[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-74872":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":15,"forks30d":15,"starsTrendScore":19,"compositeScore":20,"rankGlobal":9,"rankLanguage":9,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":24,"hasPages":22,"topics":25,"createdAt":9,"pushedAt":9,"updatedAt":31,"readmeContent":32,"aiSummary":33,"trendingCount":15,"starSnapshotCount":15,"syncStatus":14,"lastSyncTime":34,"discoverSource":35},74872,"Product-Manager-Skills","deanpeters\u002FProduct-Manager-Skills","deanpeters","Product Management skills framework built on battle-tested methods for Claude Code, Cowork, Codex, and AI agents.",null,"Shell",5028,641,49,2,0,191,380,846,573,39.42,"Other",false,"main",true,[26,27,28,29,30],"ai-agents","ai-product-management","claude-skills","pm-frameworks","product-management","2026-06-12 02:03:29","\u003Ca id=\"pmskills\">\u003C\u002Fa>\n# Product Manager Skills\n\n![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdeanpeters\u002FProduct-Manager-Skills?style=flat-square)\n[![License: CC BY-NC-SA 4.0](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-CC%20BY--NC--SA%204.0-lightgrey?style=flat-square)](https:\u002F\u002Fgithub.com\u002Fdeanpeters\u002FProduct-Manager-Skills\u002Fblob\u002Fmain\u002FLICENSE)\n[![PRs Welcome](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-welcome-brightgreen?style=flat-square)](https:\u002F\u002Fgithub.com\u002Fdeanpeters\u002FProduct-Manager-Skills\u002Fblob\u002Fmain\u002FCONTRIBUTING.md)\n[![Version](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fversion-v0.79-blue?style=flat-square)](https:\u002F\u002Fgithub.com\u002Fdeanpeters\u002FProduct-Manager-Skills)\n[![Claude Code Plugin](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FClaude%20Code-Plugin%20Marketplace-5C4EE5?style=flat-square)](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fplugin-marketplaces)\n![Skills](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fskills-49-informational?style=flat-square)\n![Commands](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcommands-6-informational?style=flat-square)\n![Streamlit Beta](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fstreamlit-beta-orange?style=flat-square)\n\n```text\n╔════════════════════════════════════════════════════════════════════╗\n║                                                                    ║\n║   ██████╗ ███╗   ███╗    ███████╗██╗  ██╗██╗██╗     ██╗     ███████╗\n║   ██╔══██╗████╗ ████║    ██╔════╝██║ ██╔╝██║██║     ██║     ██╔════╝\n║   ██████╔╝██╔████╔██║    ███████╗█████╔╝ ██║██║     ██║     ███████╗\n║   ██╔═══╝ ██║╚██╔╝██║    ╚════██║██╔═██╗ ██║██║     ██║     ╚════██║\n║   ██║     ██║ ╚═╝ ██║    ███████║██║  ██╗██║███████╗███████╗███████║\n║   ╚═╝     ╚═╝     ╚═╝    ╚══════╝╚═╝  ╚═╝╚═╝╚══════╝╚══════╝╚══════╝\n║                                                                    ║\n║   49 battle-tested skills + 6 command workflows                    ║\n║   Claude Code • Cursor • Codex  • n8n • OpenClaw • and more ...    ║\n║                                                                    ║\n║   v0.79 • May 15, 2026 • CC BY-NC-SA 4.0                            ║\n╚════════════════════════════════════════════════════════════════════╝\n```\n\n**Help product managers become more awesome at their craft — and help them send the ladder down to others.**\n\nBattle-tested PM frameworks that teach both you and your AI agents how to do product management work at a professional level. You learn the *why*. Your agents execute the *how*. Everyone gets better.\n\nFrame problems, hunt opportunities, scaffold validation experiments, and kill bad bets fast. With frameworks from Teresa Torres, Geoffrey Moore, Amazon, MITRE, and much more from product management's greatest hits.\n\n---\n\n## Start Here\n\nChoose your setup:\n\n| I use... | Download\u002Fuse this | Best for |\n|---|---|---|\n| Claude Desktop \u002F Claude Web | [`pm-skills-starter-pack.zip`](https:\u002F\u002Fgithub.com\u002Fdeanpeters\u002FProduct-Manager-Skills\u002Freleases\u002Flatest\u002Fdownload\u002Fpm-skills-starter-pack.zip) | Nontechnical PMs |\n| Claude Code | Plugin marketplace | Terminal users |\n| Codex | [`pm-skills-codex.zip`](https:\u002F\u002Fgithub.com\u002Fdeanpeters\u002FProduct-Manager-Skills\u002Freleases\u002Flatest\u002Fdownload\u002Fpm-skills-codex.zip) or repo clone | Codex CLI\u002Fapp users |\n| I am not sure | [`pm-skills-starter-pack.zip`](https:\u002F\u002Fgithub.com\u002Fdeanpeters\u002FProduct-Manager-Skills\u002Freleases\u002Flatest\u002Fdownload\u002Fpm-skills-starter-pack.zip) | Most people |\n\n### Fastest Path\n\nDownload the starter pack here:\n\n**[`pm-skills-starter-pack.zip`](https:\u002F\u002Fgithub.com\u002Fdeanpeters\u002FProduct-Manager-Skills\u002Freleases\u002Flatest\u002Fdownload\u002Fpm-skills-starter-pack.zip)**\n\nUnzip it. Inside, you will see individual skill ZIPs.\n\nUpload those individual ZIPs to Claude Skills.\n\nAsk:\n\n```text\nUse the Product Manager Skills to help me frame this product problem.\n```\n\n### Download ZIPs\n\nAll downloadable ZIPs live on the GitHub Releases page:\n\n**[Open Product Manager Skills Releases](https:\u002F\u002Fgithub.com\u002Fdeanpeters\u002FProduct-Manager-Skills\u002Freleases\u002Flatest)**\n\nCommon downloads:\n\n- Claude starter pack: [`pm-skills-starter-pack.zip`](https:\u002F\u002Fgithub.com\u002Fdeanpeters\u002FProduct-Manager-Skills\u002Freleases\u002Flatest\u002Fdownload\u002Fpm-skills-starter-pack.zip) - unzip this, then upload the skill ZIPs inside to Claude\n- Claude discovery pack: [`02-discovery-pack.zip`](https:\u002F\u002Fgithub.com\u002Fdeanpeters\u002FProduct-Manager-Skills\u002Freleases\u002Flatest\u002Fdownload\u002F02-discovery-pack.zip) - unzip this, then upload the skill ZIPs inside to Claude\n- Claude strategy pack: [`03-strategy-pack.zip`](https:\u002F\u002Fgithub.com\u002Fdeanpeters\u002FProduct-Manager-Skills\u002Freleases\u002Flatest\u002Fdownload\u002F03-strategy-pack.zip) - unzip this, then upload the skill ZIPs inside to Claude\n- Claude delivery pack: [`04-delivery-pack.zip`](https:\u002F\u002Fgithub.com\u002Fdeanpeters\u002FProduct-Manager-Skills\u002Freleases\u002Flatest\u002Fdownload\u002F04-delivery-pack.zip) - unzip this, then upload the skill ZIPs inside to Claude\n- Claude AI PM pack: [`05-ai-pm-pack.zip`](https:\u002F\u002Fgithub.com\u002Fdeanpeters\u002FProduct-Manager-Skills\u002Freleases\u002Flatest\u002Fdownload\u002F05-ai-pm-pack.zip) - unzip this, then upload the skill ZIPs inside to Claude\n- Claude all-skills pack: [`99-all-skills-pack.zip`](https:\u002F\u002Fgithub.com\u002Fdeanpeters\u002FProduct-Manager-Skills\u002Freleases\u002Flatest\u002Fdownload\u002F99-all-skills-pack.zip) - unzip this, then upload the skill ZIPs inside to Claude\n- Codex package: [`pm-skills-codex.zip`](https:\u002F\u002Fgithub.com\u002Fdeanpeters\u002FProduct-Manager-Skills\u002Freleases\u002Flatest\u002Fdownload\u002Fpm-skills-codex.zip)\n\n### Install Guides\n\n- Claude Desktop\u002FWeb: [`docs\u002FINSTALL-CLAUDE-DESKTOP.md`](docs\u002FINSTALL-CLAUDE-DESKTOP.md)\n- Claude Code: [`docs\u002FINSTALL-CLAUDE-CODE.md`](docs\u002FINSTALL-CLAUDE-CODE.md)\n- Codex: [`docs\u002FINSTALL-CODEX.md`](docs\u002FINSTALL-CODEX.md)\n- Release packaging for maintainers: [`docs\u002FRELEASE-PACKAGING.md`](docs\u002FRELEASE-PACKAGING.md)\n\n---\n\n## 📣 Updates & Announcements\n\n### May 15, 2026 — v0.79 Community Contributions: Thank You\n\nThis one belongs to the contributors.\n\nSince v0.78, three members of the community spotted things we missed and showed up with fixes. @KNE-AI submitted `pm-skill-creator` — a new interactive skill that walks you through designing a repo-compliant skill from scratch via guided conversation, a genuinely useful addition to the meta-tooling. @xiaolai ran a full security audit of the repo's scripts and submitted two targeted fixes: a configurable input length guard in `run-pm.sh` and adapter name validation with path traversal protection in `add-a-skill.sh`. And @changyan01 and @harley-chenhailin caught a real bug: the missing `.claude-plugin\u002Fplugin.json` manifest that was silently preventing skill discovery for Claude Code users.\n\nEvery one of these contributions made the repo more useful for everyone. This is exactly the kind of community this project is trying to build.\n\n**What changed in v0.79:**\n- Added `skills\u002Fpm-skill-creator\u002F` — interactive skill for guided skill design ([@KNE-AI](https:\u002F\u002Fgithub.com\u002FKNE-AI))\n- Added configurable input length guard to `run-pm.sh` via `PM_MAX_INPUT` env var, default 4000 characters ([@xiaolai](https:\u002F\u002Fgithub.com\u002Fxiaolai))\n- Added adapter name validation and path traversal protection to `add-a-skill.sh` ([@xiaolai](https:\u002F\u002Fgithub.com\u002Fxiaolai))\n- Fixed missing `.claude-plugin\u002Fplugin.json` manifest that blocked skill discovery for Claude Code plugin users ([@changyan01](https:\u002F\u002Fgithub.com\u002Fchangyan01), [@harley-chenhailin](https:\u002F\u002Fgithub.com\u002Fharley-chenhailin))\n\nRelease note: [`docs\u002Fannouncements\u002F2026-05-15-v0-79-community-contributions.md`](docs\u002Fannouncements\u002F2026-05-15-v0-79-community-contributions.md)\n\n---\n\n### Apr 26, 2026 — v0.78 Release Packaging: One Download, Then Better PM Work\n\nThis release makes Product Manager Skills easier to use outside the repo. The job is simple: when a PM wants to use these skills with Claude or Codex, they should not have to understand GitHub folders, packaging scripts, or agent internals first.\n\n**Who this is for:** nontechnical PMs using Claude Desktop\u002FWeb, Claude Code users who prefer the plugin marketplace, Codex users who need `.agents\u002Fskills`, and maintainers who want releases to be repeatable instead of handmade.\n\n**What changed in v0.78:**\n- Claude Desktop\u002FWeb users get easy-button ZIP packs that contain individual upload-ready skill ZIPs, including a small starter pack and themed packs for discovery, strategy, delivery, and AI PM work\n- Codex users get a `codex-product-manager-skills.zip` with `.agents\u002Fskills` and `AGENTS.md`\n- Maintainers get one release command: `.\u002Fscripts\u002Fbuild-release.sh`\n- GitHub Actions now builds release artifacts on PRs, main, and version tags\n- New install docs tell each audience which path to use\n\nWhy it matters: the repo now has a source, a shelf, a storefront, and a rescue desk. `skills\u002F` remains the source of truth; `dist\u002F` becomes the generated shelf; GitHub Releases becomes the storefront; and the README helps people choose the right path without feeling lost.\n\nRelease note: [`docs\u002Fannouncements\u002F2026-04-26-v0-78-release-packaging.md`](docs\u002Fannouncements\u002F2026-04-26-v0-78-release-packaging.md)\n\n---\n\n### Mar 17, 2026 — v0.75 Pedagogic-First: Restoring What This Repo Is Actually For\n\nI want to apologize  to a contributor who recently submitted a well-intentioned and well-coded improvement that stripped learning scaffolding in favor of tighter copy. It wasn't their fault — the docs they read never crisply stated that pedagogic value is non-negotiable. We fixed that. I will work with that contribution to bring in its efficiencies while retaining the learning aspects of the skills.\n\n**What this repo is actually for:** As much as this repo is for adding skills to your agent, it's equally tasked to help product managers become more awesome at their craft, and helping them send the ladder down to others. Skills here serve both goals: they make your agent more capable, and they make you more knowledgeable about why the framework works. Neither is a byproduct of the other.\n\n**ABC — Always Be Coaching** is a key governing principle. Every skill should leave the person using it knowing more than when they started. Stripping explanation to tighten output is a defect, not an improvement.