langgraph-docs
Use when answering LangGraph questions. Prefer reading local project code/specs; fetch docs only if needed.
Discover DevOps skills, compare source repositories and read the instructions for each workflow.
Use when answering LangGraph questions. Prefer reading local project code/specs; fetch docs only if needed.
Use for SvelteKit 2 + Svelte 5 + Tailwind v4 projects. Keep SSR/client boundaries and Tailwind config consistent.
Use when you want a second-opinion review from a different model/tool. Provide narrow, reviewable diffs.
Use to review OpenAI API integrations for correctness (endpoints, params, auth, response handling) and robustness.
This skill should be used when the user asks to "run tasks in parallel", "create worktrees", "dispatch parallel agents", "orchestrate execution", or when autonomous-dev needs to execute independent tasks simult...
This skill should be used when the work type is FRONTEND and visual verification is needed. Provides browser automation for screenshot comparison, responsive testing, and interactive element verification using...
This skill should be used when the user initiates autonomous development with /auto, /auto-lite, or similar commands to classify the type of work. Semantic work type classification with multi-layer detection. A...
This skill should be used when the user asks to "resolve merge conflicts", "fix git conflicts", "merge branches", or when autonomous-dev encounters merge conflicts during branch integration. Intelligently resol...
This skill defines the Initializer Agent protocol for the Two-Agent Pattern. The Initializer Agent runs ONCE at the start of a new task to analyze, plan, and set up state for Coding Agents. Use this when starti...
This skill should be used when the user asks to "break down this feature", "decompose this task", "create task list", "plan implementation steps", "identify subtasks", or when planning autonomous execution. Con...
This skill should be used when the user asks to "run verification", "check if code passes", "run tests and lint", "verify implementation", or after code changes in autonomous mode. Runs typecheck, lint, test, a...
This skill should be used when the user asks to "detect project type", "analyze this project", "create project profile", "what tech stack is this", "scan project structure", "what database does this use", or wh...
This skill should be used when the user asks to "verify test quality", "run mutation testing", "prove tests catch bugs", "check test effectiveness", or automatically after the TDD cycle completes in task-execut...
Unified command-line interface for managing feeds (Miniflux), links (Linkding), and pages (Wallabag). Use for authentication, managing feeds, managing links, and managing pages.
3-Way並列コードレビュー(Codex CLI + Gemini CLI + Claude Code Task agent)。複数視点での品質チェック、アーキテクチャ決定、デバッグ、セカンドオピニオンが必要な場合に使用。
DearTs Framework 开发技能。基于 SDL3 + ImGui 的 C++20 现代应用框架,提供完整的应用生命周期管理、类型安全事件系统、Content Registry 和插件架构。适用于 DearTs Framework 相关的所有开发任务,包括应用程序开发、事件...
Create detailed implementation plans with persistent markdown files for complex tasks
Comprehensive guide and utilities for applying Neumorphism (Soft UI) to the MyAsset project.
Updates CHANGELOG.md with recent changes. RULES: MUST use CHINESE, MUST include Date & Time (YYYY-MM-DD HH:mm).
Adds detailed comments to code files. Invoke when user asks to add comments, document code, or explain code. RULES: Core methods=English, Tests=Chinese.
Bicep/azd デプロイ前の what-if 分析。「差分確認」「変更影響」「破壊的変更」「デプロイしたら何が変わる」「Bicep と実リソースの比較」を求める場合に使用。
Create new visualizations for the IWAC Dashboard. Use this skill when: - Adding a new chart, graph, map, or data visualization - Creating Python data generation scripts for new visualizations - Building reusabl...
First-run setup for TaskFlow - configure backend and preferences
Maintain living documentation with single source of truth approach, journal reconciliation, and worklog.db integration
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.