Loading...
Loading...
Found 1,304 Skills
Integrate Honcho memory and social cognition into existing Python or TypeScript codebases. Use when adding Honcho SDK, setting up peers, configuring sessions, or implementing the dialectic chat endpoint for AI agents.
Create or update Langfuse model pricing. Use when setting up new models, updating pricing, or configuring model costs.
企业微信客服自动化系统。自动同意好友添加、基于知识库的智能问答、未知问题人工介入提醒。适用于企业微信客服场景的 AI 助手机器人。
Compress documentation, prompts, and context into minimal tokens for AGENTS.md and CLAUDE.md. Achieves 80%+ token reduction while preserving agent accuracy.
Get a deep critical review of research from GPT via Codex MCP. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
Audit your Claude Code setup for prompt caching efficiency. Measures prefix size, hook patterns, rule duplication, dynamic injection sizes, and tool stability. Use when asked to 'check caching', 'optimize prompt cache', or 'audit setup efficiency'. Returns a scored report with fixes ranked by token savings.
This skill automatically generates a comprehensive glossary of terms from a learning graph's concept list, ensuring each definition is precise, concise, distinct, non-circular, and free of business rules. Use this skill when creating a glossary for an intelligent textbook after the learning graph concept list has been finalized.
AI/ML security playbook. Use when assessing model supply chain attacks (pickle RCE, poisoned weights), adversarial examples, model poisoning, model stealing, data privacy attacks (membership inference, model inversion), and autonomous agent security risks.
Create ShinkaEvolve task scaffolds from a target directory and task description, producing `evaluate.py` and `initial.<ext>` (multi-language). Use when asked to set up new ShinkaEvolve tasks, evaluation harnesses, or baseline programs for ShinkaEvolve.
Systematic debugging for ADK agents — trace reading, log analysis, common failure diagnosis, and the debug loop.
Comprehensive multi-perspective review using specialized judges with debate and consensus building
Generate a periodic knowledge digest — a human-readable newsletter-style summary of what was learned, updated, and connected in your wiki over a specified period (day/week/month). Use when the user says "what did I learn this week", "give me a digest", "weekly summary", "knowledge report", "what's new in my wiki", "/wiki-digest [period]", "summarize my recent learning", or wants a readable overview of recent wiki activity. Distinct from wiki-status (which reports ingestion delta of sources) — wiki-digest summarizes *knowledge*, not sources.