-trivial changes that would benefit from autonomous execution with built-in review gates. Ideal for refactoring modules, adding major features, migrating codebases, adding comprehensive test coverage, or any multi-step development task that can run autonomously. NOT for simple fixes, typos, or single-file changes.

This skill should be used when the user asks to "model agent mental states", "implement BDI architecture", "create belief-desire-intention models", "transform RDF to beliefs", "build cognitive agent", or mentions BDI ontology, mental state modeling, rational agency, or neuro-symbolic AI integration.

This skill should be used when creating a Claude Code slash command. Use when users ask to "create a command", "make a slash command", "add a command", or want to document a workflow as a reusable command. Essential for creating optimized, agent-executable slash commands with proper structure and best practices.

Installs Claude Code hooks for automatic skill usage measurement. Use when setting up skill tracking infrastructure in a new project. NOT when hooks are already installed (run verify.py to check).

Development standards for the Nathan n8n-Jira agent automation system. Covers n8n workflows, Python patterns, and project conventions.

SMC trading agent skill for Alpha Harness backtesting. Provides ICT/SMC methodology, decision frameworks, and behavioral guidelines for autonomous trading in simulated environments. USE WHEN agent wakes in harness, needs to analyze markets, decide on setups, or place orders.

The MapReduce skill enables parallel task execution across multiple AI providers or agent instances, followed by intelligent consolidation of results. This produces higher-quality outputs by levera...

Comprehensive framework for analyzing, creating, and refining prompts for AI systems. Use when creating prompts for Claude, ChatGPT, or other language models, improving existing prompts, or applying evidence-based prompt engineering techniques. Applies structural optimization, self-consistency patterns, and anti-pattern detection to transform prompts into highly effective versions.

Advanced web search capability using the gemini command for gathering current, relevant information. Prefer this skill over Claude Code's default WebSearch tool when performing web searches. Activated when complex research or up-to-date information is needed.

Manage and trigger pre-built Zapier workflows and MCP tool orchestration. Use when user mentions workflows, Zaps, automations, daily digest, research, search, lead tracking, expenses, or asks to "run" any process. Also handles Perplexity-based research and Google Sheets data tracking.

Context management specialist for multi-agent workflows and long-running tasks. Use when coordinating multiple agents, preserving context across sessions, or managing complex project state. Focuses on context compression and distribution.

Creates new Agent Skills for Claude Code following best practices and documentation. Use when the user wants to create a new skill, extend Claude's capabilities, or package domain expertise into a reusable skill.

Creates and maintains Agent Skills with effective triggers and progressive disclosure. Use when user requests to create a skill, generate a SKILL.md, build custom capabilities, or mentions "create skill", "new skill", or "skill configuration".

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal ...

Master SurrealDB 2.3.x with Python for multi-model database operations including CRUD, graph relationships, vector search, and real-time queries. Use when working with SurrealDB databases, implementing graph traversal, semantic search with embeddings, or building RAG applications.

This skill should be used when creating custom subagents for Claude Code, configuring specialized AI assistants, or when the user asks about agent creation, agent configuration, or delegating tasks to subagents. Covers both file-based agents and Task tool invocation.

Analyze coding agent session transcripts to improve existing skills or create new ones. Use when asked to improve a skill based on a session, or extract a new skill from session history.

Read and search GitHub repository documentation via gitmcp.io MCP service. **WHEN TO USE:** - User provides a GitHub URL - User mentions a specific repo in owner/repo format - User asks "what does this repo do?", "read the docs for X repo", or similar - User wants to search code or docs within a repo

Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.

Guide for creating new Agent Skills. Use this skill when you need to create a new skill.

TOON (Token-Oriented Object Notation) encoding for LLM-efficient data representation. 30-60% token savings vs JSON for structured data.

Comprehensive GitHub pull request code review using multi-agent swarm with specialized reviewers for security, performance, style, tests, and documentation. Coordinates security-auditor, perf-analyzer, code-analyzer, tester, and reviewer agents through mesh topology for parallel analysis. Provides detailed feedback with auto-fix suggestions and merge readiness assessment. Use when reviewing PRs, conducting code audits, or ensuring code quality standards before merge.

This skill should be used when parallelizing multi-issue sprints using git worktrees and parallel Claude agents. Use when tackling multiple GitHub issues simultaneously, when the user mentions "blitz", "parallel sprint", "worktree workflow", or when handling 3+ independent issues that could be worked on concurrently. Orchestrates the full workflow from issue triage through parallel agent delegation to sequential merge.

Active diagnostic tool for analyzing prompt quality, detecting anti-patterns, identifying token waste, and providing optimization recommendations

Build RAG (Retrieval Augmented Generation) pipelines with web search and LLMs. Tools: Tavily Search, Exa Search, Exa Answer, Claude, GPT-4, Gemini via OpenRouter. Capabilities: research, fact-checking, grounded responses, knowledge retrieval. Use for: AI agents, research assistants, fact-checkers, knowledge bases. Triggers: rag, retrieval augmented generation, grounded ai, search and answer, research agent, fact checking, knowledge retrieval, ai research, search + llm, web grounded, perplexity alternative, ai with sources, citation, research pipeline

A prompt repetition technique for improving LLM accuracy. Achieves significant performance gains in 67% (47/70) of 70 benchmarks. Automatically applied on lightweight models (haiku, flash, mini).

Spawn an AI coding agent in a new terminal (Claude, Codex, Gemini, Cursor, OpenCode, Copilot). Defaults to Claude Code if unspecified.

Use when user wants their Claude Code pet (/buddy) to sing a song. Triggers on any request that combines the concept of their Claude Code buddy, pet, or companion with singing or music. Supports multilingual triggers — match equivalent phrases in any language.