Use when: making a mistake, breaking build/tests, realizing wrong approach, misunderstanding requirements, using wrong patterns, forgetting conventions, receiving correction from user, unexpected behavior, or any error situation
专业的知识库管理系统，旨在解决“知识诅咒”和认知偏差问题。通过显式化隐性知识、扫描代码提取领域概念、整合行业最佳实践，构建结构化的 Markdown 知识库。
Guides diagnosis and resolution when problems occur. Use when user mentions 動かない, エラーが出た, 壊れた, うまくいかない, broken, doesn't work, error. Do NOT load for: 正常なビルド, 新機能実装, レビュー.
Ingest new procedural memory (skills, patterns, docs) into the vector database.
This skill should be used when the user asks to "add warning", "remove warning", "list warnings", "check file warning", "check package warning", "manage grudges", or needs to manage file and package warnings in Matrix.
Comprehensive project context detection and state awareness. Use when relevant to the task.
Validate documentation for unsupported claims, made-up metrics, and unverifiable statements. Use when relevant to the task.
Deconstruct problems to fundamental truths and rebuild solutions from scratch. Use when conventional solutions feel wrong, costs seem fixed, you hear 'that's how it's done,' or need breakthrough rather than incremental improvement.
Use when extracting reusable patterns, solutions, or knowledge from completed tasks into documentation
This skill should be used when the user asks to "write org", "org-mode", "org file", ".org file", "org syntax", "org document", "org babel", "org export", "org agenda", "org capture", "GTD", "literate programming", "org publishing", or "org-mode workflow". Provides comprehensive Org-mode patterns and best practices.
Use when creating or updating technical blueprint documentation for new features, API changes, or architectural modifications. Always use search_blueprints first to avoid duplication, then write_blueprint with proper structure.
Use when creating troubleshooting guides and diagnostic procedures for operational issues. Covers problem diagnosis, root cause analysis, and systematic debugging.
Portfolio retrospective skill for capturing lessons learned, process improvements, and organizational learning across completed projects.
This skill should be used when writing, modifying, or reorganizing documentation in docs/learned/. Use when creating new documents, updating frontmatter, choosing categories, creating index files, updating routing tables, or moving files between categories. Essential for maintaining consistent documentation structure.
Use when researching, clustering, and prioritizing keywords for SEO roadmaps.
Toolkit for structuring hypotheses, variants, guardrails, and measurement plans.
Persistent graph-based memory for AI agents via KIP (Knowledge Interaction Protocol). Provides retrieval-first memory operations (KQL), durable writes (KML), schema discovery (META), and memory hygiene patterns. Use whenever the agent needs to consult or update persistent memory, especially for: remembering user preferences/identity/relationships, storing conversation events, answering questions that depend on past sessions, and any task involving `execute_kip`.
Create detailed implementation plans with bite-sized tasks for engineers with zero codebase context
Domain expert routing. When the knowledge base cannot answer user questions, find and notify the corresponding expert based on the question domain. Only available in IM mode. Trigger condition: No results in 6-stage retrieval.
Reference manual for framework methodology throughout session. Provides guidance on cognitive architecture that replaces default AI assistant behaviors with systematic patterns proven through collaborative experience. Consult this manual throughout session when applying framework procedures.
