Registry durchsuchen

Alle Einträge, alphabetisch — insgesamt 57.265. Seite 174 von 230.

• planning-orchestratorUse when initiating a product project, strategic planning, or roadmap creation. Orchestrates product proposal,
• planning-patternsStructured planning methodology with research, brainstorming, phased plan creation, risk assessment, and plan-
• planning-preflightInternal planning gate: consumes the normalized repository state and makes the ONE final architectural classif
• planning-project-charterUse when generating a project charter document. Project charter auto-generation, transforming product backgrou
• planning-resourceUse when planning project resource requirements. Resource requirements auto-planning, based on project scope,
• planning-roadmapUse when you need to create a product roadmap, quarterly plan, version plan, or resource allocation. Roadmap a
• planning-under-uncertaintyPlan under uncertainty: uncertainty map, hypotheses + experiments, buffers + triggers, cadence.
• planning-with-filesTransforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledg
• planning-with-files-arنظام تخطيط الملفات بنمط Manus لتنظيم وتتبع تقدم المهام المعقدة. ينشئ ملفات task_plan.md و findings.md و progre
• planning-with-files-deManus-artiges Dateiplanungssystem zur Organisation und Verfolgung des Fortschritts komplexer Aufgaben. Erstell
• planning-with-files-esSistema de planificación basado en archivos estilo Manus para organizar y rastrear el progreso de tareas compl
• planning-with-files-zh基于 Manus 风格的文件规划系统，用于组织和跟踪复杂任务的进度。创建 task_plan.md、findings.md 和 progress.md 三个文件。当用户要求规划、拆解或组织多步骤项目、研究任务或需要超过5
• planning-with-files-zht基於 Manus 風格的檔案規劃系統，用於組織和追蹤複雜任務的進度。建立 task_plan.md、findings.md 和 progress.md 三個檔案。當使用者要求規劃、拆解或組織多步驟專案、研究任務或需要超過
• planning-workflowJeffrey Emanuel's comprehensive markdown planning methodology for software projects. The 85%+ time-on-planning
• plannotate-plasmid-annotationAuto-annotate plasmids with features (promoters, terminators, resistance, origins, tags, fluorescent proteins)
• plannotator-annotateOpen Plannotator's annotation UI for a markdown file, plain-text config file (.yaml, .json, .toml, .ini, .csv,
• plannotator-compoundAnalyze a user's Plannotator plan archive to extract denial patterns, feedback taxonomy, evolution over time,
• plannotator-lastOpen Plannotator on the latest rendered assistant message and use the returned annotations to revise that mess
• plannotator-reviewOpen Plannotator's browser-based code review UI for the current worktree or a pull request URL, then act on th
• plannotator-setup-goalTurn ideas into executable goal packages with guided interviews and codebase analysis
• plannotator-visual-explainerGenerate self-contained HTML visualizations with Plannotator theming. Use for implementation plans, PR explain
• plansUse when a user hits a plan limit or runs low on credits, asks what Gipity costs / which plan to pick / how to
• plans-kanbanView plans dashboard with progress tracking and timeline visualization. Use for kanban boards, plan status ove
• plant-protection-expertExpert plant protection specialist with 15+ years in integrated pest management (IPM), pesticide application,
• plant-seedCapture forward-looking idea as a seed for future feature design.
• plantcv-plant-phenotyping-starterA framework for discovering, compiling, and validating reusable skills for scientific agents.
• plantuml-skillUse when user requests diagrams, flowcharts, sequence diagrams, class diagrams, component diagrams, ER diagram
• plasmite-agent-messagingUse the shared `codex-agents` Plasmite pool to send messages between Codex agents, read recent messages, or wa
• plate-tectonics-analysisAnalyzing earthquake data relative to tectonic plate boundaries using PB2002 dataset and GeoPandas.
• plate-tectonics-geospatialAnalyze plate tectonics data using GeoPandas, identify points within plates, and calculate distances to bounda
• platformAndroid core components lifecycle, Activities, Fragments, Services, Intent system.
• platform-apiPlatform API skill. Use when working with Platform for channels, push, keys. Covers 22 endpoints.
