AI 概览 · 由大模型根据 SKILL.md 与仓库数据生成 · 2026年11月18日
多智能体协作编排技能集:覆盖架构设计、代码清理与变更影响分析
该仓库以团队式多智能体编排为方向,内含多个可复用的工作流技能,覆盖架构设计、代码清理、变更影响分析、PR 跟进与调研写作等环节,多数技能标注为高风险,使用前需自行核验。
包含 Skill
84
可以单独安装
GitHub Star
40.9k
仓库累计 Star
近 7 天
+160
新增 Star
代码更新
2026年11月18日
最近一次推送
核心亮点
1流程化拆解
把开发与评审任务拆成可执行的步骤
2并行比较
可同时探索多个设计方案再逐项对比
3影响面评估
在重构前梳理改动可能波及的依赖
能做什么
- 按步骤拆解开发、调试与评审任务
- 并行探索多个设计方案并逐条比较取舍
- 清理代码中的冗余内容并支持复查模式
- 梳理改动波及的依赖并分类验证
- 跟进 PR 检查与评审状态并修复 CI
适用场景
重构前梳理改动可能影响的依赖范围
对多个候选设计方案做逐项对比
清理某批文件中的冗余代码并复查
跟进一个 PR 直到检查通过
用之前和用之后
- 重构前不清楚改动会波及哪些模块先梳理依赖并分类,再决定是否动手
- 只做一个设计方案,难以比较取舍并行探索多个方案后逐项对比再定
- 代码冗余靠人工逐行排查按技能流程清理并进入复查模式
它是怎么工作的
第 1 步
明确任务
第 2 步
并行探索
第 3 步
汇总决策
快速上手
安装与复制命令见“安装方式”。
- 1
回到源文件确认技能的调用方式
- 2
按技能说明准备目标文件或范围
- 3
执行技能并查看输出结果
- 4
对结果做回归验证
适合谁
- 使用 Claude Code 的开发者
- 需要做架构决策的工程团队
- 负责代码评审与交付的工程师
局限
- 多数技能标注为高风险,需谨慎使用
- 部分技能仅有简述,细节需回源文件确认
- 仓库简介的宣传表述不能单独证明技能能力
使用前注意
- · 多数技能标注高风险,建议先在非关键环境试用
- · 执行前确认技能作用范围,避免误改无关文件
包含的 Skills · 84
- Agent Doc Discipline工作流Agent Doc Discipline 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。skills/agent-doc-discipline/SKILL.md
- Ai Slop Cleaner工作流Ai Slop Cleaner 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。skills/ai-slop-cleaner/SKILL.md
- Architect工作流Architect 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。skills/architect/SKILL.md
- Architecture Survey工作流Architecture Survey 是一个可复用的 AI Agent Skill,适合用于资料研究、事实整理和结构化报告写作。skills/architecture-survey/SKILL.md
- Arena工作流Arena 是一个可复用的 AI Agent Skill,适合用于Run N parallel candidates at one brief and synthesize: rubric-first framing, isolated fan-out, a cross-judge on a different model, criterion-by-criterion pick, hand grafting. When one attempt would lock inskills/arena/SKILL.md
- Ask Navigator工作流Ask Navigator 是一个可复用的 AI Agent Skill,适合用于Shipyard's navigator — chart a foggy effort (destination unclear, questions not yet stateable) into a map of decision tickets on the repo's issue tracker, then work the frontier one ticket per sessiskills/ask-navigator/SKILL.md
- Ask工作流Ask 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。skills/ask/SKILL.md
- Autopilot工作流Autopilot 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。skills/autopilot/SKILL.md
- Autoresearch工作流Autoresearch 是一个可复用的 AI Agent Skill,适合用于Stateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behavior。skills/autoresearch/SKILL.md
- Babysit工作流Babysit 是一个可复用的 AI Agent Skill,适合用于Drive an open PR to merge-ready on the watch-pr verdict policy — watch checks and review state, fix CI, address comments; never merges, rebases, or force-pushes. For 'get this green' or 'babysit PR N'。skills/babysit/SKILL.md
- Benchmark Checklist工作流Benchmark Checklist 是一个可复用的 AI Agent Skill,适合用于资料研究、事实整理和结构化报告写作。skills/benchmark-checklist/SKILL.md
- Blast Radius工作流Blast Radius 是一个可复用的 AI Agent Skill,适合用于Map what a change could break beyond the diff — dependents found by search and AST, classified certain/likely/unlikely — and prove the certain and likely ones by running their checks. Before risky reskills/blast-radius/SKILL.md
- Bro工作流Bro 是一个可复用的 AI Agent Skill,适合用于Restate the last technical message in plain human language — no jargon, no shorthand, every fact and number kept. For 'say it plainly' or when a reply was too dense。skills/bro/SKILL.md
