Loading...
Loading...
Found 5,604 Skills
Adapter boundary rules for plugin integrations. Trigger: Changes in plugin scripts/hooks for Claude, OpenCode, Gemini, or Codex.
Session retrospective and codification. Run at the end of any significant session to extract learnings, update documentation, and create artifacts that make future sessions smoother. Invoke when: - Finishing a multi-step implementation - After debugging a hard problem - End of any session with 3+ tool calls - "what did we learn?" / "wrap up" / "done" Subsumes /codify-learning (codification is one output, not the only one).
A skill for improving prompts by applying general LLM/agent best practices. When the user provides a prompt, this skill outputs an improved version, identifies missing information, and provides specific improvement points. Use when the user asks to "improve this prompt", "review this prompt", or "make this prompt better".
Execute crypto trades (buy, sell, swap, exchange) and query account balances, market prices, and transaction history via the Crypto.com API. View weekly trading limits and portfolio positions. Use when the user wants to trade, purchase, sell, or swap cryptocurrency, check token prices or portfolio balances, view recent trades, discover coins, or activate the kill switch. Supports BTC, ETH, CRO, and 200+ tokens across fiat and crypto wallets.
Expert-level AI implementation, deployment, LLM integration, and production AI systems
Reasoning-driven image generation using structured creative briefs (Gemini 3 style) — generates high-fidelity images via muapi.ai with logic-based prompting
Inline adversarial plan review — 3 sequential checks (Feasibility, Completeness, Scope & Alignment) performed by the calling LLM in its own context. No subagents spawned. Call after saving a plan. Returns GATE_PASS or GATE_FAIL with blocking issues.
Cognitive science-based deep source code understanding assistant (Chinese improved version). Supports three analysis modes: Quick (overview), Standard (comprehension), Deep (mastery, automatically uses parallel processing for large projects). Integrates elaborative interrogation, self-explanation testing, and retrieval practice to help truly understand and master code.
This skill should be used when the user asks to "팀 구성해줘", "team assemble", "전문가 팀으로 해줘", "팀으로 해줘", "swarm", "병렬로 전문가 팀", or wants to decompose a complex task into specialist roles executed via TeamCreate. Also triggers when user describes a task clearly benefiting from parallel expert execution.
This skill should be used when the user asks to "콘텐츠 정리", "아티클 요약", "PDF 학습", "영상 정리", "트윗 정리", "digest", "summarize", "정리해줘", or provides a YouTube URL, X/Twitter URL (x.com, twitter.com), webpage URL, or PDF file for analysis. Supports YouTube (transcript), X/Twitter (via fetch-tweet skill), webpage (full content via browser), and PDF (text + image per page). Generates Quiz-First learning with 9 questions across 3 difficulty levels.
Implement tasks from the change, writing actual code following the specs and design. Trigger: When the orchestrator launches you to implement one or more tasks from a change.
Code file line limit specification: A single code file must have ≤ 300 lines. This is a mandatory restriction with no exceptions.