conventional-commits
Use this skill ONLY for 'commit', 'save', or 'finish' prompts. Enforces strict manual approval, intelligent Topic-to-Global branching, and sync automation.
Discover Tools skills, compare source repositories and read the instructions for each workflow.
Use this skill ONLY for 'commit', 'save', or 'finish' prompts. Enforces strict manual approval, intelligent Topic-to-Global branching, and sync automation.
多 Agent 並行驗證框架 - 多視角測試驗證,發布許可決策
Manage feature specifications - create, track, and implement specs with structured templates and auto-generated indexes.
Release workflow for baoyu-skills plugin. Use when user says "release", "发布", "push", "推送", "new version", "新版本", "bump version", "更新版本", or wants to publish changes to remote. Analyzes changes since...
仕様を確定させるための壁打ち専用Agent。実装可能でテスト可能なSpec.mdを1枚で確定させる。
Orchestrates the Testing Strategy & Implementation process (Planning -> Execution -> Closing). Manages the workflow by invoking specialized sub-skills like code-testing-planning, tdd-refactoring, and tdd-audit....
Run comprehensive audit on completed work. Use after implementation is done, or when user says 'audit this', 'review the work', 'check for issues'. Spawns specialized auditors and fixes found issues.
Evaluate how well a codebase supports autonomous AI development. Analyzes repositories across eight technical pillars (Style & Validation, Build System, Testing, Documentation, Dev Environment, Debugging & Obse...
Build monitoring dashboards with Grafana. Covers panel types, queries, variables, alerting, provisioning, and data sources like Prometheus and InfluxDB. Use for infrastructure monitoring, observability, and met...
Claude Code CLI usage for automated/headless execution in Daytona sandboxes. Use when running Claude Code commands, configuring authentication, or setting up non-interactive mode.
Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives.
Verify code quality, type safety, memory leaks, and coding standards. Use when reviewing code, checking for issues, or validating a PR.
Safe deployment patterns, automated rollback mechanisms, and production deployment strategies with zero-downtime and comprehensive safety checks.
Manage Portainer deployments - create stacks from Git repos, check deployment status, redeploy, view logs. Use when user asks about deploying to Portainer, checking stack status, or managing Docker deployments.
Git conventions, branch strategy, commit messages, Husky hooks, and GitHub Actions.
Finalize a completed phase after PR approval. Checks if current branch PR is merged, then returns to main. WHEN: Use after user approves PR to close out current phase. Invoke with "/plan:end-phase". WHEN NOT: W...
Work with GitHub issues, PRs, and releases. Use when managing tasks, creating issues, or preparing PRs.
Use when you have a spec or requirements for a multi-step task, before touching code
This skill should be used when the user asks to "legacy modernization, strangler pattern, migration strategy, monolith to microservices, refactoring", or needs help with Migration, strangler pattern.
Invoke the Gemini CLI for architecture and scalability review.
Reviews code for best practices and potential issues. Use when reviewing code, checking PRs, or analyzing code quality.
Complete GPU optimization pipeline. Launches N agents, runs benchmarks, anti-triche verification, and generates report automatically. One command for everything.
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
Review AI-drafted issues for human approval
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.