AI 技能AI 插件【免费下载链接】Product-Manager-SkillsProduct Management skills framework built on battle-tested methods for Claude Code, Cowork, Codex, and AI agents.项目地址https://gitcode.com/gh_mirrors/pr/Product-Manager-Skills点击查看免费下载本篇技术指南围绕 Product-Manager-Skills 仓库发布目录中的dist/CATALOG.md展开系统拆解这份收录77 个产品管理技能的完整目录它是如何按 Component / Interactive / Workflow 三大类型组织的、每个技能解决什么问题、以及如何从目录出发完成挑选、下载、解压和上传安装的全流程。读完本文你将掌握该技能库的分类心智模型、技能元数据SKILL.md frontmatter的真实结构以及无需终端即可用 Claude 跑 PM 技能的落地路径。一、CATALOG.md 是什么技能库的货架清单dist/CATALOG.md是 Product-Manager-Skills 仓库发布目录dist/中面向浏览者的技能总目录。它的定位非常明确文档开头即声明 All77 skillsin this library并且为每个技能提供指向同目录下独立 ZIP 包的链接——click, download, unzip, and upload theSKILL.mdto Claude. No terminal required.点击、下载、解压、上传 SKILL.md 到 Claude无需终端。这意味着 CATALOG.md 不是一份抽象的能力清单而是一份可操作的下载索引目录中的每个技能名都超链接到dist/下对应 ZIP 文件例如altitude-horizon-framework、prd-development。它与此前阅读的dist/README.md分工明确README 解释如何挑选捆绑包pack并安装CATALOG.md 则回答仓库里到底有哪些技能、每个技能干什么。1.1 目录由脚本生成非手工维护dist/CATALOG.md是由构建脚本自动生成的产物这一点在scripts/build-dist.sh中有明确实现。该脚本的第 4 步[3/4] Generating CATALOG.md and README.md内嵌了一段 Python遍历skills/*/SKILL.md读取每个技能的 YAML frontmattername、type、description按类型分组后拼出 Markdown 表格并写入dist/CATALOG.md。脚本头部注释也写明 Nothing underdist/is hand-maintained; re-run this to refresh itdist 下没有任何手工维护的内容重新运行脚本即可刷新。因此任何新增技能只需在skills/目录下按规范放置SKILL.md重新运行构建脚本CATALOG.md 便会自动纳入新条目。目录与真实技能源码skills/之间不存在漂移风险。与之配套的还有scripts/generate-catalog.py它生成的是catalog/目录下的导航产物如catalog/skills-index.yaml其中count: 77与 CATALOG.md 的统计完全一致可交叉印证。二、三大分类体系Component / Interactive / WorkflowCATALOG.md 将 77 个技能划分为三类每类都有明确的定位描述。这套分类不是随意的标签而是从scripts/build-dist.sh中的TYPES常量component/interactive/workflow到catalog/skills-index.yaml中每个技能的type字段一以贯之的一等公民元数据。分类数量官方定位Component Skills组件技能28Self-contained artifacts and templates自包含的工件与模板Interactive Skills交互技能29Guided, multi-turn advisors that ask then recommend引导式、多轮对话的顾问先提问再给建议Workflow Skills工作流技能20End-to-end processes that orchestrate other skills端到端流程编排其他技能理解这三个类型是使用整个技能库的关键Component Skills是产出物它们一次调用生成一个可交付工件——一份定位声明、一张用户故事地图、一份 EOL 公告。例如problem-statement产出以用户为中心的 problem statementuser-story产出 Mike Cohn 格式加 Gherkin 验收条件的用户故事。Interactive Skills是顾问它们通过多轮提问adaptive questions先诊断你的情境再给出建议。例如prioritization-advisor会根据产品阶段、团队上下文推荐 RICE / ICE / value-effort 中的合适框架避免框架摇摆症framework whiplash。这类技能的运行模式在workshop-facilitation中被定义为仓库的标准一次一步、进度清晰、决策点给出自适应建议、可预测地处理打断。Workflow Skills是总装线它们不直接产出单一工件而是编排多个技能完成端到端流程。例如competitive-analysis-process编排六步竞争分析landscape → product comparison → customer-need fulfillment → business baseline → perception and positioning → strategic direction每一步委托给合适的调研技能最终产出四个可执行工件。而autonomous-investigation更是所有调研类技能背后的协议限定问题预算、搜索计划闸门search-plan gate、Fact/Inference/Assumption 三级证据标注、禁止编造清单do-not-invent lists、可 diff 的稳定输出 schema。三、Component Skills 全目录28 个自包含的工件与模板Component Skills 是开箱即用的产出型技能覆盖从调研简报、定位声明到财务指标、EOL 公告等各类 PM 工件。以下为 CATALOG.md 中该分类的完整清单SkillWhat it doesaltitude-horizon-frameworkUnderstand the PM-to-Director transition through altitude and horizon thinking. Use when diagnosing scope, time-horizon, or leadership-level gaps.company-researchCreate a company research brief with executive quotes, product strategy, and org context. Use when preparing for interviews, competitive analysis, partnerships, or market-entry work.customer-journey-mapCreate a customer journey map across stages, touchpoints, actions, emotions, and metrics. Use when diagnosing a broken experience or aligning a team on the full customer flow.eol-checklistBuild a phase-gated EOL checklist sized to the sunset, with a named owner on every item. Use when the decision to retire is made and you need the operational plan.eol-internal-enablementBuild the support FAQ, sales talking points, and objection handling teams