Loading...
Loading...
Found 132 Skills
Use before starting implementation - research repository documentation, codebase patterns, and external resources to inform the approach
Create task documents for new features, updates, or fixes. Creates detailed specs in docs/task/*.md with full implementation context. Updates TASKS.md for tracking. Use when starting any new work.
AI-Native Issue-Driven development workflow. From GitHub Issue to merged PR: parse issue, explore codebase, design technical plan, execute with agent team, create PR, and cleanup. Use when a user wants to implement a GitHub Issue end-to-end: `/issue-flow #123` or `/issue-flow` to pick from open issues.
Execute one TASK-* with a reproducible protocol, quality gates, and Memory Bank sync.
단일 태스크의 RED-GREEN-REFACTOR TDD 루프를 ping-pong 방식으로 실행합니다. .tdd-sessions/에서 활성 세션 파일을 읽어 현재 태스크를 찾고, 개발자와 함께 전체 사이클을 진행하며 (테스트 작성과 구현을 번갈아가며), 완료 시 세션 파일을 업데이트합니다. 세션 파일을 생성하려면 먼저 /tdd-plan을 실행하세요.
Organize reusable programming patterns, library usages, and technical techniques that address "This is the correct way to do such tasks" into a prescriptive reference library, which can be retrieved and reused on demand during feature-design and issue-analyze phases. There are three types: pattern (design patterns, programming idioms), library (usage and pitfalls of a specific library/framework), technique (specific operation skills / command recipes). Trigger scenarios: when users say "Record a trick", "This usage is worth noting", "tricks", "Record library usage", or when valuable techniques worth documenting and archiving are discovered during feature-design / issue-analyze phases and actively pushed. For how to distinguish it from learning / decisions / explore, refer to the root skill of `easysdd`.
Implement the requested changes. Write production-ready code, follow existing patterns, and run tests to verify your work.
Use when the agent is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text. Originally from OpenAI's curated skills catalog.
Assess if IDD fits your project and learn about Intent-Driven Development. Use /intent-assess to evaluate project suitability or /intent-assess --learn for IDD education.
Best practices and guidelines for Webpack module bundler configuration, optimization, and development workflows
Before ANY significant development task (new feature, refactor, integration, migration), run a complete planning ritual by orchestrating other skills in sequence: rubber-duck (clarify scope) -> pre-mortem (assess risks) -> eta (estimate time) -> final confirmation. Do not start coding until the battle plan is approved.
Compound Engineering workflow for AI-assisted development. Use when planning features, executing work, reviewing code, or codifying learnings. Follows the Plan → Work → Review → Compound loop where each unit of engineering makes subsequent work easier. Triggers on: plan this feature, implement this, review this code, compound learnings, create implementation plan, systematic development.