\n\nWhat changed in v0.75:\n- `README.md` — Mission statement updated to name both audiences: human PMs and AI agents\n- `CONTRIBUTING.md` — New Design Philosophy section so contributors know what they're protecting\n- `CLAUDE.md` — Pedagogic-first added to the agent's mandate, not just the style guide\n- `AGENTS.md` — New Operating Philosophy section so coding agents don't optimize away the teaching\n\nRelease note: [`docs\u002Fannouncements\u002F2026-03-17-v0-75-pedagogic-first.md`](docs\u002Fannouncements\u002F2026-03-17-v0-75-pedagogic-first.md)\n\n**Now available:** Install skills directly from Claude Code via the plugin marketplace:\n```bash\n\u002Fplugin marketplace add deanpeters\u002FProduct-Manager-Skills\n\u002Fplugin install jobs-to-be-done@pm-skills\n```\n\n---\n\n### Mar 9, 2026 — v0.7 Sharper Skills, Faster Discovery\n\nThis release is about making the library easier to trust and easier to use.\n\nAs this repo grows, the standard has to rise with it. So v0.7 focuses on the parts users actually feel:\n- finding the right skill faster,\n- understanding when to use it,\n- getting cleaner activation behavior,\n- and trusting that the repo is being actively tightened, not just expanded.\n\n#### Why it matters:\n1. You spend less time guessing which skill to use.\n2. Skills are more likely to show up in the situations where you actually need them.\n3. The library becomes easier to navigate as it grows, not more chaotic.\n4. Quality becomes a maintained promise, not a one-time cleanup.\n\n#### What shipped:\n- Trigger-oriented description updates across the skill library so skills answer both \"what it does\" and \"use this when...\"\n- New `intent` frontmatter field so every skill can keep a sharp trigger description and a richer deeper-purpose summary\n- New trigger-readiness auditing in `scripts\u002Fcheck-skill-triggers.py`\n- Trigger checks wired into `scripts\u002Ftest-library.sh`\n- New `find-a-skill.sh --mode trigger` for discovering skills by use-case language, `best_for`, and `scenarios`\n- New Streamlit (beta) `Find My Skill` mode so users can describe a situation in plain English and get recommended skills with clear next actions\n- Streamlit navigation now separates `Learn`, `Find My Skill`, and `Run Skills` so first-time users can move from confusion to action faster\n- Contributor docs updated so future skills follow the same tighter standard\n- Cross-checked the tighter standard against Anthropic's [Complete Guide to Building Skills for Claude](https:\u002F\u002Fresources.anthropic.com\u002Fhubfs\u002FThe-Complete-Guide-to-Building-Skill-for-Claude.pdf)\n\nRelease note: [`docs\u002Fannouncements\u002F2026-03-09-v0-7-skill-quality-trigger-clarity.md`](docs\u002Fannouncements\u002F2026-03-09-v0-7-skill-quality-trigger-clarity.md)\n\n---\n\n### Mar 8, 2026 — v0.65 You Asked, We Listened: Setup + Integration Everywhere\n\nYou asked, we listened. We took a moment to create comprehensive instructions on how to install, integrate, or otherwise use any one or all of these skills.\n\nWhat shipped:\n- `docs\u002FUsing PM Skills 101.md` as the complete beginner-first guide\n- `docs\u002FPlatform Guides for PMs.md` as the pick-your-tool index\n- `docs\u002FUsing PM Skills with Slash Commands 101.md` for Claude `\u002Fslash` workflows like `\u002Fpm-story` and `\u002Fpm-prd`\n- New PM-friendly platform docs for Claude Code, Claude Desktop, Claude Cowork, ChatGPT Desktop, OpenClaw, n8n, LangFlow, and Python agents\n- Updated `START_HERE.md` with comfort-level paths (chat-first, terminal-first, automation-first)\n\nHow to make the best use of this release:\n1. Start with [`docs\u002FUsing PM Skills 101.md`](docs\u002FUsing%20PM%20Skills%20101.md)\n2. Choose your platform in [`docs\u002FPlatform Guides for PMs.md`](docs\u002FPlatform%20Guides%20for%20PMs.md)\n3. Run one real task with one skill before scaling to multi-skill workflows\n\nRelease note: [`docs\u002Fannouncements\u002F2026-03-08-v0-65-onboarding-integration-guides.md`](docs\u002Fannouncements\u002F2026-03-08-v0-65-onboarding-integration-guides.md)\n\n---\n\n### Mar 6, 2026 — v0.6 Navigation + Commands\n\nWe added a command layer and fast navigation system while keeping skills as the source of truth.\n\nWhat shipped:\n- `START_HERE.md` for 60-second onboarding\n- `commands\u002F` directory with reusable multi-skill workflows\n- `catalog\u002F` generated indexes for quick browsing\n- New helper scripts: `run-pm.sh`, `find-a-command.sh`, `test-library.sh`, and `generate-catalog.py`\n- Command validation with `scripts\u002Fcheck-command-metadata.py`\n\nRelease note draft: [`docs\u002Fannouncements\u002F2026-03-06-v0-6-navigation-commands.md`](docs\u002Fannouncements\u002F2026-03-06-v0-6-navigation-commands.md)\n\n---\n\n### Feb 27, 2026 — v0.5 Streamlit (beta) Playground\n\nWe launched a new **Streamlit (beta)** interface for local skill test-driving.\n\nWhat shipped:\n- Local playground at `app\u002Fmain.py` with guided browsing and session flows\n- Multi-provider support (Anthropic, OpenAI, Ollama) with provider\u002Fmodel picker\n- Environment-variable-only API handling (`app\u002F.env.example`) for safer defaults\n- Workflow UX upgrades (phase detection fix, per-phase output persistence, run-all phases control)\n- Fast-model quality warnings on long workflows (especially PRD-style runs)\n\nDocs:\n- [`app\u002FSTREAMLIT_INTERFACE.md`](app\u002FSTREAMLIT_INTERFACE.md)\n- [`app\u002F.env.example`](app\u002F.env.example)\n\nFeedback welcome:\n- [GitHub Issues](https:\u002F\u002Fgithub.com\u002Fdeanpeters\u002FProduct-Manager-Skills\u002Fissues)\n- [Dean on LinkedIn](https:\u002F\u002Flinkedin.com\u002Fin\u002Fdeanpeters)\n\n---\n\n\u003Ca id=\"leaderskills\">\u003C\u002Fa>\n### Feb 27, 2026 — v0.5 Career & Leadership Skills Suite\n\nFour new skills covering the full product leadership career arc — from PM to Director to VP\u002FCPO — distilled from two episodes of [The Product Porch](https:\u002F\u002Fthe-product-porch-43ca35c0.simplecast.com) podcast.