发现 数据与 AI 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Inline orchestration workflow for code review with Beads integration. Provides comprehensive analysis of issues (bugs) AND improvements (recommendations), issue creation, priority-based fixing, and verification...
Expert guidance for Beads (bd) - a Git-backed issue tracker for AI-supervised coding workflows. Use when working with bd CLI commands, MCP tools, hooks, issue tracking, dependencies, workflows, or troubleshooti...
Guide to writing standard, parseable commit messages (Conventional Commits).
Inline orchestration workflow for dependency audit and updates with Beads integration. Provides step-by-step phases for dependency-auditor detection, priority-based updates with dependency-updater, and verifica...
Create GitHub issues from ui-skills review results or feature requests.
Inline orchestration workflow for code duplication detection and consolidation with Beads integration. Provides step-by-step phases for reuse-hunter detection, priority-based consolidation with reuse-fixer, and...
Inline orchestration workflow for dead code detection and removal with Beads integration. Provides step-by-step phases for dead-code-hunter detection, priority-based cleanup with dead-code-remover, and verifica...
Semantic diffing for .NET source using roslyn-diff. Supports file/folder diffs, HTML reports, and git/PR-aware comparisons (GitHub + Azure DevOps).
Use this skill to evaluate implementation quality, track technical debt via an append-only log, and generate a fix queue (prd.json) when a change does not meet the specification.
Analyze repository structure, patterns, conventions, and documentation for understanding a new codebase
Create git commits with user approval and no Claude attribution
MEMORY FIRST - Query memory BEFORE scanning any codebase. Use when encountering ANY problem, error, or task. Call "recall" FIRST, then scan codebase only if nothing found. Triggers: "check memory", "recall", "h...
Archive completed changes and optionally sync specs first.
Remove AI-generated code slop from the current branch. Use after writing code to clean up unnecessary comments, defensive checks, and inconsistent style.
Helper logic for automatically selecting appropriate Argonauts reviewers based on files discovered by the Explore agent. Analyzes file characteristics (path, name, extension) to determine optimal reviewer combi...
Expert guidance for mprocs configuration, multi-process orchestration, and TUI customization. Use when configuring mprocs.yaml, setting up process management, customizing keybindings, styling the interface, tro...
No Polling for Background Agents
Use this skill to orchestrate autonomous implementation loops with ralph-tui. It guides you through creating a bite-sized, spec-aligned task list (prd.json) and setting up the execution environment.
Named Tmux Manager - orchestrate multiple AI coding agents (Claude Code, Codex, Gemini) in tiled tmux panes with visual dashboards, command palette, context rotation, Agent Mail integration, and robot mode for...
Agentica server + Claude proxy setup - architecture, startup sequence, debugging
Completion Check Verify Infrastructure Is Wired
Coordinate multiple agents in parallel or sequential workflows. Use when running agents simultaneously, delegating to sub-agents, switching between specialized agents, or managing agent selection. Trigger keywo...
System health check (MOT) for skills, agents, hooks, and memory
Comprehensive status report for Startup multi-agent system. Shows bd stats, active tmux sessions, blocked issues, Decision Ledger history, and agent activity.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。