• platform-arbitragePlatform arbitrage audit for a founder's product — a Diffmode growth-tactics think-tank research stage (prompt
• platform-bottleneckСкилл IWE — см. тело файла
• platform-conventionsDesign to iOS and Android conventions — what each OS mandates, where they diverge, and when to unify. Use when
• platform-detectionDetect a .NET project's test platform/framework and SDK-style vs classic project system. ALWAYS USE for "which
• platform-engineerPlatform Engineering SKILL
• platform-engineeringUse this skill when building or operating internal developer platforms: infrastructure as code, CI/CD, contain
• platform-friction-detectorUse when scanning for silent user workarounds, platform friction signals, dependency removals, or users routin
• platform-infrastructureProduce a Platform & Infrastructure Pack (capabilities plan, scaling triggers, execution roadmap).
• platform-product-managerExpert platform and API product management guidance for developer-focused products. Use when planning API prod
• platform-project-skillUse when initializing a new *-platform project, deriving from omni-platform, upgrading an existing codebase fo
• platform-skillsUse when troubleshooting, implementing, reviewing, or auditing platform infrastructure as a system — where Kub
• platform-specs-and-validationPlatform specs and publish validation — per-platform requirements and the validate-before-publish step for mul
• platform-strategistAnalyzes platform business models by distinguishing Aggregators from Platforms, mapping network effects, and i
• platform-strategyCreate a Platform Strategy Pack (charter, interface map, ecosystem model, governance, metrics).
• platformerBuild a 2D platformer: run/jump control with coyote time, jump buffering, and variable jump height, plus tiled
• playPlay .cast recordings in iTerm2 with speed controls. TRIGGERS - play recording, asciinema play, view cast.
• play-fishing-frenzyPlay Fishing Frenzy autonomously — an AI agent that fishes, cooks, dives, completes quests, and optimizes your
• play-store-release27 Android skills for AI agents (Claude Code, Codex, Cursor). Fixes Supabase auth, Hilt errors, design inconsi
• playbookRun a user-authored playbook from the vault: a multi-step guided procedure. Lists available global and local p
• playbook-design-deskdesign the customer success play library with triggers stated as an evaluable signal and threshold, entry and
• player-houseDesigns and blueprints a player's base of operations in a live Minecraft Bedrock world — a place to live, stor
• playfulness-funUse when creating animations that entertain, engage with humor, or create lighthearted interactive experiences
• playgroundCreates interactive HTML playgrounds — self-contained single-file explorers that let users configure something
• playing-to-winThis skill should be used when the user asks to evaluate, sharpen, red-team, or pressure-test a business idea,
• playtest-reportGenerates a structured playtest report template or analyzes existing playtest notes into a structured format.
• playwrightProduction-ready AI coding skills for APIs. Installable skills for Claude Code, Cursor, Codex CLI, Gemini CLI,
• playwright-apiAPI testing skill using Playwright's built-in APIRequestContext for RESTful service validation, authentication
• playwright-auth-statePlaywright workflows for authenticated browser state reuse through storageState and setup projects.
• playwright-automationWrite production-grade Playwright tests in TypeScript: Page Object Model, fixtures, auto-waiting, user-facing
• playwright-automation-expertUse when writing E2E tests with Playwright, setting up test infrastructure, debugging flaky browser tests, org
• playwright-best-practicesUse when writing or modifying Playwright tests (.spec.ts, .test.ts with @playwright/test imports).
• playwright-blazor-testingWrite UI tests for Blazor applications (Server or WebAssembly) using Playwright. Covers navigation, interactio
• playwright-browser-automationDirect Playwright API for browser automation without MCP complexity. Navigate websites, interact with elements
• playwright-browser-testingA curated guide to convention files AI agents read, write, and act on: AGENTS.md, CLAUDE.md, SKILL.md, llms.tx
• playwright-ci-cachingCache Playwright browser binaries in CI/CD pipelines (GitHub Actions, Azure DevOps) to avoid 1-2 minute downlo
• playwright-cliAutomates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the u
• playwright-cli-cloakbrowserDrive CloakBrowser Manager stealth profiles with @playwright/cli over CDP. Use for browser automation that nee
• playwright-coreConducts rigorous authoring and review of Playwright E2E tests. Enforces accessibility-first locators, web-fir
• playwright-cucumber-expertUse when writing E2E tests with Cucumber BDD and Playwright, setting up BDD test infrastructure, writing Gherk
• playwright-debuggingDiagnostic Playwright workflows for flaky or failing tests, including trace analysis, UI mode, and state isola
• playwright-droplinx-runnerUse this skill when the user drops a URL into chat and wants
• playwright-e2eComprehensive end-to-end testing skill using Playwright for web applications, covering page objects, selectors
• playwright-e2e-skillBrowser automation and E2E testing with Playwright MCP. Use when automating web pages, testing UI, debugging v
• playwright-expertUse when writing E2E tests with Playwright, setting up test infrastructure, or debugging flaky browser tests.
