AI 概览 · 由大模型根据 SKILL.md 与仓库数据生成 · 2026年11月3日
面向 AI 编程代理的工程工作流集合
这是一个面向多种编码代理环境整理的 pstack 工作流集合,包含用于任务规划、变更审查、PR 跟进、偏好整理和验证等环节的 Skill。仓库简介提到将 Cursor primitives 转换到其他运行环境,但单项 Skill 的采集资料才说明具体用途;部分条目描述较简略,不能据此推断其具备未写明的能力。
包含 Skill
67
可以单独安装
GitHub Star
4,447
仓库累计 Star
近 7 天
+233
新增 Star
代码更新
2026年11月18日
最近一次推送
核心亮点
1覆盖工程环节
包含规划、代码变更分析、PR 跟进和验证相关工作流。
2输出有结构
Architect 会先记录调用者的使用方式,并根据任务规模输出类型草图或模块图及理由。
3关注核验过程
Blast Radius 的流程要求检查实际代码,并通过脚本或测试验证关键事实。
能做什么
- 将小型或大型工程变更整理为类型草图、签名或模块图。
- 分析代码变更及其影响范围,并记录已确认和已排除的风险。
- 按优先级处理 PR 状态、合并冲突、失败检查和评审意见。
- 起草或修订用于表达用户偏好和工作方式的个人 Skill。
- 根据项目情况生成项目本地的验证 Skill。
适用场景
开发前梳理小型改动的类型与函数签名。
检查一次代码变更的实际影响,并用测试验证关键判断。
跟进 PR 中的合并冲突、失败检查或评审意见。
把个人工作偏好整理成可复用的模式 Skill。
用之前和用之后
- 工程任务的步骤和预期输出可能没有明确整理。可按对应 Skill 的流程组织任务,并形成约定的输出。
- 评估代码风险可能停留在猜测。Blast Radius 流程要求查阅相关实现并验证关键事实。
- PR 的不同问题需要分别确认。Babysit 按状态分类处理冲突、检查失败和评审意见。
它是怎么工作的
第 1 步
说明任务和使用方式
第 2 步
执行对应工作流
第 3 步
检查输出并验证
快速上手
安装与复制命令见“安装方式”。
- 1
先从 Skill 清单中选择与当前任务相符的条目。
- 2
打开对应的 SKILL.md,核对触发条件、输入要求和输出说明。
- 3
在已配置该 Skill 的编码代理环境中发起相应任务。
- 4
检查生成结果;涉及代码或 PR 时按工作流要求核验实际变更。
适合谁
- 使用 AI 编码代理处理软件开发任务的开发者。
- 需要梳理代码变更影响或跟进 PR 的工程团队成员。
- 希望将个人工作偏好整理为可复用 Skill 的用户。
局限
- Skill 资料的完整程度不一,部分条目只有简短描述,无法据此确认详细输入、步骤或输出。
- 具体工作流各有适用条件,不能把某个 Skill 的流程视为所有工程任务的通用流程。
- 采集信息未提供统一的安装命令或配置步骤。
使用前注意
- · Automate Me 的描述提到可结合近期对话记录获取证据;使用前应确认哪些对话内容会被纳入处理。
- · Babysit 涉及提交、推送及评审意见处理;执行前应核对分支归属、共享状态和实际变更。
- · 不同代理环境的适配细节未在采集信息中展开,启用前应核验目标环境中的触发方式和依赖。
包含的 Skills · 67
- 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。plugins/pstack/skills/architect/SKILL.md
- Arena工作流Arena 是一个可复用的 AI Agent Skill,适合用于Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifaplugins/pstack/skills/arena/SKILL.md
- Automate Me工作流Automate Me 是一个可复用的 AI Agent Skill,适合用于Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personalplugins/pstack/skills/automate-me/SKILL.md
- Babysit工作流Babysit 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。plugins/pstack/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。plugins/pstack/skills/benchmark-checklist/SKILL.md
- Blast Radius工作流Blast Radius 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。plugins/pstack/skills/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 message in plain human language, with no jargon. Use for /bro or when asked to say it plainly。plugins/pstack/skills/bro/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 one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each cplugins/pstack/skills/correct/SKILL.md
- Create Formal Verification Skill工作流Create Formal Verification Skill 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。plugins/pstack/skills/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a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this rplugins/pstack/skills/create-verification-skill/SKILL.md
- Deslop工作流Deslop 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。plugins/pstack/skills/deslop/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。plugins/pstack/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 failing PR checks, inspect logs or external check links, and apply focused fixes。plugins/pstack/skills/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, validate build and tests, and finalize conflict resolution。plugins/pstack/skills/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 summarize review comments from the active pull request。plugins/pstack/skills/get-pr-comments/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。plugins/pstack/skills/how/SKILL.md
- Interrogate工作流Interrogate 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。plugins/pstack/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Restate in your own words what you think the user's goals are and what problem they're trying to solve. Use for /in-your-own-words。plugins/pstack/skills/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 the user up on what changed in this chat since their last message, in plain words and small visuals. List every item waiting on them with what they need to decide it from the reply alone. Use for /kplugins/pstack/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。plugins/pstack/skills/ketchup-video/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。plugins/pstack/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Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven coplugins/pstack/skills/maintain-verification-skill/SKILL.md
