notes
Address PR comments in worktree, resolve feedback, push fixes
Découvrez les skills Tests et sécurité, comparez leurs dépôts et consultez leurs instructions.
Address PR comments in worktree, resolve feedback, push fixes
Four-phase debugging methodology with root cause analysis. Use when investigating bugs, fixing test failures, or troubleshooting unexpected behavior. Emphasizes NO FIXES WITHOUT ROOT CAUSE FIRST.
Use when reviewing local branch changes before merge, when you want code review feedback without a PR, or before committing significant changes
Create new Agent Skills following the official specification and best practices. Use when the user wants to create a skill, write a SKILL.md file, or package instructions/workflows for reuse across conversation...
Build question/answer style agents using InteractiveNode, explicit routing, and workflow slices.
Build a production-minded AI agent using agent-contracts (contracts, slices, validation, graph, runtime, CLI tooling).
Build an API-oriented agent using AgentRuntime/StreamingRuntime with predictable request/response slices and session support.
Make contract-driven agents safe to change with strict validation, architecture docs, and contract diffs in CI.
Tune routing with TriggerCondition priorities, LLM hints, context_builder, and traceable decisions.
Implement tool-using or retrieval-style nodes with services, dependency injection, and safe LLM context building.
新規コンポーネント作成時にStorybookファイルを自動生成。「Storybookを作成」「Storybook追加」「○○コンポーネントのStoryを作って」などで起動。プロジェクト規約に従ったテンプレートを使用。
Project-specific prompt optimization knowledge management. Use when storing or retrieving learned patterns from comparisons. Provides schema, extraction criteria, capacity management, and retention scoring.
Model-agnostic prompt analysis and optimization patterns based on 2025-2026 research. Use when analyzing prompts for issues or generating optimized versions. Provides 8 patterns (BP-001 through BP-008) and 3-st...
Git worktree management for isolated parallel prompt execution. Use when creating isolated environments for prompt comparison or managing worktree lifecycle. Provides creation, cleanup, and orphan detection scr...
Fresheyes provides code review from a larger model. Use when the user asks for fresh eyes.
How to review code; a pull request, feature branch, local changes etc.
How to add entries to the glossary
Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches
Use when creating or developing anything, before writing code or implementation plans - refines rough ideas into fully-formed designs through structured Socratic questioning, alternative exploration, and increm...
Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches code-reviewer subagent to review implementation against plan or requirements before proce...
TypeScript best practices. Use when writing TypeScript code for backend services, API handlers, or shared utilities. Applies async/await patterns, typed errors, and strict type safety.
UI design patterns for React + TailwindCSS. Use when creating new UI components, styling elements, implementing dark mode support, or working on any React component that needs consistent styling.
REST API design patterns for SpecFlux. Use when creating new API endpoints, designing request/response schemas, implementing pagination, or updating OpenAPI specifications. Follows Domain-Driven Design with spe...
Spring Boot and Java best practices. Use when developing REST APIs, services, repositories, or any Java code. Applies DDD architecture, transaction management, and code style conventions.
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.