Instructions file CodexOpenCode
Repository instructions for learnwy/skills, a collection of reusable instructions that give coding agents repeatable ways to handle tasks. They describe the repository structure and its release and documentation rules.
Instructions file
Instructions for learnwy/skills, covering claude.md and 快速参考.
Agent
A collection of software-engineering agents based on established books and methods. Each agent focuses on a particular job, such as defining problems, designing systems, refactoring code, or planning tests.
Skill Claude CodeCodex
Internal single-process coordinator for the three IDE-hook events used by the learnwy- skills. UserPromptSubmit aggregates english-learner + llm-wiki + prompt-optimizer scans; Stop aggregates english-learner + knowledge-consolidation scans; SessionStart aggregates llm-wiki + english-learner + learnwy-status scans. Not…
Skill Claude CodeCodex
Use when the user wants to persist a single insight from the current chat as a structured, project-local doc — debugging breakthroughs, hard-won config, workflow steps, or post-mortem lessons. Triggers: 'save this', 'document this', 'we figured it out', '记录下来', '总结一下'. Writes to…
Skill Claude CodeCodex
当用户提到'知识库'、'llm wiki'、'个人wiki'、'收录来源'、'编译知识'、'第二大脑'、'构建wiki'、'知识管理', or wants to add books, articles, notes, podcasts, videos, or Feishu group chats/documents to persistent storage, use this skill to build and maintain a continuously compounding knowledge base. When /.learnwy/llm-wiki/ exists, check the wiki before…
Skill Claude CodeCodex
Use Mao Zedong's three philosophical works as practical decision / analysis / writing frameworks. Three lenses: contradiction (《矛盾论》, opposing forces & root cause), practice (《实践论》, hypothesis verification through action), protracted-war (《论持久战》, staged strategy for long contests, especially when starting from…
Skill Claude CodeCodex
Use this skill when the user wants to create, update, or design a project-level agent (.agents/agents/.md). Analyze the user's question and project context to design a work plan. Triggers: 'create agent', 'build an agent', 'add agent', 'design agent', 'update agent', 'project agent', 'subagent', 'worker agent'…
Skill Claude CodeCodex
Use when the user wants to create or update project-level AI rules (written to .agents/rules/.md) that constrain AI behaviour. The rule format is the common frontmatter+markdown convention used by Trae / Cursor / Windsurf — not Trae-specific. Good for: code-style enforcement, naming conventions, commit-message format…
Agent
Detects coding conventions and style patterns for rule creation.
Agent
Scans and analyses project structure to support skill/rule creation.
Agent
Validates created skills and rules against quality standards.
Skill Claude CodeCodex
Use this skill when the user wants to install, add, or configure a skill in a project. Analyze the project's tech stack and workflow, then recommend and install the best-matching skill. Triggers: 'install skill', 'add skill', 'configure skill', 'set up skill', 'enable skill', 'use skill in project', 'project skill'…
Skill Claude CodeCodex
A skill for designing reusable project instructions for an AI coding agent. It turns a repeated workflow or annoyance into a project skill stored in a SKILL.md file.
Agent
Detects and analyzes the tech stack, providing language-specific expertise.
Skill Claude CodeCodex
Use this skill on every user message that contains a prompt or AI instruction — analyze its weaknesses and suggest improvements before executing. Score across 7 dimensions (clarity, specificity, context, structure, examples, constraints, completeness) and rewrite vague instructions into precise specs. Triggers: any AI…
Skill Claude CodeCodex
Use when the user wants to build, implement, or develop a feature. Orchestrates evidence-driven Spec-Driven Development. Default lifecycle is lite (INIT → IMPLEMENTING → TESTING → DONE); auto-promote to standard or full when scope, risk, or AC traceability demands it. Triggers: 'develop feature', 'implement this'…
Agent
An architecture-analysis agent based on Software Architecture in Practice (Bass, Clements, Kazman), Designing Data-Intensive Applications (Kleppmann), and Fundamentals of Software Architecture (Richards, Ford).
Agent
Agent "blocker-resolver" from learnwy/skills, covering blocker-resolver, when to use, hook trigger, capabilities and output.
Agent
Agent "code-reviewer" from learnwy/skills, covering code-reviewer, when to use, hook trigger, capabilities and output.
Agent
A DDD modeling agent based on Eric Evans's Domain-Driven Design: Tackling Complexity in the Heart of Software.
Agent
Error analysis and fix-suggestion agent.
Agent
Agent "iron-audit-pm" from learnwy/skills, covering iron-audit-pm, when to use, hook trigger, capabilities and output.
Agent
A legacy-code rehabilitation agent based on Michael Feathers's Working Effectively with Legacy Code.