Pulls latest code and runs tests until all pass. Use after code review passes to verify changes work correctly.
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Pulls latest code and runs tests until all pass. Use after code review passes to verify changes work correctly.
Validates commit messages against Conventional Commits specification using programmatic validation. Replaces the git-conventional-commit-messages text file with a tool that provides instant feedback.
Create final git commit with requirement traceability tags (REQ-*). Use after refactor-phase to finalize TDD cycle with proper requirement linkage for bidirectional traceability.
Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.
Reviews common RMS Go patterns including caching, retry logic, enums, and unmarshalling. Use when implementing utility patterns, seeing repeated boilerplate, or reviewing pattern usage.
Apply when debugging errors, reviewing code for issues, or encountering unexpected behavior. Contains known mistakes with ChurchTools API, Vue components, TypeScript, Safari cookies, and form handling.
Best practices for the Common utilities package in LlamaFarm. Covers HuggingFace Hub integration, GGUF model management, and shared utilities.
Guidelines for communication, problem-solving and platform thinking applying to all files.
Establish a professional and concise style for all AI communication and output.
Perform thorough, constructive code reviews on pull requests and code changes. Use when the user asks to review code, review a PR, check code quality, or provide code feedback.
Compare a GitHub repository with connectrpc-axum. This skill should be used when the user provides a GitHub repository URL and wants to compare it with the current project. Analyzes user features, technical implementation, architecture patterns, code quality, tests, and documentation. Outputs comparison to docs/guide/compare/ directory.
Generate and review documentation for competition organizers using Diataxis framework. Use when writing docs for organizer workflows like creating competitions, managing divisions, scheduling heats, handling registrations, entering results, or managing volunteers/judges.
Gemini DeepSearch MCPを活用した競合分析専門エージェント。直接・間接競合の徹底調査と差別化軸の特定。競合調査、市場分析、ポジショニング分析の際に積極的に使用。MUST BE USED for competitive analysis.
Build competitive positioning with positioning canvas, competitive wedge statements, and differentiation strategy.
competitive-review
Complete task: validate, document, review, commit, and merge to develop. Use when all implementation is done and ready to finalize.
Maintain and improve code quality using PHPInsights without decreasing quality thresholds. Use when PHPInsights fails, cyclomatic complexity is too high, code quality drops, or when refactoring for better maintainability. Always maintains 94% complexity and 100% quality/architecture/style scores.
Standardized template for campaign compliance intake, reviews, and approvals.
Review ads and landing pages for compliance issues including FTC disclosure requirements, platform policy compliance, and restricted claims. Use before launching campaigns, when ads get rejected, or when auditing existing creative.
Activate regulatory compliance specialist mode. Expert in SOX, GDPR, HIPAA, and PCI-DSS requirements. Use when reviewing code for compliance, implementing audit trails, data protection, or regulatory controls.
Generate compliance reports from OSCAL assessment results, SSPs, and POA&Ms in various formats. Use this skill to create audit-ready documentation, executive summaries, and detailed compliance status reports.
Repository pattern for pre-approved financial disclosures and claim language.
Reviews React components and provides improvement suggestions. Use when you need code review, component review, structure improvement, refactoring, or component separation.
Implements UI components from design specifications. Use when implementing frontend components, pages, or UI elements. Follows design specs from ui-ux-designer, implements responsive design, and ensures accessibility.
Enforce consistent React component naming conventions using domain + role patterns. Use when creating, reviewing, or refactoring components.
Run Vitest tests for a specific component with coverage. Use when making changes to React components to ensure tests pass and coverage is maintained.
Design Plan/Build/Review/Fix workflow steps for ADWs. Use when creating composable workflow primitives, defining step contracts, or implementing step isolation patterns.
Rules pertaining to Composer dependency management, promoting best practices for declaring and updating dependencies.
Use when Codex needs to run CI/CD or cross-service automations through the Composio MCP server.
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.
Use Plan → Work → Review → Compound to compound skills and maintain project context.
Use when working with comprehensive review full review
Use after implementing features - 7-criteria code review with MANDATORY artifact posting to GitHub issue; blocks PR creation until complete
Perform thorough test review for the specified test files or directories.
Requires detailed type annotations for all Python functions, methods, and class members.
發展研究概念並驗證創新性。觸發：concept、發展概念、研究概念、novelty、創新點、補充概念、幫我補充、擴展概念、加強、驗證失敗、novelty不夠、怎麼改。
End-to-end workflow for creating complete JavaScript concept documentation, orchestrating all skills from research to final review
Go concurrency safety review. Use when checking goroutines, channels, race conditions, or synchronization. Detects goroutine leaks, deadlocks, race conditions, and unsafe channel operations.
This rule enforces encapsulating nested conditionals into functions to improve clarity.
Complete workflow for conducting thorough code reviews with structured feedback
This skill should be used when writing official conference-style reviews for research papers as if from a top-tier systems conference reviewer. Use when the author wants a realistic, formal peer review with scores, strengths, weaknesses, and detailed feedback following standard conference review formats.
Read and merge `.agents.yml` and `.agents.local.yml` configuration files. Local config overrides base config.
Security review of configuration files and infrastructure as code.
Automatically validate DAPR configuration files (dapr.yaml, component YAML files) when they are created or modified. Checks for schema compliance, missing required fields, invalid values, and common misconfigurations. Use when validating DAPR configs, reviewing component setup, or before deployment.
confighub-usage-guide
Use when setting up GitHub Actions CI/CD for pull request checks - provides workflow templates for Python, JavaScript, and polyglot projects that run quality gates on every PR
Plan confirmation workflow - extract plan from conversation, create file, auto-review with Interactive Recovery. Use for confirming plans after /00_plan.
Expert in consent to assignment agreements where a tenant transfers their entire lease to a new party (assignee). Use when tenant is selling their business and assigning the lease, landlord is reviewing a consent request, analyzing whether original tenant remains liable after assignment, drafting assignment consent agreements, negotiating release provisions, or handling assignment plus sublease combinations (e.g., professional corporations). Key terms include assignment vs sublease, assignee, privity of estate, joint and several liability, no release, recapture rights, assignor remains liable, change of control, business sale
Reviews React/TypeScript code for the depot console web application with focus on real-time rover teleoperation, state management, WebSocket communication, and 3D visualization. Use when reviewing console frontend changes, debugging teleop UI issues, optimizing rendering performance, validating WebSocket protocols, checking React Three Fiber implementations, or evaluating state management patterns. Covers Zustand store architecture, binary protocol encoding, input handling, page visibility safety, memory management, and 360-degree video streaming.
Detects timing side-channel vulnerabilities in cryptographic code. Use when implementing or reviewing crypto code, encountering division on secrets, secret-dependent branches, or constant-time programming questions in C, C++, Go, Rust, Swift, Java, Kotlin, C#, PHP, JavaScript, TypeScript, Python, or Ruby.