need before an EOL announcement. Use when customer-facing teams must be ready before customers hear.eol-messageWrite a right-sized EOL announcement — brief notice through full phased comms — with rationale, customer impact, and next steps. Use when retiring a product, feature, or plan.eol-stakeholder-sequencePlan who to talk to about a sunset, in what order, and what each conversation must cover. Use when an EOL decision is made and you want the landmines found before the announcement.epic-hypothesisFrame an epic as a testable hypothesis with target user, expected outcome, and validation method. Use when defining a major initiative before roadmap, discovery, or delivery planning.finance-metrics-quickrefLook up SaaS finance metrics, formulas, and benchmarks fast. Use when you need a quick metric definition, formula, or benchmark during analysis.intelligence-collection-disciplinesRun competitive research like an intelligence agency: eight collection disciplines (OSINT to MASINT), signal-to-inference chains, and fusion. Use when one-source research isnt enough.jobs-to-be-doneUncover customer jobs, pains, and gains in a structured JTBD format. Use when clarifying unmet needs, repositioning a product, or improving discovery and messaging.pestel-analysisAnalyze political, economic, social, technological, environmental, and legal forces. Use when external market shifts could materially affect a product, roadmap, or strategy.pol-probeDefine a Proof of Life probe to test a risky hypothesis cheaply. Use when you need harsh truth before building real product.positioning-statementCreate a Geoffrey Moore-style positioning statement. Use when clarifying who you serve, what problem you solve, your category, and why youre different from alternatives.press-releaseWrite an Amazon-style press release that defines customer value before building. Use when aligning stakeholders on a new product, feature, or strategic bet.problem-statementWrite a user-centered problem statement with who is blocked, what they are trying to do, why it matters, and how it feels. Use when framing discovery, prioritization, or a PRD.product-lifecycle-playsMap a products lifecycle stage and choose between extension, replacement, and retirement plays. Use when a product is maturing or declining and the next move isnt obvious.product-sense-interview-answerStructure a spoken PM product-sense answer with assumptions, segmentation, pain-point prioritization, and MVP tradeoffs. Use when practicing design, improve, or build-next interview questions.proto-personaCreate a proto-persona from current research, market signals, and team knowledge. Use when you need a working customer profile before deeper validation.recommendation-canvasEvaluate an AI product idea across outcomes, hypotheses, risks, and positioning. Use when deciding whether an AI solution deserves investment or recommendation.saas-economics-efficiency-metricsEvaluate SaaS unit economics and capital efficiency. Use when deciding whether the business can scale efficiently or needs correction.saas-revenue-growth-metricsCalculate SaaS revenue, retention, and growth metrics. Use when diagnosing momentum, churn, expansion, or product-market-fit signals.stakeholder-identificationMap every stakeholder before engaging anyone. Use when launching an initiative, scoping discovery, or building an engagement plan from scratch.stakeholder-mappingPrioritize stakeholders using two complementary grids. Use when setting engagement strategy and surfacing whose voice needs elevating after stakeholder identification.storyboardCreate a six-frame storyboard that shows a users journey from problem to solution. Use when you need a fast narrative for