\n\n**Based on Episode 42 — [From PM to Director: How to Make the Shift (Part 1)](https:\u002F\u002Fthe-product-porch-43ca35c0.simplecast.com\u002Fepisodes\u002Ffrom-product-manager-to-director-how-to-make-the-shift-part-1):**\n- [`altitude-horizon-framework`](skills\u002Faltitude-horizon-framework\u002FSKILL.md) (Component) — The core mental model: altitude (scope) and horizon (time), the waiter-to-operator shift, four transition zones, named failure modes, and the Cascading Context Map\n- [`director-readiness-advisor`](skills\u002Fdirector-readiness-advisor\u002FSKILL.md) (Interactive) — Coaches PMs and new Directors across four situations: preparing, interviewing, newly landed, and recalibrating\n\n**Based on Episode 43 — [Becoming a VP & CPO: Leading Product at the Executive Level (Part 2)](https:\u002F\u002Fthe-product-porch-43ca35c0.simplecast.com\u002Fepisodes\u002Fbecoming-a-vp-cpo-leading-product-at-the-executive-level-part-2):**\n- [`executive-onboarding-playbook`](skills\u002Fexecutive-onboarding-playbook\u002FSKILL.md) (Workflow) — A 30-60-90 day diagnostic playbook for VP\u002FCPO transitions: diagnose before acting, surface unwritten strategy, assess people, act with evidence\n- [`vp-cpo-readiness-advisor`](skills\u002Fvp-cpo-readiness-advisor\u002FSKILL.md) (Interactive) — Coaches Directors and executives through the VP\u002FCPO transition, including the CEO interview framework for evaluating roles before accepting\n\n---\n\n### Feb 10, 2026 — v0.4 Facilitation Protocol Fix\n\nWe found and fixed a facilitation regression in interactive flows.\n\nWhat happened:\n- We expected guided, step-by-step facilitation with progressive context handling.\n- In practice, a brevity-focused rewrite path stripped out parts of the original facilitation modality (especially the \"walk through questions\" behavior).\n\nWhat we changed in v0.4:\n- Standardized a canonical facilitation protocol in [`skills\u002Fworkshop-facilitation\u002FSKILL.md`](skills\u002Fworkshop-facilitation\u002FSKILL.md).\n- Rolled that source-of-truth linkage across interactive skills and facilitation-heavy workflow skills.\n- Added mandatory session heads-up, `Context dump` bypass, and `Best guess` mode.\n- Added stronger progress labels, interruption handling, and decision-point recommendation rules.\n\nCredit:\n- Codex identified the protocol mismatch and implemented the fix across the repo.\n\nAnnouncement draft: [`docs\u002Fannouncements\u002F2026-02-10-v0-4-facilitation-fix.md`](docs\u002Fannouncements\u002F2026-02-10-v0-4-facilitation-fix.md)\n\n---\n\n### Feb 8, 2026 — LinkedIn Launch\n\n**Post title:** Product Management Skills for Your Agents\n**Subtitle:** Because \"just prompt better\" is not a strategy.\n\nStill rewriting PM prompts and getting generic AI output? I built a reusable PM Skills repo to help you make sharper decisions, docs, and outcomes faster.\n\n- Full announcement draft: [`docs\u002Fannouncements\u002F2026-02-08-linkedin-launch.md`](docs\u002Fannouncements\u002F2026-02-08-linkedin-launch.md)\n- Substack article draft: [`docs\u002Fannouncements\u002F2026-02-08-substack-savage-launch.md`](docs\u002Fannouncements\u002F2026-02-08-substack-savage-launch.md)\n- Announcements index: [`docs\u002Fannouncements\u002FREADME.md`](docs\u002Fannouncements\u002FREADME.md)\n- Skills repo: [Product Manager Skills](https:\u002F\u002Fgithub.com\u002Fdeanpeters\u002FProduct-Manager-Skills)\n- Prior prompts repo: [Product Manager Prompts](https:\u002F\u002Fgithub.com\u002Fdeanpeters\u002Fproduct-manager-prompts)\n\n---\n\n## 🎯 What This Is\n\n**49 ready-to-use PM skills + reusable command workflows** that teach both you and your AI agents how to do product management work at a professional level — so the PM understands the *why* and the agent can execute the *how*.\n\nInstead of saying *\"Write a PRD\"* and hoping for the best, you and your agent both know:\n- ✅ How to structure a PRD and why each section earns its place\n- ✅ What questions to ask stakeholders and what you're listening for\n- ✅ Which prioritization framework to use (and when each one breaks down)\n- ✅ How to run customer discovery interviews and what signals matter\n- ✅ How to break down epics using proven patterns — and the tradeoffs of each\n\n**Result:** You work faster, with better consistency, at a higher strategic level — and you can explain why.\n\n**Works with:** Claude Code, Cowork, OpenAI Codex, ChatGPT, Gemini, and any AI agent that can read structured knowledge.\n\n---\n\n## 🎓 Design Philosophy — Pedagogic and Practical in Equal Measure\n\nAs much as this repo is for adding skills to your agent, it's equally tasked to **help product managers become more awesome at their craft — and to help them send the ladder down to others.**\n\nSkills here serve both goals simultaneously. They equip AI agents to do PM work at a professional level, and they teach the human PM the *why* behind the framework — so they can explain it, adapt it, and pass it on.\n\n**ABC — Always Be Coaching** is a key governing principle. Every skill should leave the person using it knowing more than when they started.\n\nThis means:\n- Skills explain reasoning, not just steps\n- Examples show the thinking, not just the output\n- Anti-patterns name the failure mode so you recognize it in the wild\n- Interactive skills coach through discovery — they don't just collect answers\n\n**An edit that strips learning scaffolding to tighten copy is a defect, not an improvement.**\n\n---\n\n## ⚡ Start in 60 Seconds\n\nNew here? Start with [`START_HERE.md`](START_HERE.md).\n\n```bash\n# Run a skill (artifact\u002Fanalysis)\n.\u002Fscripts\u002Frun-pm.sh skill prioritization-advisor \"We have 12 requests and one sprint\"\n\n# Run a command (multi-skill workflow)\n.\u002Fscripts\u002Frun-pm.sh command discover \"Reduce onboarding drop-off for self-serve users\"\n```\n\nNeed discovery first?\n\n```bash\n.\u002Fscripts\u002Ffind-a-skill.sh --keyword onboarding\n.\u002Fscripts\u002Ffind-a-command.sh --keyword roadmap\n```\n\n---\n\n## Why The Command Layer Helps\n\nCommands make using skills easier without replacing skills.\n\n- Skills stay deep and pedagogic: they are the source of truth for frameworks, reasoning, and quality — for humans and agents alike.\n- Commands remove stitching work: one command chains the right skills in the right order.\n- You start faster: less \"which skill should I run first?\" and fewer manual handoffs.\n- Outputs are more consistent: commands enforce checkpoints, then defer to skill-level rigor.\n- Teams onboard quicker: new users can run `\u002Fdiscover` or `\u002Fwrite-prd` and learn the skill system while shipping.\n\nIn short: **skills provide expertise; commands provide momentum.