• playwright-figma-scrape用 Playwright MCP 系統性抓取 Figma 設計稿（screenshot / design token / layer inventory）的完整工作流。 適用於：Figma MCP 限額耗盡 / 需要批量
• playwright-interactivePersistent browser and Electron interaction through `js_repl` for fast iterative UI debugging.
• playwright-network-mockingPlaywright workflows for deterministic third-party responses using page.route().
• playwright-patternsUse when writing Playwright automation code, building web scrapers, or creating E2E tests - provides best prac
• playwright-proProduction-grade Playwright testing toolkit. Use when the user mentions Playwright tests, end-to-end testing,
• playwright-recordingRecord browser interactions as video using Playwright. Capture demo videos, app walkthroughs, and UI flows. In
• playwright-scraper-skillPlaywright-based web scraping OpenClaw Skill with anti-bot protection. Successfully tested on complex sites li
• playwright-skillComplete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test
• playwright-test-builderGenerates robust Playwright end-to-end tests for web pages and user flows.
• playwright-test-diagnosisAnalyze playwright test results
• playwright-traceInspect Playwright trace files from the command line — list actions, view requests, console, errors, snapshots
• playwright-trace-analyzerAnalyzes Playwright E2E `trace.zip` archives (and bare trace JSONL when unpacked). Extracts the action timelin
• playwright-uiRun interactive browser UI tests against the running SlateFlow dev server using MCP Playwright.
• plc-code-analysisStandalone skill for multi-perspective PLC code security and quality analysis. Triggers on: "review", "audit",
• pleaRole-playing as end users to generate authentic feature requests, surface unmet needs, and challenge team assu
• pleading-qc-and-risk-auditAudit a pleading like opposing counsel will—find the weaknesses before they do.
• pleadings-coreThe foundation for drafting civil pleadings—complaints, answers, counterclaims, cross-claims.
• please-optimize-my-claudeOptimize your CLAUDE.md hierarchy — deduplicate content across global/project/repo levels, detect misplaced se
• PleasePrompto/notebooklm-mcpMCP server for NotebookLM - Let your AI agents (Claude Code, Codex) research documentation directly with groun
• plenum-architecture-contractThe load-bearing design decisions of Plenum (smart-thermostat-with-vents), the invariants that must hold, WHY
• plexControl Plex Media Server - browse libraries, search media, check what's playing, view recently added. Use whe
• plg-fundamentalsHelp users master the transition from sales-led to product-led growth by leveraging the product itself as the
• plg-sales-integrationHelp users transition from a pure self-serve model to a hybrid motion that uses human sales to capture large e
• plg-skillUse when a SaaS founder is deciding on or building a product-led growth motion — assessing PLG readiness, choo
• plink2-gwas-analysisGWAS and population genetics tool. Processes PLINK (.bed/.bim/.fam), VCF, and BGEN; runs QC (MAF, HWE, missing
• plooc-integrationUse when integrating, refactoring, or debugging PLOOC object-oriented C - def_class encapsulation, private_mem
• plot-structureThis skill should be used when the user asks to "create a plot arc", "story structure", "add a plot point", "s
• plotext-financial-chartASCII financial line charts for markdown using plotext dot marker. TRIGGERS - financial chart, line chart, plo
• plotlyPlotly interactive visualization library. Use for interactive charts.