alignment, concept reviews, or demos.user-storyCreate user stories with Mike Cohn format and Gherkin acceptance criteria. Use when turning user needs into development-ready work with clear outcomes and testable conditions.user-story-mappingCreate a user story map that lays out activities, steps, tasks, and release slices. Use when planning a workflow, backlog, or MVP around the user journey.user-story-splittingBreak a large story or epic into smaller deliverable stories using proven split patterns. Use when backlog items are too big for estimation, sequencing, or independent release.阅读这张表的方法每个条目的描述固定采用动词开头的能力说明 Use when触发场景的双段式结构。前半句告诉你技能产出什么后半句是触发条件——这正是 CATALOG 生成脚本 直接从 SKILL.md frontmatter 的description字段提取的原文因此表中每行都可以在catalog/skills-index.yaml里找到对应的type: component条目与更详细的intent展开。四、Interactive Skills 全目录29 个引导式多轮顾问Interactive Skills 是这个库中数量最多的类型特征是先问后荐ask then recommend。它们适合情境高度依赖具体上下文、无法一次给答案的任务。完整清单如下SkillWhat it doesacquisition-channel-advisorEvaluate acquisition channels using unit economics, customer quality, and scalability. Use when deciding whether to scale, test, or kill a growth channel.agent-orchestration-advisorDesign multi-agent AI workflows with clear boundaries, handoffs, and monitoring. Use when a complex PM task should run as parallel specialized agents instead of one linear process.ai-shaped-readiness-advisorAssess whether your product work is AI-first or AI-shaped. Use when evaluating AI maturity and choosing the next team capability to build.business-health-diagnosticDiagnose SaaS business health across growth, retention, efficiency, and capital. Use when preparing a business review or prioritizing urgent fixes.context-engineering-advisorDiagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably.customer-journey-mapping-workshopRun a customer journey mapping workshop with adaptive questions and outputs. Use when you need to map stages, actions, emotions, pain points, and opportunities for a persona and scenario.derisk-measurement-advisorIdentify what to measure, test, or track to de-risk a product or AI idea. Use when stress-testing an idea across internal (DUFV) and external (PESTEL) dimensions.director-readiness-advisorGuide the PM-to-Director transition across preparing, interviewing, landing, and recalibrating. Use when leadership scope is changing and you need practical coaching.discovery-interview-prepPlan customer discovery interviews with the right goal, segment, constraints, and method. Use when preparing interviews for problem validation, churn research, or new product ideas.eol-readiness-advisorRun a go/no-go assessment for retiring a product or feature, then right-size the effort. Use when someone says we should probably kill this and nobody has made the call.epic-breakdown-advisorBreak down epics into user stories with Humanizing Work split patterns. Use when a backlog item is too large to estimate, sequence, or deliver safely.feature-investment-advisorEvaluate feature investments using revenue impact, cost structure, ROI, and strategy. Use when deciding whether a feature deserves investment.finance-based-pricing-advisorEvaluate pricing changes using ARPU, conversion, churn risk, NRR, and payback. Use when deciding whether a pricing move should ship.incoming-request-advisorDecode an incoming message into a structured breakdown separating the literal ask from the job-to-be-done. Use when a loaded Slack ping, email, mandate, or escalation needs a reply.intel-discipline-advisorTriage a competitive or market question into the right intelligence disciplines, cadence, and executing skill. Use when you know something needs researching but not which channel to run.lean-ux-canvasGuide teams through Lean UX