**\n\n---\n\n## 🧪 Streamlit (beta)\n\nWant a quick local test-drive before using skills in your agent workflow?\n\n```bash\npip install -r app\u002Frequirements.txt\nstreamlit run app\u002Fmain.py\n```\n\nWhat you can do in v0.7:\n- `Learn` setup and integration paths without leaving the app\n- `Find My Skill` by describing your situation in plain English\n- `Run Skills` with your own scenario once you know what you want\n\nThis beta interface is a feature in flight. Feedback is welcome via [GitHub Issues](https:\u002F\u002Fgithub.com\u002Fdeanpeters\u002FProduct-Manager-Skills\u002Fissues) or [LinkedIn](https:\u002F\u002Flinkedin.com\u002Fin\u002Fdeanpeters).\n\n---\n\n## ✅ Safety and Evaluation\n\nBefore using any skill:\n- Review the skill file and any linked resources. If it includes `scripts\u002F`, read them before running.\n- Prefer least privilege. Skills should not require secrets or network access unless explicitly documented.\n- Do a quick dry run with a realistic prompt, then refine `name` and `description` for better discoverability.\n- Run `python3 scripts\u002Fcheck-skill-triggers.py --show-cases` before packaging if you want a quick trigger-readiness pass.\n\n---\n\n## 🧰 Optional Scripts (Deterministic Helpers)\n\nSome skills include a `scripts\u002F` folder with deterministic helpers for calculations or formatting. These are optional, should be audited before running, and should avoid network calls or external dependencies.\n\n**Examples:**\n- `skills\u002Ftam-sam-som-calculator\u002Fscripts\u002Fmarket-sizing.py`\n- `skills\u002Fuser-story\u002Fscripts\u002Fuser-story-template.py`\n\n---\n\n## 🤖 Skill Creation Utility\n\n**Want to create your own skills?** Choose one of these utilities:\n\n- `scripts\u002Fadd-a-skill.sh` - Content-first, AI-assisted generation from notes\u002Fframeworks.\n- `scripts\u002Fbuild-a-skill.sh` - Guided \"build-a-bear\" wizard that prompts section-by-section.\n- `scripts\u002Ffind-a-skill.sh` - Search skills by name\u002Ftype\u002Fkeyword with ranked results.\n- `scripts\u002Ffind-a-command.sh` - Search commands by name\u002Fkeyword\u002Fused skills.\n- `scripts\u002Frun-pm.sh` - Fast runner for either a skill or a command.\n- `scripts\u002Ftest-a-skill.sh` - Run strict conformance checks and optional smoke checks.\n- `scripts\u002Fcheck-skill-triggers.py` - Audit frontmatter descriptions and scenario prompts for Claude-style triggering.\n- `scripts\u002Ftest-library.sh` - Validate skills, commands, and regenerate catalogs.\n- `scripts\u002Fzip-a-skill.sh` - Build upload-ready `.zip` files by skill, type, or all skills.\n- `scripts\u002Fgenerate-catalog.py` - Regenerate skill\u002Fcommand navigation indexes.\n\n**New to terminals?** See [`scripts\u002FREADME.md`](scripts\u002FREADME.md) for a plain-language walkthrough.\n**Power users:** These scripts are designed to chain together into fast end-to-end workflows (idea -> prompt -> validation -> packaging).\n\n**What it does:**\n1. Analyzes your content and suggests skill types\n2. Generates complete skill files with examples\n3. Validates metadata for marketplace compliance\n4. Updates documentation automatically\n\n**Usage:**\n```bash\n# From a file\n.\u002Fscripts\u002Fadd-a-skill.sh research\u002Fyour-framework.md\n\n# Guided wizard\n.\u002Fscripts\u002Fbuild-a-skill.sh\n\n# Find a skill\n.\u002Fscripts\u002Ffind-a-skill.sh --keyword pricing --type interactive\n\n# Find a command\n.\u002Fscripts\u002Ffind-a-command.sh --keyword roadmap\n\n# Run a command workflow\n.\u002Fscripts\u002Frun-pm.sh command write-prd \"Mobile onboarding redesign\"\n\n# Test one skill\n.\u002Fscripts\u002Ftest-a-skill.sh --skill finance-based-pricing-advisor --smoke\n\n# Test full library surface\n.\u002Fscripts\u002Ftest-library.sh\n\n# Build Claude upload zip for one skill\n.\u002Fscripts\u002Fzip-a-skill.sh --skill finance-based-pricing-advisor\n\n# Build Claude upload zips for all skills\n.\u002Fscripts\u002Fzip-a-skill.sh --all --output dist\u002Fskill-zips\n\n# Build Claude upload zips for one category (component|interactive|workflow)\n.\u002Fscripts\u002Fzip-a-skill.sh --type component --output dist\u002Fskill-zips\n\n# Build curated starter pack\n.\u002Fscripts\u002Fzip-a-skill.sh --preset core-pm --output dist\u002Fskill-zips\n\n# Show available curated presets\n.\u002Fscripts\u002Fzip-a-skill.sh --list-presets\n\n# From clipboard\npbpaste | .\u002Fscripts\u002Fadd-a-skill.sh\n\n# Check available adapters\n.\u002Fscripts\u002Fadd-a-skill.sh --list-agents\n```\n\n**Agent support:** Claude Code, Manual mode (works with any CLI), and custom adapters via `scripts\u002Fadapters\u002FADAPTER_TEMPLATE.sh`\n\n**Learn more:** See [`docs\u002FAdd-a-Skill Utility Guide.md`](docs\u002FAdd-a-Skill%20Utility%20Guide.md) for complete guide.\n**Cloning locally?** Start with [`docs\u002FBuilding PM Skills.md#local-clone-quickstart`](docs\u002FBuilding%20PM%20Skills.md#local-clone-quickstart).\n\n---\n\n## ✅ Claude Web Upload Checklist\n\n- Keep frontmatter `name` \u003C= 64 chars and `description` \u003C= 200 chars.\n- Use `intent` for the richer repo-facing explanation of the skill, while keeping `description` short and trigger-oriented.\n- Ensure the skill folder name matches the `name` value.\n- Use `scripts\u002Fzip-a-skill.sh --skill \u003Cskill-name>` (or `--type component`, `--preset core-pm`) to generate upload-ready ZIPs.\n- (Advanced) Use `scripts\u002Fpackage-claude-skills.sh` if you need unpacked upload-ready folders.\n- Validate metadata with `scripts\u002Fcheck-skill-metadata.py`.\n- For GitHub ZIP upload flow, see [`docs\u002FUsing PM Skills with Claude.md`](docs\u002FUsing%20PM%20Skills%20with%20Claude.md#github-zip-install).\n\n---\n\n## 🏗️ Three-Tier Architecture (How Skills Work Together)\n\nThese 49 skills are organized into **three types** that build on each other:\n\n```text\n┌───────────────────────────────────────────────────────────┐\n│  WORKFLOW SKILLS (6)                                      │\n│  Complete end-to-end PM processes                         │\n│  Example: \"Run a product strategy session\"                │\n│  Timeline: 2-4 weeks                                      │\n└───────────────────────────────────────────────────────────┘\n                         ↓ orchestrates\n┌───────────────────────────────────────────────────────────┐\n│  INTERACTIVE SKILLS (20)                                  │\n│  Guided discovery with adaptive questions                 │\n│  Example: \"Which prioritization framework should I use?