• plotly-interactive-plotsInteractive scientific visualization with Plotly. Two APIs: plotly.express (px) for one-liner DataFrame plots,
• plotly-interactive-visualizationInteractive visualization with Plotly. 40+ chart types (scatter, line, heatmap, 3D, geographic) with hover, zo
• plotting-agentStep 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — r
• pluginDesigns, packages, validates, and prepares distributable plugins containing skills and optional supported exte
• plugin-architectureDecides which Claude Code extension type to use for a given capability — skill, hook, MCP server, subagent, or
• plugin-auditClaude Code に導入する plugin / skill / hooks のセキュリティ・品質を自動チェックし、Pass / Warn / Fail でスコアリングする防衛スキル。
• plugin-best-practicesOpinionated conventions for designing focused agent-skill plugins as encapsulated, installable capabilities. U
• plugin-checkA CLI tool for managing project specifications and AI-powered development workflow
• plugin-compositionIntegrates multiple components inside a single Claude Code plugin — skills, hooks, MCPs, subagents, and comman
• plugin-creatorInteractive tool to scaffold a complete Claude Code plugin - plugin.json manifest, skills, agents, hooks, MCP
• plugin-dev-workflowGuide plugin development workflow — editing skills, agents, hooks, or eval framework in this repo. Use when mo
• plugin-developmentUse when packaging skills, commands, hooks, and MCP servers into a distributable plugin. Covers manifest struc
• plugin-directoryA CLI tool for managing project specifications and AI-powered development workflow
• plugin-documenterGenerates comprehensive documentation for any Claude Code plugin by fetching and analyzing all source files. U
• plugin-evaluationMeasures whether a Claude Code plugin actually works by running triggering evals (does the model pick the skil
• plugin-forgeCreate and manage Claude Code plugins with proper structure, manifests, and marketplace integration. Use when
• plugin-hooksAuthoritative guide to Claude Code hooks — event-driven scripts that execute before or after tool calls, sessi
• plugin-ideationTurns a vague "I want to build a Claude plugin" into a concrete, problem-first plugin idea — or tells you to n
• plugin-managementA plugin system for Claude Code with specialized agents, skills, and templates
• plugin-only-agent-surface-gatingSkip agent-declared MCP servers when strict plugin-only mode is active unless the agent is admin-trusted, keep
• plugin-qaValidates plugin manifest consistency, README cross-references, SKILL.md frontmatter, and version sync across
• plugin-researchValidates a plugin idea by surveying the marketplace, reading authoritative Anthropic sources, and deciding bu
• plugin-reviewReview plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.
• plugin-settingsThis skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-conf
• plugin-standardA CLI tool for managing project specifications and AI-powered development workflow
• plugin-structureThis skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin str
• plugin-system用于 Python 应用程序的通用插件系统。自动发现、验证、容错。零依赖（仅使用 Python 标准库）。
• plugin-validationValidates the structural correctness of Claude Code plugins — plugin.json manifest fields, SKILL.md YAML front
• plugin87-design-reviewReview or audit a design/UI across 6 weighted dimensions with Nielsen's 10 heuristics and a prioritized findin
• plugin87-prototypeMove an idea up the fidelity ladder (content-first → wireframe → low-fi → high-fi → code) with a validation pl
• plugins-managementCreate, publish, delete, and submit plugins for coding agents (Claude Code, OpenCode). Use when user wants to
• pluginslab-prCreate a pull request with proper branch, description, and labels
• plumbAudit code for craft — and write it craft-grade — so it stays cheap to read and change, across: intent-reveali
• plumberExpert plumber specializing in pipe installation, drainage systems, water supply, and plumbing code compliance
• plume-naturelleTransforme un texte généré par IA en texte indiscernable d'une écriture humaine. Trigger dès que l'utilisateur
• pmCreate incident postmortems by reading Slack incident channels and creating structured postmortem documents in
• pm-00-guideUse when full product methodology process navigation, product planning, or new project launch path recommendat
• pm-aarrrUse when: 产品上线后需要分析用户增长、制定增长策略、诊断产品健康度、优化AARRR各环节 Do NOT use when: 产品未上线、仅需单一指标分析无需全链路
• pm-abtestUse when: 需要验证产品优化效果、进行数据驱动的A/B实验决策、评估功能改动的因果影响 Do NOT use when: 改动无法量化测量、样本量不足、不需要严格统计验证
• pm-agileUse when: 项目启动时需要建立敏捷开发流程、设计团队协作机制、规划迭代节奏 Do NOT use when: 团队已有成熟敏捷流程、仅需单一项目管理工具而非流程设计
• pm-allOrchestrate full governance scan with prerequisite gates; default noise-filtered summary; rebuild .pm/dashboar
• pm-archScan project structure and generate Mermaid architecture diagrams + flowcharts under .pm/architecture/.