- Cancel工作流Cancel 是一个可复用的 AI Agent Skill,适合用于Cancel any active OMC mode (autopilot, ralph, ultragoal, swarm, ultrapilot, pipeline, team) and clean up retired legacy state。skills/cancel/SKILL.md
- Configure Notifications工作流Configure Notifications 是一个可复用的 AI Agent Skill,适合用于Configure notification integrations (Telegram, Discord, Slack) via natural language。skills/configure-notifications/SKILL.md
- Correct工作流Correct 是一个可复用的 AI Agent Skill,适合用于Find the mistakes agents keep repeating in this repo and make each impossible at the highest enforcing level — lint rule, type guard, runtime check, script, then text — with every enforcement proven to fiskills/correct/SKILL.md
- Create Formal Verification Skill工作流Create Formal Verification Skill 是一个可复用的 AI Agent Skill,适合用于Verify the project's riskiest invariant with TLA+, Lean, or Kani — chosen by property shape — and leave a project-local skill the next agent reruns; assumptions are part of the deskills/create-formal-verification-skill/SKILL.md
- Create Verification Skill工作流Create Verification Skill 是一个可复用的 AI Agent Skill,适合用于生成the project's own verify skill: build/test/lint commands discovered by running them, a feature map of what each covers, manual checks, and an earned first verdict. Run once per repo。skills/create-verification-skill/SKILL.md
- Debug工作流Debug 是一个可复用的 AI Agent Skill,适合用于Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction。skills/debug/SKILL.md
- Deepinit工作流Deepinit 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。skills/deepinit/SKILL.md
- Deep Interview工作流Deep Interview 是一个可复用的 AI Agent Skill,适合用于Socratic deep interview with mathematical ambiguity gating before explicit execution approval。skills/deep-interview/SKILL.md
- Diagram工作流Diagram 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。skills/diagram/SKILL.md
- Drydock工作流Drydock 是一个可复用的 AI Agent Skill,适合用于设计协作、界面方案梳理和视觉表达。skills/drydock/SKILL.md
- Execute工作流Execute 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。skills/execute/SKILL.md
- External Context工作流External Context 是一个可复用的 AI Agent Skill,适合用于Invoke parallel document-specialist agents for external web searches and documentation lookup。skills/external-context/SKILL.md
- Figure It Out工作流Figure It Out 是一个可复用的 AI Agent Skill,适合用于设计协作、界面方案梳理和视觉表达。skills/figure-it-out/SKILL.md
- Fix Ci工作流Fix Ci 是一个可复用的 AI Agent Skill,适合用于Find the failing checks on the current PR, read their logs, classify the failure (real / flaky / environmental), fix the real ones with focused changes, and rerun to green with evidence. Use when CI is redskills/fix-ci/SKILL.md
- Fix Merge Conflicts工作流Fix Merge Conflicts 是一个可复用的 AI Agent Skill,适合用于Resolve merge conflicts non-interactively: start the integration, read both sides' intent from their commits, preserve both intents, validate on the resolved tree. Never force-pushes shared brskills/fix-merge-conflicts/SKILL.md
- Get Pr Comments工作流Get Pr Comments 是一个可复用的 AI Agent Skill,适合用于Fetch and triage review threads on a PR: threads deduped with resolution state, each with a fix/dismiss/ask recommendation, bot findings read skeptically. Before addressing review feedback。skills/get-pr-comments/SKILL.md