\"  │\n│  Timeline: 30-90 minutes                                  │\n└───────────────────────────────────────────────────────────┘\n                         ↓ uses\n┌───────────────────────────────────────────────────────────┐\n│  COMPONENT SKILLS (21)                                    │\n│  Templates for specific PM deliverables                   │\n│  Example: \"Write a user story\"                            │\n│  Timeline: 10-30 minutes                                  │\n└───────────────────────────────────────────────────────────┘\n```\n\n### Component Skills (21) — Templates & Artifacts\n**What:** Reusable templates for creating specific PM deliverables (user stories, positioning statements, epics, personas, PRDs, etc.)\n\n**When to use:** You need a standard template or format for a specific deliverable.\n\n**Example:** \"Write a user story with acceptance criteria\" → Use [`user-story.md`](skills\u002Fuser-story\u002FSKILL.md)\n\n---\n\n### Interactive Skills (22) — Guided Discovery\n**What:** Multi-turn conversational flows where AI asks you 3-5 adaptive questions, then offers smart recommendations based on your context.\n\n**When to use:** You need help deciding which approach to take or gathering context before executing.\n\n**Example:** \"Which prioritization framework should I use?\" → Run [`prioritization-advisor.md`](skills\u002Fprioritization-advisor\u002FSKILL.md), which asks about your product stage, team size, data availability, then recommends RICE, ICE, Kano, or other frameworks.\n\n**How they work:**\n1. AI asks 3-5 questions about your context\n2. You answer (or pick from numbered options)\n3. AI offers 3-5 tailored recommendations\n4. You choose one (or combine approaches)\n5. AI executes using the right component skills\n\n---\n\n### Workflow Skills (6) — End-to-End Processes\n**What:** Complete PM processes that orchestrate multiple component and interactive skills over days\u002Fweeks.\n\n**When to use:** You need to run a full PM workflow from start to finish (strategy session, discovery cycle, roadmap planning, PRD creation).\n\n**Example:** \"Align stakeholders on product strategy\" → Run [`product-strategy-session.md`](skills\u002Fproduct-strategy-session\u002FSKILL.md), which guides you through positioning → problem framing → solution exploration → roadmap planning over 2-4 weeks.\n\n---\n\n## 📦 All 49 Skills (Clickable)\n\nNow that you understand the three types, here's the complete catalog:\n\n### 🧱 Component Skills (21)\n\n| Skill | Use When You Need To... |\n|-------|-------------------------|\n| **[altitude-horizon-framework](skills\u002Faltitude-horizon-framework\u002FSKILL.md)** | Understand the PM→Director mindset shift: altitude (scope), horizon (time), four transition zones, failure modes, and the Cascading Context Map. Based on [The Product Porch E42](https:\u002F\u002Fthe-product-porch-43ca35c0.simplecast.com\u002Fepisodes\u002Ffrom-product-manager-to-director-how-to-make-the-shift-part-1) |\n| **[company-research](skills\u002Fcompany-research\u002FSKILL.md)** | Deep-dive competitor or company analysis |\n| **[customer-journey-map](skills\u002Fcustomer-journey-map\u002FSKILL.md)** | Map customer experience across all touchpoints (NNGroup framework) |\n| **[eol-message](skills\u002Feol-message\u002FSKILL.md)** | Communicate product\u002Ffeature deprecation gracefully |\n| **[epic-hypothesis](skills\u002Fepic-hypothesis\u002FSKILL.md)** | Turn vague initiatives into testable hypotheses with success metrics |\n| **[finance-metrics-quickref](skills\u002Ffinance-metrics-quickref\u002FSKILL.md)** | Fast lookup table for 32+ SaaS finance metrics with formulas, benchmarks, and when to use each |\n| **[jobs-to-be-done](skills\u002Fjobs-to-be-done\u002FSKILL.md)** | Understand what customers are trying to accomplish (JTBD framework) |\n| **[pestel-analysis](skills\u002Fpestel-analysis\u002FSKILL.md)** | Analyze external factors (Political, Economic, Social, Tech, Environmental, Legal) |\n| **[pol-probe](skills\u002Fpol-probe\u002FSKILL.md)** | Define lightweight, disposable validation experiments to test hypotheses before building (Dean Peters PoL framework) |\n| **[positioning-statement](skills\u002Fpositioning-statement\u002FSKILL.md)** | Define who you serve, what problem you solve, and how you're different (Geoffrey Moore framework) |\n| **[press-release](skills\u002Fpress-release\u002FSKILL.md)** | Write a future press release to clarify product vision (Amazon Working Backwards) |\n| **[problem-statement](skills\u002Fproblem-statement\u002FSKILL.md)** | Frame a customer problem with evidence before jumping to solutions |\n| **[product-sense-interview-answer](skills\u002Fproduct-sense-interview-answer\u002FSKILL.md)** | Structure a spoken product-sense answer with assumptions, segmentation, pain-point prioritization, and MVP tradeoffs |\n| **[proto-persona](skills\u002Fproto-persona\u002FSKILL.md)** | Create hypothesis-driven personas before doing full research |\n| **[recommendation-canvas](skills\u002Frecommendation-canvas\u002FSKILL.md)** | Document AI-powered product recommendations |\n| **[saas-economics-efficiency-metrics](skills\u002Fsaas-economics-efficiency-metrics\u002FSKILL.md)** | Evaluate unit economics and capital efficiency (CAC, LTV, payback, margins, burn rate, Rule of 40, magic number) |\n| **[saas-revenue-growth-metrics](skills\u002Fsaas-revenue-growth-metrics\u002FSKILL.md)** | Calculate and interpret revenue, retention, and growth metrics (revenue, ARPU, MRR\u002FARR, churn, NRR, expansion) |\n| **[storyboard](skills\u002Fstoryboard\u002FSKILL.md)** | Visualize user journeys with 6-frame narrative storyboards |\n| **[user-story](skills\u002Fuser-story\u002FSKILL.md)** | Write user stories with proper acceptance criteria (Mike Cohn + Gherkin) |\n| **[user-story-mapping](skills\u002Fuser-story-mapping\u002FSKILL.md)** | Organize stories by user workflow (Jeff Patton framework) |\n| **[user-story-splitting](skills\u002Fuser-story-splitting\u002FSKILL.md)** | Break down large stories using 8 proven patterns |\n\n---\n\n### 🔄 Interactive Skills (22)\n\n| Skill | What It Does |\n|-------|--------------|\n| **[acquisition-channel-advisor](skills\u002Facquisition-channel-advisor\u002FSKILL.md)** | Evaluate acquisition channels using unit economics, customer quality, and scalability. Recommends scale\u002Ftest\u002Fkill decisions |\n| **[ai-shaped-readiness-advisor](skills\u002Fai-shaped-readiness-advisor\u002FSKILL.md)** | Assess if you're \"AI-first\" (automating tasks) or \"AI-shaped\" (redesigning how you work). Evaluates 5 competencies and recommends which to build first |\n| **[business-health-diagnostic](skills\u002Fbusiness-health-diagnostic\u002FSKILL.md)** | Diagnose SaaS business health using key metrics, identify red flags, and prioritize actions. Analyzes growth, retention, efficiency, and capital health |\n| **[context-engineering-advisor](skills\u002Fcontext-engineering-advisor\u002FSKILL.md)** | Diagnose context stuffing (volume without intent) vs. context engineering (structure for attention). Guides memory architecture, retrieval strategies, and Research→Plan→Reset→Implement cycle |\n| **[customer-journey-mapping-workshop](skills\u002Fcustomer-journey-mapping-workshop\u002FSKILL.md)** | Guides journey mapping with pain point identification |\n| **[director-readiness-advisor](skills\u002Fdirector-readiness-advisor\u002FSKILL.md)** | Coaches PMs and new Directors through the transition across four situations: preparing, interviewing, newly landed, recalibrating. Based on [The Product Porch E42](https:\u002F\u002Fthe-product-porch-43ca35c0.simplecast.com\u002Fepisodes\u002Ffrom-product-manager-to-director-how-to-make-the-shift-part-1) |\n| **[discovery-interview-prep](skills\u002Fdiscovery-interview-prep\u002FSKILL.md)** | Plans customer interviews (Mom Test style) based on your research goals |\n| **[epic-breakdown-advisor](skills\u002Fepic-breakdown-advisor\u002FSKILL.md)** | Splits epics into user stories using Richard Lawrence's 9 patterns |\n| **[feature-investment-advisor](skills\u002Ffeature-investment-advisor\u002FSKILL.md)** | Evaluate feature investments using revenue impact, cost structure, ROI, and strategic value. Delivers build\u002Fdon't build recommendations |\n| **[finance-based-pricing-advisor](skills\u002Ffinance-based-pricing-advisor\u002FSKILL.md)** | Evaluate pricing changes using financial impact analysis (ARPU\u002FARPA, conversion, churn risk, NRR, payback) |\n| **[lean-ux-canvas](skills\u002Flean-ux-canvas\u002FSKILL.md)** | Sets up hypothesis-driven planning (Jeff Gothelf Lean UX Canvas v2) |\n| **[opportunity-solution-tree](skills\u002Fopportunity-solution-tree\u002FSKILL.md)** | Generates opportunities and solutions, recommends best proof-of-concept to test |\n| **[organic-growth-advisor](skills\u002Forganic-growth-advisor\u002FSKILL.md)** | Identify 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 |\n| **[pm-skill-creator](skills\u002Fpm-skill-creator\u002FSKILL.md)** | Design 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 |\n| **[pol-probe-advisor](skills\u002Fpol-probe-advisor\u002FSKILL.md)** | Recommends which of 5 prototype types to use based on your hypothesis and risk (Feasibility, Task-Focused, Narrative, Synthetic Data, Vibe-Coded) |\n| **[positioning-workshop](skills\u002Fpositioning-workshop\u002FSKILL.md)** | Guides you through defining your positioning with adaptive questions |\n| **[prioritization-advisor](skills\u002Fprioritization-advisor\u002FSKILL.md)** | Recommends the right prioritization framework (RICE, ICE, Kano, etc.) for your situation |\n| **[problem-framing-canvas](skills\u002Fproblem-framing-canvas\u002FSKILL.md)** | Leads you through MITRE Problem Framing (Look Inward\u002FOutward\u002FReframe) |\n| **[tam-sam-som-calculator](skills\u002Ftam-sam-som-calculator\u002FSKILL.md)** | Projects market size (TAM\u002FSAM\u002FSOM) with real-world data and citations |\n| **[user-story-mapping-workshop](skills\u002Fuser-story-mapping-workshop\u002FSKILL.md)** | Walks you through creating story maps with backbone and release slices |\n| **[vp-cpo-readiness-advisor](skills\u002Fvp-cpo-readiness-advisor\u002FSKILL.md)** | Coaches Directors and executives through the VP\u002FCPO transition — includes CEO interview framework for evaluating roles before accepting. Based on [The Product Porch E43](https:\u002F\u002Fthe-product-porch-43ca35c0.simplecast.com\u002Fepisodes\u002Fbecoming-a-vp-cpo-leading-product-at-the-executive-level-part-2) |\n| **[workshop-facilitation](skills\u002Fworkshop-facilitation\u002FSKILL.md)** | Adds one-step-at-a-time facilitation with numbered recommendations for workshop skills |\n\n---\n\n### 🎭 Workflow Skills (6)\n\n| Skill | What It Does | Timeline |\n|-------|--------------|----------|\n| **[discovery-process](skills\u002Fdiscovery-process\u002FSKILL.md)** | Complete discovery cycle: frame problem → research → synthesize → validate solutions | 3-4 weeks |\n| **[executive-onboarding-playbook](skills\u002Fexecutive-onboarding-playbook\u002FSKILL.md)** | 30-60-90 day diagnostic playbook for VP\u002FCPO transitions: diagnose before acting, surface unwritten strategy, assess people, act with evidence. Based on [The Product Porch E43](https:\u002F\u002Fthe-product-porch-43ca35c0.simplecast.com\u002Fepisodes\u002Fbecoming-a-vp-cpo-leading-product-at-the-executive-level-part-2) | 90 days |\n| **[prd-development](skills\u002Fprd-development\u002FSKILL.md)** | Structured PRD: problem statement → personas → solution → metrics → user stories | 2-4 days |\n| **[product-strategy-session](skills\u002Fproduct-strategy-session\u002FSKILL.md)** | Full strategy: positioning → problem framing → solution exploration → roadmap | 2-4 weeks |\n| **[roadmap-planning](skills\u002Froadmap-planning\u002FSKILL.md)** | Strategic roadmap: gather inputs → define epics → prioritize → sequence → communicate | 1-2 weeks |\n| **[skill-authoring-workflow](skills\u002Fskill-authoring-workflow\u002FSKILL.md)** | Meta workflow: choose add\u002Fbuild path → validate conformance → update docs → package\u002Fpublish | 30-90 minutes |\n\n\u003Ca id=\"future-skills\">\u003C\u002Fa>\n### 🔮 Agent Skills of the Future\n\n**_Possible skills in development:_**\n\n- **Dangerous Animals of Product Management** - Feature hostage negotiations and stakeholder shuttle diplomacy for when you're facing HiPPOs, RHiNOs, and WoLFs (_oh my!