- Make Pr Easy To Review工作流Make Pr Easy To Review 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。plugins/pstack/skills/make-pr-easy-to-review/SKILL.md
- No Comments工作流No Comments 是一个可复用的 AI Agent Skill,适合用于Spawn the comment-sicko subagent, fix accepted findings, and offer encodings for claimed constraints。plugins/pstack/skills/no-comments/SKILL.md
- Poteto Help工作流Poteto Help 是一个可复用的 AI Agent Skill,适合用于Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question。plugins/pstack/skills/poteto-help/SKILL.md
- Poteto Mode工作流Poteto Mode 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。plugins/pstack/skills/poteto-mode/SKILL.md
- Principle Attack The Premise工作流Principle Attack The Premise 是一个可复用的 AI Agent Skill,适合用于Apply when two or more fixes that share one premise have failed the same gate. Write the premise down and test it directly before you write another fix that assumes it。plugins/pstack/skills/principle-attack-the-premise/SKILL.md
- Principle Boundary Discipline工作流Principle Boundary Discipline 是一个可复用的 AI Agent Skill,适合用于Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep busiplugins/pstack/skills/principle-boundary-discipline/SKILL.md
- Principle Build The Lever工作流Principle Build The Lever 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。plugins/pstack/skills/principle-build-the-lever/SKILL.md
- Principle Encode Lessons In Structure工作流Principle Encode Lessons In Structure 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。plugins/pstack/skills/principle-encode-lessons-in-structure/SKILL.md
- Principle Exhaust The Design Space工作流Principle Exhaust The Design Space 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。plugins/pstack/skills/principle-exhaust-the-design-space/SKILL.md
- Principle Experience First工作流Principle Experience First 是一个可复用的 AI Agent Skill,适合用于Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones。plugins/pstack/skills/principle-experience-first/SKILL.md
- Principle Explain The Number工作流Principle Explain The Number 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。plugins/pstack/skills/principle-explain-the-number/SKILL.md
- Principle Fix Root Causes工作流Principle Fix Root Causes 是一个可复用的 AI Agent Skill,适合用于Apply when debugging. Trace each symptom back to the first place the system went wrong and fix it there. A guard is a fix only when the state it handles is legitimate。plugins/pstack/skills/principle-fix-root-causes/SKILL.md
- Principle Foundational Thinking工作流Principle Foundational Thinking 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。plugins/pstack/skills/principle-foundational-thinking/SKILL.md
- Principle Guard The Context Window工作流Principle Guard The Context Window 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。plugins/pstack/skills/principle-guard-the-context-window/SKILL.md
- Principle Laziness Protocol工作流Principle Laziness Protocol 是一个可复用的 AI Agent Skill,适合用于Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem。plugins/pstack/skills/principle-laziness-protocol/SKILL.md
- Principle Make Operations Idempotent工作流Principle Make Operations Idempotent 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。plugins/pstack/skills/principle-make-operations-idempotent/SKILL.md
- Principle Migrate Callers Then Delete Legacy Apis工作流Principle Migrate Callers Then Delete Legacy Apis 是一个可复用的 AI Agent Skill,适合用于Apply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in the same wave instead of preserving compatibiliplugins/pstack/skills/principle-migrate-callers-then-delete-legacy-apis/SKILL.md
- Principle Minimize Reader Load工作流Principle Minimize Reader Load 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。plugins/pstack/skills/principle-minimize-reader-load/SKILL.md
- Principle Model The Domain工作流Principle Model The Domain 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。plugins/pstack/skills/principle-model-the-domain/SKILL.md
- Principle Never Block On The Human工作流Principle Never Block On The Human 是一个可复用的 AI Agent Skill,适合用于Apply when tempted to ask 'should I do X?' on reversible work。plugins/pstack/skills/principle-never-block-on-the-human/SKILL.md