Canvas v2. Use when framing a business problem, surfacing assumptions, and defining what to learn next.lifecycle-play-advisorDiagnose where a product sits in its lifecycle and which play fits — extend, replace, or retire. Use when a product is fading and you need the call, not just the worry.opportunity-solution-treeBuild an Opportunity Solution Tree from outcomes to opportunities, solutions, and tests. Use when a stakeholder request needs problem framing before you decide what to build.organic-growth-advisorIdentify which organic growth path to pursue — new segments, geographies, channels, or products. Use when diagnosing where a growth constraint lives and which McKinsey growth level to act on next.pm-skill-creatorDesign a new PM skill through guided conversation. Use when you have raw content or an idea and want to shape it into a compliant skill.pol-probe-advisorSelect the right Proof of Life (PoL) probe based on hypothesis, risk, and resources. Use this to match the validation method to the real learning goal, not tooling comfort.positioning-workshopRun a positioning workshop that surfaces target customer, unmet need, category, benefits, and differentiation. Use when your product messaging feels fuzzy, generic, or misaligned.prioritization-advisorChoose a prioritization framework based on stage, team context, and stakeholder needs. Use when deciding between RICE, ICE, value/effort, or another scoring approach.problem-framing-canvasGuide teams through MITREs Problem Framing Canvas. Use when you need a clearer problem statement before jumping to solutions.stakeholder-engagement-advisorPlan engagement for a specific stakeholder. Use when preparing an outreach, navigating resistance, or aligning a critical relationship before a key milestone.tam-sam-som-calculatorCalculate TAM, SAM, and SOM with explicit assumptions, methods, and caveats. Use when sizing a market for a product idea, business case, or executive review.user-story-mapping-workshopRun a user story mapping workshop with adaptive questions and a structured map output. Use when you need backbone activities, tasks, and release slices for a workflow.vp-cpo-readiness-advisorGuide the transition to VP or CPO across preparing, interviewing, landing, and recalibrating. Use when executive product scope is changing fast.workshop-facilitationFacilitate workshop sessions in a one-step, multi-turn flow. Use when an interactive skill needs consistent pacing, options, and progress tracking.值得注意的是交互技能之间存在内部协作约定多个*-workshop技能如customer-journey-mapping-workshop、user-story-mapping-workshop、positioning-workshop都遵循workshop-facilitation定义的一次一步、进度跟踪的多轮流程而*-advisor类技能intel-discipline-advisor、lifecycle-play-advisor则在诊断之后路由到具体执行技能——例如生命周期顾问会把你引导至 extension / replacement / retirement 对应的执行技能。五、Workflow Skills 全目录20 个端到端流程编排Workflow Skills 是三类中最重的它们把多个技能串成完整流程适合需要全链路而非单一工件的任务。完整清单如下SkillWhat it doesansoff-matrixMap evidence-backed growth options across the Ansoff Matrix with risk-rated sequencing. Use when the question is where the next tranche of growth comes from, and at what risk.autonomous-investigationThe protocol behind every investigation skill. Use when AI research must proceed without you: search-plan gate, Fact/Inference/Assumption labels, confidence stacking, diffable outputs.battle-card-builderResearch and draft a competitive battle card from public evidence — every claim labeled and sourced. Use when a rep needs a field-action card, not a research report.company-intelResearch a company, industry, or competitor set using web search and seven analytical lenses. Use when you need structured intel that feeds downstream PM skills.competitive-analysis-processOrchestrate a complete competitive analysis