AI 概览 · 由大模型根据 SKILL.md 与仓库数据生成 · 2026年11月20日
产品工程技能合集:从决定做什么到发布上线
仓库汇集了 45 个代理技能,按代理运行环境、代理团队、AI 交付等方向分组,覆盖任务规划、编码实现、交叉评审、交接与复盘等环节。仓库简介提到这些技能来自三个已上线产品的实践,但具体能力仍以各技能文件为准。
包含 Skill
45
可以单独安装
GitHub Star
659
仓库累计 Star
近 7 天
+114
新增 Star
代码更新
2026年11月19日
最近一次推送
核心亮点
1覆盖完整链路
从需求判断到实现、评审与发布都有对应技能。
2多模型协作
提供面向不同代理的协作与委派类技能。
3工程化收尾
包含代码评审、交接与复盘等交付环节技能。
能做什么
- 按代理运行环境组织技能,便于在不同工具中复用。
- 提供代理团队协作与任务委派类技能。
- 包含代码评审类技能,用于交付前检查。
- 包含交接与复盘类技能,用于任务收尾。
- 提供规则约束类技能,把反复出现的问题固化为规则。
适用场景
为新产品功能做取舍判断并整理结论。
让一个代理实现功能,另一个代理做代码评审。
在任务交接时整理上下文与待办。
在迭代结束后做一次复盘记录。
用之前和用之后
- 需求、实现与评审分散在不同工具和对话里,上下文容易丢失。按技能分组推进,各环节有对应文件可查,交接更清晰。
- 代理反复违反同一条规则,只能每次手动提醒。可参考规则约束类技能,把要求固化为钩子或权限规则。
它是怎么工作的
第 1 步
决定做什么
第 2 步
动手实现
第 3 步
复核与发布
快速上手
安装与复制命令见“安装方式”。
- 1
打开仓库,按目录分组浏览技能列表。
- 2
阅读目标技能的 SKILL.md 了解用途与用法。
- 3
按技能文件说明在对应代理环境中配置。
- 4
在具体任务中调用该技能并检查输出。
适合谁
- 使用代理工具的产品经理
- 需要组织代理协作的研发团队
- 关注交付流程的独立开发者
局限
- 多数技能仅有简短摘要,具体步骤需回到源文件确认。
- 采集信息未提供安装命令与详细输入输出说明。
- 技能效果依赖所用代理工具与配置环境。
使用前注意
- · 多个技能被标注为高风险,使用前应阅读源文件确认行为。
- · 技能可能涉及执行命令或修改配置,建议先在测试环境验证。
包含的 Skills · 45
- Agent Instructions工作流Writing or restructuring AGENTS.md or CLAUDE.md, adding a rule ('remember this'), or after an agent ignored a rule it had: make each rule get met when it applies.agent-harness/skills/agent-instructions/SKILL.md
- Flight Deck工作流'What's the status', 'where were we', a progress report or status deck; long work that must survive compaction: multi-hour runs, background jobs, waiting on a decision.agent-harness/skills/flight-deck/SKILL.md
- Guardrail Hooks工作流An agent keeps breaking a rule ('it did it again', 'make this impossible', 'add a hook', 'my hook didn't fire'): make it a hook, permission rule or script.agent-harness/skills/guardrail-hooks/SKILL.md
- Handover工作流Write the handover a fresh session starts from: the objective, what is true now, the evidence actually obtained, what is left, the open decisions and the next concrete action, reconciled with the disk first. Started by name only: /agent-haragent-harness/skills/handover/SKILL.md
- Retro工作流Build a session's learnings into the setup: its friction, what went wrong and why, then an improved instruction, route, hook or script, verified, or 'no setup change warranted'. Started by name only: /agent-harness:retro in Claude Code, $agagent-harness/skills/retro/SKILL.md
- Windows Agent Shell工作流A coding agent on Windows: Git Bash path rewriting, PowerShell quoting and encoding, CRLF. Use when output comes back garbled, or it works here and breaks there.agent-harness/skills/windows-agent-shell/SKILL.md
- Claude Agents工作流'Ask Claude', 'have Claude build or review this': drive Claude Code headless (claude -p) from another agent as a peer, builder or fresh reviewer.agent-teams/skills/claude-agents/SKILL.md
- Codex Agents工作流'Ask Codex', 'check with Codex', handing Codex a build or review, or stuck between two framings: the Codex CLI as peer, builder or fresh reviewer.agent-teams/skills/codex-agents/SKILL.md
- Delegation工作流Before spawning a subagent or dispatching a build, review or research, and before trusting its report: the brief, the delegate, parallel runs, the handoff.agent-teams/skills/delegation/SKILL.md
- Gemini Agents工作流'Ask Gemini', 'have Gemini build or review this': Google's Antigravity CLI as a partner. It may break Google's terms on a consumer plan, so the user agrees first.agent-teams/skills/gemini-agents/SKILL.md
- Grok Agents工作流'Ask Grok', 'have Grok build or review this': drive the Grok CLI headless from another agent as a peer, builder or fresh reviewer.agent-teams/skills/grok-agents/SKILL.md
- Code Review工作流'Review this', 'find bugs', 'is this fix safe': review code for defects that matter, correctness first, each finding refuted before it's reported.ai-shipping/skills/code-review/SKILL.md