• pm-brainstormПроводит структурированный сеанс дивергенции вокруг конкретной продуктовой проблемы или возможности. Встроены
• pm-brand-motionUse when: 需要为品牌设计动效方向、制作 logo 动画 demo、定义品牌动效性格、从静态 logo 到动态展示的过渡 Do NOT use when: 需要专业级动效交付（应交给设计师）、已有成品动效无需方向
• pm-business-modelUse when: 需要设计商业模式画布、规划盈利模式、制定定价策略、设计收入模型 Do NOT use when: 商业模式已确定且已验证、仅需简单定价调整而非全面设计
• pm-career-coachPM Career Coach — guides product managers through career transitions, skill development, and growth planning U
• pm-career-growthHelp users navigate the path from junior product manager to executive leadership by focusing on ownership, cro
• pm-case-studyGenerate end-to-end PM case studies from real AI product launches, pivots, and decisions. Analyzes what happen
• pm-changeUse when: 项目进行中出现需求变更、需要评估变更影响范围和风险、记录变更历史 Do NOT use when: 变更极小无需正式评估、变更已有明确决策无需分析
• pm-charterCreate, import, discover, approve, or skip project charter; integrates Spec Kit constitution. Trigger on /pm-c
• pm-clarifyUse when: 有初步需求清单需要细化细节、需明确需求场景和边界条件、需求描述模糊需要结构化 Do NOT use when: 需求已足够详细可直达开发、仅需快速立项无需深入
• pm-competitiveГотовит многомерный разбор конкурентов — feature-матрица, SWOT с cross-strategy, 5 сил Портера, сравнение цено
• pm-competitorUse when: 需要持续监控竞品动态、建立竞品情报预警、定期输出竞品监控月报、追踪竞品版本/定价/功能/舆情/融资异动 Do NOT use when: 仅需一次性竞品调研（用 pm-market / pm-sear
• pm-crossUse when: 技术方案确定后涉及多部门协作、需要明确协作流程与职责分工、跨团队沟通困难 Do NOT use when: 单一团队独立完成、协作关系已明确无需梳理
• pm-daily-briefAI产品经理每日情报简报。手动每天调用一次,自动抓取当天 ProductHunt 榜单、GitHub Trending(daily)、Hacker News 热门,以 AI 相关为主、其他破圈热度也带,会读用户最近报告
• pm-dataUse when: 需要设计产品数据指标、规划数据埋点、建立数据监控体系、进行数据分析和趋势预测 Do NOT use when: 数据指标已明确、仅需简单统计无需指标体系
• pm-decisionUse when: 需要做重大战略决策（自研vs外包vs收购）、投资评估、多方案比较选择 Do NOT use when: 决策已由高层确定、决策影响极小无需系统分析
• pm-demandUse when: 已完成 /pm-brainstorm 后，需要系统化收集需求、验证产品想法真伪、分析用户痛点 用户明确要求"需求调研""需求验证""验证痛点""分析用户痛点" 用户明确选择跳过 brain
• pm-discoverDeep-scan all enabled governance modules and refresh state (internal; used by pm-all / status --full).
• pm-discoveryPM-focused discovery interview that uncovers the true user problem, measurable friction, and real-life impact
• pm-doc-writerWrites PM-quality documentation for AI products and solo builds following a structured stage-by-stage framewor
• pm-docsUse when: 需要输出PRD/BRD/MRD产品文档、方案文档、商业计划文档、需要文档模板 Do NOT auto-select when: 用户用自然语言说"写需求文档""写PRD""帮我设计需求"等新产品请求
• pm-doneClose a todo (TODO-xxx), sync completed.md, refresh overview Top3.