across six steps, from landscape to strategic direction. Use when you need the full picture, not a single scan or card.competitive-intel-watchScheduled delta monitoring against a prior competitive snapshot. Use when tracking competitors on a cadence: material shifts only, cited evidence, battle-card update flags, runs unattended.competitive-research-snapshotResearch a competitive landscape with cited snapshots, a comparison matrix, and so-what implications. Use when a product decision needs competitive grounding, not a market report.discovery-processRun a full discovery cycle from problem hypothesis to validated solution. Use when a team needs a structured path through framing, interviews, synthesis, and experiments.eol-processRun a product sunset end to end — decide, align, plan, prepare, announce, close. Use when you need the whole EOL process, not just one artifact.executive-onboarding-playbookPlan a VP or CPO 30-60-90 day diagnostic onboarding path. Use when entering a new executive product role and avoiding premature change.market-landscape-scanMap a markets segments, players, substitutes, and whitespace with cited evidence. Use when entering or re-evaluating a market before sizing, positioning, or picking competitors to study.pestel-delta-monitorQuarterly re-scan of a prior PESTEL analysis. Use when checking which macro factors moved, which assumptions broke, and whats new — turning PESTEL from a workshop artifact into a radar.porters-five-forcesRead an industrys structure through Porters Five Forces with documented signals per rating, ending at the profit pool. Use when weighing market entry or when margins erode and nobody can say why.prd-developmentBuild a structured PRD that connects problem, users, solution, and success criteria. Use when turning discovery notes into an engineering-ready document for a major initiative.pricing-packaging-trackerTrack competitor pricing and packaging as a diffable time series. Use when monitoring tiers, gates, limits, and price moves on a monthly or quarterly cadence.product-strategy-sessionRun an end-to-end product strategy session across positioning, discovery, and roadmap planning. Use when a team needs validated direction before committing to execution.roadmap-planningPlan a strategic roadmap across prioritization, epic definition, stakeholder alignment, and sequencing. Use when turning strategy into a release plan that teams can execute.skill-authoring-workflowTurn raw PM content into a compliant, publish-ready skill. Use when creating or updating a repo skill without breaking standards.swot-analysisBuild an evidence-cited SWOT of one company — yours or a competitors — from public sources, ending with the S-O/W-T crossings. Use for strategy reviews, board prep, or competitor depth.voice-of-customer-minerMine public reviews, app stores, and forums for unmet needs, competitor weaknesses, and switching triggers — with quoted evidence. Use when you want customer voice without waiting on interviews.工作流之间的数据流设计是这 20 个技能最值得关注的点。从目录描述可清晰看到一套快照 → 差异 → 更新的闭环competitive-research-snapshot产出稳定 schema 的竞争快照competitive-intel-watch基于上一份快照做定时差异扫描空 changelog 也是合法结果pestel-analysis的产物由pestel-delta-monitor按季度 diffthe value is catching the two that moved, not re-debating the twenty that did not。同理company-intel的七透镜结构化输出可被下游的 battle card、SWOT、positioning statement、PESTEL、market sizing 复用。这种稳定输出 schema 可 diff 可编排的设计正是autonomous-investigation协议所要求的。六、技能元数据模型目录背后的 SKILL.md frontmatterCATALOG.md 每个表格行的内容并非手工撰写而是取自技能源码的 frontmatter。