- Derive Tests工作流'What should we test' or a coverage map: derive the coverage map and missing tests from docs and code; check mode reports staleness.ai-shipping/skills/derive-tests/SKILL.md
- Document App工作流'Document the app': write or refresh an app's system docs from its code. 'Are the docs right?': check mode, which only reports where docs and code disagree.ai-shipping/skills/document-app/SKILL.md
- Independent Review工作流Before 'ship it', a deploy or release, for 'an independent review', and after each fix until a round is clean: a fresh reviewer that never saw the build.ai-shipping/skills/independent-review/SKILL.md
- Intended Vs Implemented工作流Auditing AI-built code against its docs: where it does what the docs or permissions don't say, access control against documented roles, cited both sides.ai-shipping/skills/intended-vs-implemented/SKILL.md
- Performance Audit Static工作流Only when a performance audit is asked for (ship-check asks by name; a release proposes, never runs it): static audit of N+1 queries, over-fetching, indexes, caching.ai-shipping/skills/performance-audit-static/SKILL.md
- Release Gate工作流Before 'push it', 'ship it', a deploy, release or go-live, or calling a stage done: the gate, the owner's preview, go/no-go, promote, prove it serves, roll back.ai-shipping/skills/release-gate/SKILL.md
- Security Audit Static工作流Only when a security audit is asked for (ship-check asks by name; a release proposes one, never runs it): a static audit of AI-built code against its documented trust boundaries.ai-shipping/skills/security-audit-static/SKILL.md
- Ship Check工作流Is this safe to ship? Documents the app, wires the agent's context, runs the correctness, security and performance reviews and an independent unsteered pass, maps test coverage, and compiles one reviewer-ready shipping packet. Started by naai-shipping/skills/ship-check/SKILL.md
- Shipping Artifacts工作流Documenting an AI-built app for handoff, review or audit: the docs that make it reviewable (architecture, flows, permissions, variables, coverage).ai-shipping/skills/shipping-artifacts/SKILL.md
- Test Harness工作流Writing or running tests, proving a fix, a red or flaky run, a fix that didn't land, 'is it verified', 'run the gate': tests where green means something.ai-shipping/skills/test-harness/SKILL.md
- App Lifecycle工作流Planning a SaaS stage, 'what's next', 'where are we', calling a stage done: the detailed path from an idea to production, each stage with its done-when.app-stack/skills/app-lifecycle/SKILL.md
- Chatgpt Plugin工作流Before building, submitting or changing a ChatGPT plugin or Apps SDK app: get it through OpenAI's directory review (auth, package, OAuth, data rules, portal).app-stack/skills/chatgpt-plugin/SKILL.md
- Clerk Production工作流Setting up or changing Clerk sign-in, organizations, roles or billing on Next.js, or sign-in that does nothing or lands wrong: Clerk in production.app-stack/skills/clerk-production/SKILL.md
- Embedded Agents Agent Sdk工作流Only when the Agent SDK is asked for, an agent needs Claude Code's own tools, or the app already runs it: embed Claude agents in a Next.js app with the Agent SDK.app-stack/skills/embedded-agents-agent-sdk/SKILL.md
- Embedded Agents Messages Api工作流Building, adding or wiring up an agent or an agent chat inside a Next.js app: embed Claude agents on the Messages API, the default way.app-stack/skills/embedded-agents-messages-api/SKILL.md
- Environments工作流Adding a variable or secret, 'set up production', a domain or a provider token, 'which database is this', a leaked key: dev and production for an AI-built app, backups, incidents.app-stack/skills/environments/SKILL.md