• pm-especialistaSkill criada pelo Product Guru’s que atua como um PM sênior aplicando 28 frameworks consagrados de produto (LN
• pm-exportExport desensitized governance summary markdown for sharing or machine switch. Trigger on /pm-export and relat
• pm-featureUse when: 需要细化功能实现细节、拆解复杂功能、为开发准备详细任务、功能点需多维度描述 Do NOT use when: 功能已足够简单可直接进入开发、仅需功能列表无需深度拆解
• pm-feedbackКлассифицирует пользовательский фидбек (Excel/CSV/текст) по 6 категориям, делает sentiment-анализ, кластеризац
• pm-fixAnalyze pasted logs/stacks/slow SQL from chat (or --path) into bugs findings and todos.
• pm-funnelUse when: 需要分析用户转化漏斗、诊断流失原因、生成优化建议、提升用户转化率 Do NOT use when: 用户转化路径已非常清晰、仅需单一指标监控无需全链路分析
• pm-geoUse when: 需要提升产品在 AI 搜索/生成式引擎（ChatGPT、Perplexity、AI Overviews、豆包、文心）中的可见性与被推荐率、做 GEO（Generative Engine Optimiz
• pm-growthUse when: 需要制定增长策略、优化增长指标、突破增长瓶颈、设计系统化增长方案 Do NOT use when: 产品仍在验证期未上线、仅需单一渠道优化而非系统方案
• pm-initInitialize local .pm governance workbench; detect new vs existing project; discover Spec Kit constitution; opt
• pm-interviewUse when: 需要设计用户访谈/用户调研方案、编写访谈提纲、规划样本与招募、制定访谈执行与分析方法 Do NOT use when: 仅做案头需求调研（用 pm-demand）；已有明确结论只需验证单一假设且无需访
• pm-interview-prepPM Interview Preparation — practice product sense, execution, behavioral, and strategy questions Use when: Pre
• pm-iterationUse when: 需要规划迭代内容、制定迭代排期、明确迭代优先级、从需求到排期的落地 Do NOT use when: 迭代已由团队自行规划、无需系统化管理
• pm-journeyUse when: 需要理解用户体验全链路、发现用户痛点与机会点、优化用户转化流程 Do NOT use when: 用户流程已非常清晰、仅需单一功能分析而非全局体验
• pm-managerProject governance workbench (/pm-*). Use for /pm-init, /pm-status, /pm-next, /pm-done, /pm-fix, /pm-all, /pm-
• pm-marketUse when: 需要了解市场格局与竞争态势、收集行业数据、分析竞品优劣势、评估市场机会 Do NOT use when: 市场已有充分内部调研数据、仅需简单规模估算无需深度分析
• pm-metricsДелает ревью продуктовых метрик — тренды, аномалии, root causes и рекомендации к действиям. Включает декомпози
• pm-mvpUse when: 需要确定第一版产品功能范围、已有需求清单需筛选 MVP 功能、需要确定最小可行产品边界 Do NOT use when: 产品已上线需要完整功能集、仅需梳理需求无需裁剪范围
• pm-nextClaim the single next governance todo (marks in_progress). Trigger on /pm-next and related English phrases for
• pm-okrUse when: 需要制定 OKR（目标与关键结果）、拆解公司/产品级目标、做目标对齐与 cascading、设定复盘节奏 Do NOT use when: 仅需简单待办清单（用 pm-iteration）；目标已由上
• pm-outlineGenerate detailed project outline and draft charter from user intent (empty/new projects). Trigger on /pm-outl
• pm-poolUse when: 有新需求需要录入跟踪、需求状态需要变更、需要统一管理需求池、需求数量增多需要结构化 Do NOT use when: 需求极少可直接管理、仅需一次性分析无需持续跟踪
