技能检索
facepalm
Crosscheck OpenClaw console logs with chat history (last 5 mins) and use Codex 5.3 to troubleshoot issues. Standalone troubleshooting tool that can be invoked manually or integrated with other skills.
agentskills-io
Create, validate, and publish Agent Skills following the official open standard from agentskills.io. Use when (1) creating new skills for AI agents, (2) validating skill structure and metadata, (3) understanding the Agent Skills specification, (4) converting existing documentation into portable skills, or (5) ensuring cross-platform compatibility with Claude Code, Cursor, GitHub Copilot, and other tools.
redacta
Redacta pseudonymises medical documents — replacing patient identifiers (NHS numbers, dates of birth, postcodes, phone numbers, hospital numbers) with labelled tokens so clinical content can be safely processed by AI. Built by PharmaTools.AI.
list
List conversations, members, and messages from the XMTP CLI. Use when listing or finding conversations.
beancount-skill
Professional personal finance advisor specializing in plain-text accounting with Beancount and Fava. Use when users need help with: (1) Analyzing spending habits and financial patterns from Beancount files, (2) Creating or understanding Beancount transactions and syntax, (3) Financial planning, budgeting, and investment advice, (4) Interpreting Fava reports and creating custom queries, (5) Organizing chart of accounts, (6) Double-entry bookkeeping principles, (7) Personal finance optimization and wealth building strategies. Provides analysis, education, and personalized recommendations while maintaining professional standards.
litellm
Call 100+ LLM providers through LiteLLM's unified API. Use when you need to call a different model than your primary (e.g., use GPT-4 for code review while running on Claude), compare outputs from multiple models, route to cheaper models for simple tasks, or access models your runtime doesn't natively support.
fractal-memory
Automated hierarchical memory compression system that prevents context overflow through daily→weekly→monthly→core compression. Use when you need (1) long-term memory management without manual curation, (2) token-efficient context loading with attention-optimized hierarchy, (3) preventing session bloat from accumulated history, (4) automated memory rollups via cron, or (5) migrating from flat daily files to structured memory. Activates for memory architecture questions, context overflow issues, or setting up persistent agent memory.
mulch-self-improving-agent
Mulch Self Improver — Let your agents grow 🌱. Captures learnings with Mulch so expertise compounds across sessions. Use when: command/tool fails, user corrects you, missing feature, API fails, knowledge was wrong, or better approach found. Run mulch prime at session start; mulch record before finishing. Benefits: better and more consistent coding, improved experience, less hallucination.
geepers-llm
Send requests to the dr.eamer.dev LLM API for chat completions, vision analysis, image generation, text-to-speech, and video generation across 12 model providers. Use when you need to call an external LLM endpoint or want to compare responses across providers.