- Principle Outcome Oriented Execution工作流Principle Outcome Oriented Execution 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。plugins/pstack/skills/principle-outcome-oriented-execution/SKILL.md
- Principle Prove It Works工作流Principle Prove It Works 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。plugins/pstack/skills/principle-prove-it-works/SKILL.md
- Principle Redesign From First Principles工作流Principle Redesign From First 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。plugins/pstack/skills/principle-redesign-from-first-principles/SKILL.md
- Principle Separate Before Serializing Shared State工作流Principle Separate Before Serializing Shared State 是一个可复用的 AI Agent Skill,适合用于Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one sharedplugins/pstack/skills/principle-separate-before-serializing-shared-state/SKILL.md
- Principle Sequence Verifiable Units工作流Principle Sequence Verifiable Units 是一个可复用的 AI Agent Skill,适合用于Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, checplugins/pstack/skills/principle-sequence-verifiable-units/SKILL.md
- Principle Subtract Before You Add工作流Principle Subtract Before You Add 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。plugins/pstack/skills/principle-subtract-before-you-add/SKILL.md
- Principle Test Behavior Not Implementation工作流Principle Test Behavior Not Implementation 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。plugins/pstack/skills/principle-test-behavior-not-implementation/SKILL.md
- Principle Type System Discipline工作流Principle Type System 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。plugins/pstack/skills/principle-type-system-discipline/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。plugins/pstack/skills/recall/SKILL.md
- Reflect工作流Reflect 是一个可复用的 AI Agent Skill,适合用于Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect。plugins/pstack/skills/reflect/SKILL.md
- Setup Pstack工作流Setup Pstack 是一个可复用的 AI Agent Skill,适合用于Configure which models pstack uses per role. Detects available models and writes the current runtime's override sheet. Use for /setup-pstack, "configure pstack models", changing pstack's model choiceplugins/pstack/skills/setup-pstack/SKILL.md
- Sharpen工作流Sharpen 是一个可复用的 AI Agent Skill,适合用于Make a task deeper, not bigger, then rewrite the prompt. Use for /sharpen。plugins/pstack/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Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the traplugins/pstack/skills/show-me-your-work/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。plugins/pstack/skills/statechart/SKILL.md
- Swarm工作流Swarm 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。plugins/pstack/skills/swarm/SKILL.md
- Tdd工作流Tdd 是一个可复用的 AI Agent Skill,适合用于Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy,plugins/pstack/skills/tdd/SKILL.md
- Teach工作流Teach 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。plugins/pstack/skills/teach/SKILL.md
- Technical Writing工作流Technical Writing 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。plugins/pstack/skills/technical-writing/SKILL.md
- Thermo Nuclear Code Quality Review工作流Thermo Nuclear Code Quality Review 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。plugins/pstack/skills/thermo-nuclear-code-quality-review/SKILL.md
- Thermo Nuclear Review提示词Thermo Nuclear Review 是一个可复用的 AI Agent Skill,适合用于Comprehensive security and correctness audit of a branch's changes. Use for thermo nuclear, thermonuclear, or deep review requests, or branch/PR diff audits focused on bugs, breaking changesplugins/pstack/skills/thermo-nuclear-review/SKILL.md
- Thermos工作流Thermos 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。plugins/pstack/skills/thermos/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TypeScript best practices. Use when reading or editing any .ts or .tsx file。plugins/pstack/skills/typescript-best-practices/SKILL.md
- Unslop工作流Unslop 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。plugins/pstack/skills/unslop/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 user-specified time period into a concise update。plugins/pstack/skills/what-did-i-get-done/SKILL.md
- Why工作流Why 是一个可复用的 AI Agent Skill,适合用于数据分析、指标解释和结论整理。plugins/pstack/skills/why/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。