• pm-portfolioUse when: 管理多个产品线需要组合决策、BCG矩阵分析、产品生命周期评估、资源分配 Do NOT use when: 单一产品无需组合管理、产品线已固定无需调整
• pm-positionUse when: 需要明确产品定位、设计商业模式、规划盈利方式、制定定价策略、进行盈利预测 Do NOT use when: 产品定位已明确、仅需执行无需重新定位
• pm-prdГенерирует структурированный PRD (Product Requirements Document) с шаблонами под тип продукта (B2C / B2B / вну
• pm-prd-reviewUse when: 需要评审 PRD/BRD/MRD 等需求文档的质量、检查完整性/清晰度/可行性/指标/风险/一致性、在开发前做文档把关 Do NOT use when: 文档尚未产出（应先 /pm-docs 生成）；
• pm-preview产品文档实时预览 - 在浏览器中预览 docs/ 下的所有 MD 文档，文档更新时自动刷新 Use when: 需要预览产品文档、查看 PRD/BRD/MRD 等 MD 文档的渲染效果 Do NOT use when:
• pm-prioritizeUse when ranking a list of requirements, features, or backlog items using RICE / ICE / MoSCoW / Kano. Built-in
• pm-priorityUse when: 有多个需求需要排定先后顺序、资源有限需决定先做什么、需求冲突需要客观评分 Do NOT use when: 只有一个需求无需排序、优先级已由上级/业务方明确指定
• pm-protoUse when: 需要设计产品原型、规划交互流程、确定界面布局、从PRD到视觉的过渡 Do NOT use when: 原型已由设计师完成、仅需文字描述无需视觉产出
• pm-releaseUse when: 风险管控完成后准备上线发布、需要制定上线检查清单与回滚方案、正式发版流程 Do NOT use when: 上线流程已标准化且由运维自动化执行、仅需简单发布无需检查清单
• pm-reportUse when: 需要生成数据报告、收集整理用户反馈、进行数据驱动的分析汇报 Do NOT use when: 数据已由BI系统自动生成、无需人工分析
• pm-resourceUse when: 需要在多个产品间分配研发资源、进行ROI评估、解决资源冲突、团队规划 Do NOT use when: 资源充足无需分配优先级、单产品无需多项目协调
• pm-resumePM Resume Optimization — analyze, improve, and tailor your PM resume for specific roles Use when: Updating you
• pm-retroUse when: 迭代结束后需要复盘总结经验教训、改进团队流程、记录改进行动项 Do NOT use when: 迭代尚未结束、团队不需要正式复盘
• pm-riskUse when: 技术方案完成后需要风险排查、上线前风险识别评估、项目关键节点风险管控 Do NOT use when: 项目极小风险可控、已存在完整的风险管理机制无需新建
• pm-roadmapСводит статус итерации, оценивает прогресс milestones, фиксирует изменения приоритетов, отслеживает зависимост
• pm-searchUse when: 需要进行市场调研数据收集、竞品信息采集、行业舆情监控、合规政策检查 Do NOT use when: 已有完整数据无需补充、仅需内部数据分析无需外部信息
• pm-selfcheckUse when: 需要检查super-pm skills健康状态、定期维护审计、验证元数据完整性 Do NOT use when: 正在使用某个功能skill、仅需执行产品管理任务
• pm-skill-creatorDesign a new PM skill through guided conversation. Use when you have raw content or an idea and want to shape
• pm-soulUse when preserving product intent, acceptance criteria, decision memory, open loops, roadmap context, or the
• pm-specProduct spec / PRD as a single page — problem, success metrics, scope, user stories, design notes, rollout pla
• pm-spec-writingTranslate ideas, feature requests, or vague concepts into specific, actionable dev briefs. Use this skill when
• pm-statusShow governance health, iteration progress, and today's Top3 actionable todos. Primary daily entry.