- Graph工作流Graph 是一个可复用的 AI Agent Skill,适合用于Deterministic orchestration graph runtime - declarative DAG pipelines with journal-based crash recovery。skills/graph/SKILL.md
- Harbor工作流Harbor 是一个可复用的 AI Agent Skill,适合用于Harbor intake for external work — the captain only handles unresolved decisions. Sweeps incoming issues and PRs, verifies every claim before disposition, reuses every decision already made, and hands the mskills/harbor/SKILL.md
- Hillclimb工作流Hillclimb 是一个可复用的 AI Agent Skill,适合用于Sustained single-metric improvement loop — hypothesis, before/after measurement against a fixed baseline, decision log, one accepted commit per verified win. For targets climbed over multiple rounds; noskills/hillclimb/SKILL.md
- How工作流How 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。skills/how/SKILL.md
- Hud工作流Hud 是一个可复用的 AI Agent Skill,适合用于Configure HUD display options (layout, presets, display elements)。skills/hud/SKILL.md
- Intent工作流Intent 是一个可复用的 AI Agent Skill,适合用于资料研究、事实整理和结构化报告写作。skills/intent/SKILL.md
- Interrogate工作流Interrogate 是一个可复用的 AI Agent Skill,适合用于设计协作、界面方案梳理和视觉表达。skills/interrogate/SKILL.md
- In Your Own Words工作流In Your Own Words 是一个可复用的 AI Agent Skill,适合用于Play back the goal, the problem, and the success check in your own words when a brief is genuinely ambiguous — vague, contested, or leaving real forks open — so misunderstanding is caught cheaplskills/in-your-own-words/SKILL.md
- Ketchup工作流Ketchup 是一个可复用的 AI Agent Skill,适合用于Catch up on everything since your last message: a 1-3 sentence executive summary, one status line per action item with evidence links, and open questions. For 'catch me up' after stepping away。skills/ketchup/SKILL.md
- Ketchup Video工作流Ketchup Video 是一个可复用的 AI Agent Skill,适合用于Catch the user up like /ketchup, with a short subtitled video of slides for what happened and the waiting calls as text under it. Use for /ketchup-video。 把文本、资料或参考风格整理成演示文稿生成流程。skills/ketchup-video/SKILL.md
- Launch工作流Launch 是一个可复用的 AI Agent Skill,适合用于资料研究、事实整理和结构化报告写作。skills/launch/SKILL.md
- Loft工作流Loft 是一个可复用的 AI Agent Skill,适合用于设计协作、界面方案梳理和视觉表达。skills/loft/SKILL.md
- Maintain Formal Verification Skill工作流Maintain Formal Verification Skill 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。skills/maintain-formal-verification-skill/SKILL.md
- Maintain Verification Skill工作流Maintain Verification Skill 是一个可复用的 AI Agent Skill,适合用于Re-sync the project's verification skill when its commands drift — re-run each recorded command, update expectations and the feature map to what is true now, record the verdict actuallskills/maintain-verification-skill/SKILL.md
- Map工作流Map 是一个可复用的 AI Agent Skill,适合用于The yard's skill map — which skill owns which job, in delivery-loop order. Use when something needs doing but not which of the shipped skills owns it; the map routes, it never executes。skills/map/SKILL.md
- Minimal Code Discipline工作流Minimal Code Discipline 是一个可复用的 AI Agent Skill,适合用于内容写作、文案生成和表达润色。skills/minimal-code-discipline/SKILL.md
- Minimal Prose Discipline工作流Minimal Prose Discipline 是一个可复用的 AI Agent Skill,适合用于资料研究、事实整理和结构化报告写作。skills/minimal-prose-discipline/SKILL.md