- Legal Pages工作流Privacy policy, terms, a cookie banner, consent at sign-up, a public front door: legal pages drafted from what the code does, held to it by a test, with the owner's facts and sign-off.app-stack/skills/legal-pages/SKILL.md
- Mcp ServermcpBefore adding a remote MCP server or tool to a web product, adding OAuth to it, or listing it in a directory: ship it right the first time, tests included.app-stack/skills/mcp-server/SKILL.md
- Product Analytics工作流Adding analytics, session recordings, heatmaps, 'what did users do', Clarity or PostHog: behaviour analytics without analytics cookies, read back by the agent.app-stack/skills/product-analytics/SKILL.md
- Saas Authorization工作流Adding sign-in, a role, a route that touches data, API tokens, a webhook or job, or 'is this secure': who may do what in a multi-tenant SaaS.app-stack/skills/saas-authorization/SKILL.md
- Supabase Production工作流A Supabase query, RPC or migration, 'db push', 'supabase link', RLS or grants, a Supabase error: server-only keys, deny-all RLS, migrations via the CLI.app-stack/skills/supabase-production/SKILL.md
- Transactional Email工作流Adding transactional or alert email, choosing a provider, 'sent twice', 'never arrived': app email sent once, never lost, with one-click unsubscribe.app-stack/skills/transactional-email/SKILL.md
- Ui Design工作流Mandatory for any product's screens, a builder's too, and any mock, prototype or artifact that shows them: its design system, colour, type, components; judging the look.app-stack/skills/ui-design/SKILL.md
- Uptime Monitoring工作流Publishing an app, adding /health or a cron job, 'set up monitoring', 'is it down': content checks, a second location, heartbeats, a tested alert route; Staygreen by default.app-stack/skills/uptime-monitoring/SKILL.md
- Beachhead Segment工作流Choosing the first market or customer segment to win, scored on burning pain, willingness to pay, winnable share and referrals.product/skills/beachhead-segment/SKILL.md
- Competitor Analysis工作流Competitive research or a competitive brief: competitors and substitutes, their strengths and weaknesses, where to differentiate.product/skills/competitor-analysis/SKILL.md
- Growth Loops工作流Designing how a product grows: loops that compound (viral, usage, collaboration, user-generated, referral).product/skills/growth-loops/SKILL.md
- Market Segments工作流Exploring customer segments, audiences or new markets: 3-5 segments with their jobs, pains and product fit.product/skills/market-segments/SKILL.md
- Propose工作流'I have an idea', 'is this worth building', 'what next': research it and propose what to build, with sources and key screens to review. Not for agreed changes or bugs.product/skills/propose/SKILL.md
- Start Here工作流Where to start, and what comes next, along the product lifecycle: from a new idea, new evidence, an agreed change, a bug or a release to the next step and the skill that does it. Started by name only: /product:start-here in Claude Code, $prproduct/skills/start-here/SKILL.md
- Value Curve工作流Comparing a product with competitors or choosing what to be best at: a value curve on one segment's top needs, plus price.product/skills/value-curve/SKILL.md
- Value Proposition工作流Creating or testing a value proposition: the 6-part form (Who, Why, What before, How, What after, Alternatives).product/skills/value-proposition/SKILL.md
- Work Humanizer工作流'Make this sound human', 'less AI': edit AI-sounding work writing so a careful person could have written it, without changing what it says.work-humanizer/skills/work-humanizer/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。
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。
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。