• pm-techUse when: 需要与技术团队对接技术方案、评估技术可行性、制定技术架构、评估第三方服务 Do NOT use when: 技术方案已由技术团队确定、仅需功能描述无需技术评估
• pm-user-storiesРазбивает Epic или крупное требование на независимые User Stories с acceptance criteria в формате Given-When-T
• pm-user-storyUse when: 需要将需求转化为用户故事、准备敏捷开发任务、进行需求拆分、编写验收标准 Do NOT use when: 需求已可直接进入开发、团队不使用用户故事格式
• pm-workflowFull PM/designer loop — draft an issue, interact with users and stakeholders to validate it, refine until dev-
• pm-writingRewrite or generate PM documents with extreme clarity. Applies principles of canonical docs, numbered lists ov
• pm4-smartfinance-frontend-ui-engineeringBuilds production-quality React 19 UIs that match SmartFinance conventions. Use when creating or modifying com
• pmax-auditPerformance Max campaign audit — asset group strength, asset coverage, search themes, audience signals, brand
• pmax-launch-kitBuild a complete Performance Max campaign from a brand URL — asset group copy, search themes, audience signals
• pmcontextContext for the pmcontext PM-Claude workflow plugin. Use this skill whenever any /pmcontext:* command is invok
• pmdSet up, run, and triage PMD static analysis on a Maven/Java project — the ruleset, the plugin wiring, parsing
• pmfThis skill should be used when the user asks about product-market fit — measuring it, testing it, or diagnosin
• pmmGenerate the core product marketing artifact suite for a product, feature, or segment — positioning brief, per
• pmstack-briefDraft a stakeholder brief on a topic, tailored to executive, engineering, customer, or board audience. Use whe
• pmstack-compareFeature-by-feature comparison of two or more products with built-in eval design and runnable execution. Use wh
• pmstack-competitiveGenerate a structured competitive landscape analysis for a market or product category. Use when a PM mentions
• pmstack-evalDesign a PM-runnable evaluation suite for an AI feature, implementing Anthropic's eval framework (Demystifying
• pmstack-eval-driftRe-runs an existing eval suite, diffs against the prior baseline, and writes a release-blocker memo if anythin
• pmstack-eval-gradeGrades an eval the user already has against Anthropic's eval-design principles and returns an Eval Report Card
• pmstack-eval-reportTurns a /run-eval result into a single self-contained, shareable HTML report — a verdict hero (pass/conditiona
• pmstack-eval-selfRun the pmstack self-eval suite to score every pmstack skill against canonical scenarios, with regression chec
• pmstack-launch-readinessPre-launch verifier. Aggregates PRD, metrics, eval design, eval run, premortem, eval-drift, and brief evidence
• pmstack-lintWalks the pmstack skill graph against the outputs/ directory to find graph gaps (missing downstream artifacts)
• pmstack-metricsDesign a measurement framework for an AI product or feature with North Star, supporting metrics, counter-metri
• pmstack-onboardingAn interactive 9-step tutorial that walks a new user through every pmstack capability using a realistic AI-cod
• pmstack-prdTurn a raw customer signal (quote, support ticket, feature request, exec ask) into a structured Product Requir
• pmstack-premortemRun a Klein-style pre-mortem on a draft PRD before launch — simulates 3 plausible failure stories 6 months in
• pmstack-run-evalExecute an evaluation YAML produced by pmstack-eval against a real target system, running n_trials per task an
• pmstack-sprintFull PM sprint orchestrator — chains pmstack-prd, pmstack-metrics, pmstack-eval, and pmstack-brief in sequence
• pmstack-transcript-reviewWalks a PM through Anthropic's Step 6 ritual — reading transcripts from many trials to diagnose every failed e
• pmstack-vibe-testWalks a PM through the layer-1 ritual of reading raw transcripts of an AI feature in action — what Anthropic c
• pmstack-vocSynthesize many raw customer signals (support tickets, interview snippets, churn reasons, sales notes, NPS ver
• pmstack-weeklyA Monday-morning self-snapshot for PMs. Three sections only — decisions made, open loops aging out, and one re
• pmstudioPM Studio command center. Use for a quick overview of available commands and document inventory. Use when some
• pmstudio-arbGenerate an Architecture Review Board (ARB) presentation in Coco Inc's standard 11-slide format. Use when some
• pmstudio-changelogCreate or update a structured change log for a product or platform. Use when someone asks to "create a change
• pmstudio-commsGenerate templated stakeholder communications from project context. Use when someone asks to "write a go-live
• pmstudio-drGenerate a Disaster Recovery plan with RTO/RPO targets. Use when someone asks to "create a DR plan", "disaster
• pmstudio-initUse when starting a new project, onboarding to an existing product, or setting up a documentation ecosystem fo
• pmstudio-irpGenerate an Incident Response Plan (IRP) with severity classification, escalation procedures, and communicatio