Build a retrieval-optimized knowledge layer over agent documentation in dotfiles (.claude, .codex, .cursor, .aider). Use when asked to "optimize docs", "improve agent knowledge", "make docs more...
统一智能体协议适配层。一套 API 调用所有 Agent 协议（ANP/MCP/A2A/AITP 等）。当用户需要调用 Agent、跨协议通信、连接工具时触发此技能。
Update AGENTS.md based on the current state of the repository. This skill should be used when repository configuration, structure, or tooling has changed and AGENTS.md needs to reflect those changes.
Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and...
Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and...
Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and...
Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and...
Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and...
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
HIPAA compliance skill for PHI/PII detection, code scanning, audit reports, and remediation. This skill should be used when the user asks to "scan for PHI", "detect PII", "HIPAA compliance check",...
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
Agentic orchestration patterns for long-running tasks. Implements evidence-based delivery and Simon Willison's agent loop. Use when managing multi-step work, coordinating subagents, or...
Jeffrey Emanuel's comprehensive markdown planning methodology for software projects. The 85%+ time-on-planning approach that makes agentic coding work at scale. Includes exact prompts used.
Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.
Use when you have a spec or requirements for a multi-step task, before touching code
Use when you have a spec or requirements for a multi-step task, before touching code
Cloud-native infrastructure management with Crossplane using Kubernetes APIs. Build internal platform APIs for self-service infrastructure provisioning. Use when implementing infrastructure as...
Use when receiving code review feedback, before implementing suggestions,
Local-first backlog workflow. Use when planning work, creating/updating backlog items, writing ADRs, enforcing Ready gate, generating views, or maintaining derived indexes (SQLite/FTS/embeddings).