以skills/prd-development/SKILL.md为例其头部字段展示了仓库的技能元数据规范--- name: prd-development argument-hint: [feature or initiative] description: Build a structured PRD that connects problem, users, solution, and success criteria. Use when turning discovery notes into an engineering-ready document for a major initiative. intent: - Guide product managers through structured PRD creation by orchestrating problem framing, user research synthesis, solution definition, and success criteria into a cohesive document... type: workflow theme: pm-artifacts best_for: - Writing a complete PRD from scratch - Structuring product requirements for an engineering handoff scenarios: - I need a PRD for a new AI-powered recommendation feature in our e-commerce platform estimated_time: 60-120 min ---关键字段与目录的对应关系如下name技能唯一标识也是 ZIP 文件名与目录中的链接锚文本typecomponent/interactive/workflow三者之一直接决定技能进入 CATALOG.md 的哪个分类表——从scripts/build-dist.sh的TYPES常量可见该枚举是强约束的description双段式描述能力 Use when 场景CATALOG.md 表格的 What it does 列即此字段原文argument-hint如[feature or initiative]提示调用时如何传参intent比 description 更长的何时用、产出什么说明完整收录在catalog/skills-index.yaml中供机器检索。这也解释了目录的一致性保证只要 SKILL.md 的 description 质量过关目录条目就自动具备同等质量反过来想在目录中看到某个技能唯一要做的是在skills/下按规范提交 SKILL.md 并重新运行构建脚本scripts/build-dist.sh。七、从目录到落地挑选、下载与安装7.1 两种获取方式dist/README.md提供了两条路径CATALOG.md 开头的提示也指向 README整包获取推荐dist/packages/下提供 9 个捆绑包下载一个 ZIP、解压后即可得到内部可直接上传的技能 ZIP。各包的定位见下表BundleBest forpm-skills-starter-pack.zipMost PMs — a small, practical starter set02-discovery-pack.zipUnderstanding customers, problems, and opportunities03-strategy-pack.zipPositioning, market thinking, product direction04-delivery-pack.zipStories, epics, PRDs, roadmap execution05-ai-pm-pack.zipAI product work06-market-intel-pack.zipCompetitive and market intelligence — the full suite07-lifecycle-eol-pack.zipAging products — extend, replace, or retire, and how to sunset well99-all-skills-pack.zipEverything — all 77 skillspm-skills-codex.zipOpenAI Codex users (.agents/skillsAGENTS.md)单技能获取直接在 CATALOG.md 的三张表中浏览点击任一技能名下载对应的独立 ZIP。这是按需安装的最小粒度方式。7.2 Claude Desktop / Web 安装步骤综合dist/README.md与docs/INSTALL-CLAUDE-DESKTOP.md下载一个捆绑包或单个技能 ZIP若是捆绑包先解压出内部的技能 ZIP 们打开 Claude进入Settings - Capabilities - Skills上传技能 ZIP新建对话并请求使用例如Use the Product Manager Skills to help me frame this product problem.。两点重要注意事项来自 README 原文不要把外层捆绑包 ZIP 直接上传必须先解压拿到内层技能 ZIPClaude Code 用户通常应走插件市场而非这些 ZIPCodex 用户则应使用pm-skills-codex.zip或直接克隆仓库分别参见docs/INSTALL-CLAUDE-CODE.md与docs/INSTALL-CODEX.md。7.3 仓库视角dist 目录与打包脚本从源码层面看dist/是组装产物目录scripts/build-dist.sh依次执行校验与构建build-release.sh、把dist/skill-zips/下的单技能 ZIP 平铺到dist/根目录、把dist/claude-desktop/与dist/codex/的包归入dist/packages/最后重新生成 CATALOG.md 与 README.md。因此目录中的每个.zip链接背后都有真实的构建产物支撑用户在浏览器中点击即可直接下载无需接触终端或命令行。八、总结如何高效使用这份目录dist/CATALOG.md的核心价值在于把 77 个技能按产出Component— 对话式顾问Interactive— 流程编排Workflow三种心智模型组织起来并让每个条目自带触发场景Use when。实际使用时可遵循以下决策路径任务是一个可交付工件定位声明、用户故事、EOL 公告、财务速查→ 去 Component Skills 表直接挑任务依赖你的具体情境、需要先诊断再决策该不该砍渠道、用哪个优先级框架、这个功能值不值得投→ 去 Interactive Skills 表挑对应 advisor或先跑*-workshop技能对齐团队任务需要跨多个阶段、多个产出完整竞争分析、产品日落、PRD 开发→ 去 Workflow Skills 表让 AI 编排整套流程并留意技能之间的快照/差异/更新数据流设计。此外目录本身由scripts/build-dist.sh自动生成、与catalog/skills-index.yaml的count: 77相互印证读者可以放心地把 CATALOG.md 当作仓库技能集的权威索引使用。赞分享AI 技能AI 插件【免费下载链接】Product-Manager-SkillsProduct Management skills framework built on battle-tested methods for Claude Code, Cowork, Codex, and AI agents.项目地址https://gitcode.com/gh_mirrors/pr/Product-Manager-Skills点击查看免费下载相关推荐Product-Manager-Skills 技能分类目录全解析Component、Interactive、Workflow 三大类型与 77 个技能的检索实战Product Manager Skills 技能分类目录全解析Component、Interactive、Workflow 三大类型与 77 个技能的检索实AI 技能AI 插件Product Manager Skills 演进全记录从 42 个技能到 77 个技能库的版本路线图Product Manager Skills 演进全记录从 42 个技能到 77 个技能库的版本路线图 Product Manager SkillsPM SAI 技能AI 插件Product-Manager-Skills 分发指南读懂 dist/ 下载货架、技能包与安装全流程Product Manager Skills 分发指南读懂 dist/ 下载货架、技能包与安装全流程 dist/ 是 Product Manager SkilAI 技能AI 插件创作声明：本文部分内容由AI辅助生成（AIGC），仅供参考