- Models工作流Models 是一个可复用的 AI Agent Skill,适合用于Interactive setup for role-based model routing: edit team.roleRouting (provider, tier, per-provider reasoning effort; orchestrator model-only), check panel diversity, warn on missing provider CLIs。skills/models/SKILL.md
- Omc Doctor工作流Omc Doctor 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。skills/omc-doctor/SKILL.md
- Omc Setup工作流Omc Setup 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。skills/omc-setup/SKILL.md
- Personal Mode工作流Personal Mode 是一个可复用的 AI Agent Skill,适合用于Draft a user-level behavior profile from recent transcripts — cross-project preferences, habits, and standing calls stored under the user skills dir so every project's agents work the way you work.skills/personal-mode/SKILL.md
- Omc Plan工作流Omc Plan 是一个可复用的 AI Agent Skill,适合用于任务规划、步骤拆解和执行前对齐。skills/plan/SKILL.md
- Principles工作流Principles 是一个可复用的 AI Agent Skill,适合用于设计协作、界面方案梳理和视觉表达。skills/principles/SKILL.md
- Project Session Manager工作流Project Session Manager 是一个可复用的 AI Agent Skill,适合用于Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions。skills/project-session-manager/SKILL.md
- Pr工作流Pr 是一个可复用的 AI Agent Skill,适合用于Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary languskills/pr/SKILL.md
- Ralph工作流Ralph 是一个可复用的 AI Agent Skill,适合用于Self-referential loop until task completion with configurable verification reviewer。skills/ralph/SKILL.md
- Ralplan工作流Ralplan 是一个可复用的 AI Agent Skill,适合用于任务规划、步骤拆解和执行前对齐。skills/ralplan/SKILL.md
- Recall工作流Recall 是一个可复用的 AI Agent Skill,适合用于资料研究、事实整理和结构化报告写作。skills/recall/SKILL.md
- Refit工作流Refit 是一个可复用的 AI Agent Skill,适合用于资料研究、事实整理和结构化报告写作。skills/refit/SKILL.md
- Reflect工作流Reflect 是一个可复用的 AI Agent Skill,适合用于After a long task, a three-reviewer panel audits the session transcript — tooling, judgment, missed alternatives — and proposes concrete skill edits. Findings feed skillify. For banking marathon-session lskills/reflect/SKILL.md
- Release工作流Release 是一个可复用的 AI Agent Skill,适合用于Generic release assistant — analyzes repo release rules, caches them in .omc/RELEASERULE.md, then guides the release。skills/release/SKILL.md
- Remember工作流Remember 是一个可复用的 AI Agent Skill,适合用于Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs。skills/remember/SKILL.md
- Research工作流Research 是一个可复用的 AI Agent Skill,适合用于Investigate an open question and return grounded, sourced findings。skills/research/SKILL.md
- Omc Review工作流Omc Review 是一个可复用的 AI Agent Skill,适合用于Evaluate finished work for defects, risk, and simplification before it ships。skills/review/SKILL.md
- Sdd工作流Sdd 是一个可复用的 AI Agent Skill,适合用于任务规划、步骤拆解和执行前对齐。skills/sdd/SKILL.md
- Self Improve工作流Self Improve 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。skills/self-improve/SKILL.md
- Session Flow工作流Session Flow 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。skills/session-flow/SKILL.md
- Sharpen工作流Sharpen 是一个可复用的 AI Agent Skill,适合用于Aim a vague task at its real target without overspecifying: name the consumer, the observable change, the done-check, and the non-goals; at most one question when a real fork remains。skills/sharpen/SKILL.md
- Show Me Your Work工作流Show Me Your Work 是一个可复用的 AI Agent Skill,适合用于Append-only decision trail for long or autonomous work: one TSV row per non-obvious decision — what was chosen, what was rejected and why, the deciding evidence. For work a human will audit lateskills/show-me-your-work/SKILL.md
- Skillify工作流Skillify 是一个可复用的 AI Agent Skill,适合用于Turn a repeatable workflow from the current session into a reusable OMC skill draft。skills/skillify/SKILL.md
- Skill工作流Skill 是一个可复用的 AI Agent Skill,适合用于Manage local skills - list, add, remove, search, edit, setup wizard。skills/skill/SKILL.md
- Stacked Delivery工作流Stacked Delivery 是一个可复用的 AI Agent Skill,适合用于Deliver a queue of changes as one linear stacked PR chain — each PR lands on the last, verdicts record patch-ids, rebases trigger re-verification, and landing goes bottom-up only. For 'stack themskills/stacked-delivery/SKILL.md
- Statechart工作流Statechart 是一个可复用的 AI Agent Skill,适合用于资料研究、事实整理和结构化报告写作。skills/statechart/SKILL.md
- Tdd工作流Tdd 是一个可复用的 AI Agent Skill,适合用于Test-first at pre-agreed seams — one test, one implementation, tracer-bullet red/green; independent expected values; substitutions only at the seam's boundary class; launch Phase 4 reference。skills/tdd/SKILL.md
- Teach工作流Teach 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。skills/teach/SKILL.md
- Team工作流Team 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。skills/team/SKILL.md
- Technical Writing工作流Technical Writing 是一个可复用的 AI Agent Skill,适合用于One layered standard for shipping prose — docs, RFCs, readmes, PR descriptions, commit messages: outcome first, one meaning one home, checkable statements, no filler. Composes with minimal-proseskills/technical-writing/SKILL.md
- Trace工作流Trace 是一个可复用的 AI Agent Skill,适合用于Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode。skills/trace/SKILL.md
- Typescript Best Practices工作流Typescript Best Practices 是一个可复用的 AI Agent Skill,适合用于数据分析、指标解释和结论整理。skills/typescript-best-practices/SKILL.md
- Ultragoal工作流Ultragoal 是一个可复用的 AI Agent Skill,适合用于任务规划、步骤拆解和执行前对齐。skills/ultragoal/SKILL.md
- Verify工作流Verify 是一个可复用的 AI Agent Skill,适合用于Verify that a change really works before you claim completion。skills/verify/SKILL.md
- Visual Verdict工作流Visual Verdict 是一个可复用的 AI Agent Skill,适合用于Structured visual QA verdict for screenshot-to-reference comparisons。skills/visual-verdict/SKILL.md
- What Did I Get Done工作流What Did I Get Done 是一个可复用的 AI Agent Skill,适合用于Summarize authored commits over a period, grouped by theme with commit-range evidence, mechanical churn separated, and unfinished branches named. For standups and 'what did I get done'。skills/what-did-i-get-done/SKILL.md
- Why工作流Why 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。skills/why/SKILL.md
- Wiki工作流Wiki 是一个可复用的 AI Agent Skill,适合用于LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model)。skills/wiki/SKILL.md
公开来源
相关 Skills
查看更多ECC
314 Skills编程智能体技能集 · affaan-m
覆盖 Agent 评估、安全、架构审查、支付接入和网关测试等场景,可用于梳理任务流程、执行专项检查并形成结构化产出。
security-audit-skill
JavaScript代码安全审计技能 · cloudflare
用于资料研究、事实整理和结构化报告写作,适合需要按流程开展安全审计并整理结果的场景。
ponytail
6 Skills精简编程技能集 · DietrichGebert
覆盖任务拆解、代码评审、快捷参考与简化债务标记整理,适合在开发和交付过程中调用相应 Skill 辅助处理具体任务。
impeccable
20 SkillsAgent 设计语言 · pbakaus
为编码代理提供一套设计表达方式,可在开发过程中打磨界面、评审设计并检查交付前的粗糙产出,适合前端与设计协作场景。