_).\n- **Pricing for Product Managers** - Value-based pricing, packaging strategy, price increases, and grandfather clause negotiations without the panic spiral and flop sweat.\n- **Classic Business Strategy Frameworks** - Ansoff, BCG, Porter's 5 Forces, Blue Ocean, and SWOT in agent-ready format that helps you decide, not decorate slides.\n- **Storytelling for Product Managers** - Narrative arc, demo choreography, and pitch structure built on pro-opera lessons and Hakawati orations for commanding the room.\n- **Prompt Building for Product Managers** - Industrial-strength prompt engineering: team session starters, multi-turn workflow wizards, and reverse engineering templates for artifacts like PRDs.\n- **Nightmares of Product Management** - Telemetry, triage, and tactics for when things don't go as planned: adoption theater, feature graveyards, metric manipulation, launch amnesia, technical debt wildfires. Plus prevention strategies.\n\nDetailed concept notes live in [`PLANS.md`](PLANS.md#future-skill-candidates).\n\n---\n\n## 🚀 How to Use\n\n**Confused by setup options?** Start here: [PM Skills Rule-of-Thumb Guide](docs\u002FPM%20Skills%20Rule-of-Thumb%20Guide.md).\n\n### Fastest Path (Local Repo)\n\n```bash\n# Skill mode\n.\u002Fscripts\u002Frun-pm.sh skill user-story \"Checkout improvements for returning customers\"\n\n# Command mode\n.\u002Fscripts\u002Frun-pm.sh command plan-roadmap \"Q3-Q4 roadmap for enterprise reporting\"\n```\n\nCommand definitions live in [`commands\u002F`](commands\u002FREADME.md), and generated browse indexes live in [`catalog\u002F`](catalog\u002FREADME.md).\n\n### With Claude Desktop or Claude.ai\n\n1. Open a conversation with Claude\n2. Share the skill file: \"Read user-story.md\"\n3. Ask Claude to apply it: \"Using the User Story skill, write stories for our checkout flow\"\n\n### With Claude Code (CLI)\n\n```bash\ncd product-manager-skills\nclaude \"Using the PRD Development workflow, create a PRD for our mobile feature\"\n```\n\nYou can discover via `npx skills find \u003Cquery>` and `npx skills add deanpeters\u002FProduct-Manager-Skills --list`, then install for Claude Code. See [Using PM Skills with Claude](docs\u002FUsing%20PM%20Skills%20with%20Claude.md).\n\n### With OpenAI Codex\n\nUse local workspace paths, GitHub-connected Codex on ChatGPT, or discover\u002Finstall directly with `npx skills`. See [Using PM Skills with Codex](docs\u002FUsing%20PM%20Skills%20with%20Codex.md).\n\n### With ChatGPT\n\nUse GitHub app connections (formerly connectors), Custom GPT Knowledge uploads, or Project files. See [Using PM Skills with ChatGPT](docs\u002FUsing%20PM%20Skills%20with%20ChatGPT.md).\n\n### With Cowork or Other Agents\n\n**Cowork:** Import skills as knowledge modules, invoke via natural language.\n**Other agents:** Follow your agent's docs for loading custom knowledge.\n\n---\n\n## 📄 Docs\n\n- **[Using PM Skills 101](docs\u002FUsing%20PM%20Skills%20101.md)** — Beginner-friendly orientation for PMs who want clear setup without technical overload.\n- **[Using PM Skills with Claude](docs\u002FUsing%20PM%20Skills%20with%20Claude.md)** — Claude Code usage plus GitHub ZIP upload steps for Claude Desktop\u002FWeb.\n- **[Using PM Skills with Codex](docs\u002FUsing%20PM%20Skills%20with%20Codex.md)** — Local workspace usage plus GitHub-connected Codex on ChatGPT.\n- **[Using PM Skills with ChatGPT](docs\u002FUsing%20PM%20Skills%20with%20ChatGPT.md)** — GitHub app connection, Custom GPT Knowledge setup, and Project-based usage.\n- **[Platform Guides for PMs](docs\u002FPlatform%20Guides%20for%20PMs.md)** — Tool-by-tool setup chooser for Claude Code, Codex, OpenClaw, Cowork, Claude Desktop, ChatGPT Desktop, n8n, LangFlow, and Python agents.\n- **[Using PM Skills with Claude Code](docs\u002FUsing%20PM%20Skills%20with%20Claude%20Code.md)** — PM-focused quickstart for Claude Code users.\n- **[Using PM Skills with Slash Commands 101](docs\u002FUsing%20PM%20Skills%20with%20Slash%20Commands%20101.md)** — Turn PM skills into reusable Claude slash commands like `\u002Fpm-story` and `\u002Fpm-prd`.\n- **[Using PM Skills with Claude Desktop](docs\u002FUsing%20PM%20Skills%20with%20Claude%20Desktop.md)** — Skill upload workflow for non-technical desktop users.\n- **[Using PM Skills with ChatGPT Desktop](docs\u002FUsing%20PM%20Skills%20with%20ChatGPT%20Desktop.md)** — Project-first setup for desktop-based PM work.\n- **[Using PM Skills with n8n](docs\u002FUsing%20PM%20Skills%20with%20n8n.md)** — Practical automation patterns for repeatable PM workflows.\n- **[Using PM Skills with LangFlow](docs\u002FUsing%20PM%20Skills%20with%20LangFlow.md)** — Visual workflow setup using skill-guided prompt templates.\n- **Additional harness guides:** [Cursor](docs\u002FUsing%20PM%20Skills%20with%20Cursor.md), [Windsurf](docs\u002FUsing%20PM%20Skills%20with%20Windsurf.md), [Bolt](docs\u002FUsing%20PM%20Skills%20with%20Bolt.md), [Replit Agent](docs\u002FUsing%20PM%20Skills%20with%20Replit%20Agent.md), [Make.com](docs\u002FUsing%20PM%20Skills%20with%20Make.com.md), [Devin](docs\u002FUsing%20PM%20Skills%20with%20Devin.md), [CrewAI](docs\u002FUsing%20PM%20Skills%20with%20CrewAI.md), [Gemini](docs\u002FUsing%20PM%20Skills%20with%20Gemini.md)\n- **[Start Here](START_HERE.md)** — One-page \"do this now\" onboarding for skills and commands.\n- **[Commands](commands\u002FREADME.md)** — Command format, command list, validation, and discovery.\n- **[Catalog Artifacts](catalog\u002FREADME.md)** — Generated skill\u002Fcommand indexes for fast navigation.\n- **[PM Skills Rule-of-Thumb Guide](docs\u002FPM%20Skills%20Rule-of-Thumb%20Guide.md)** — Non-technical setup choices (local repo vs ZIP vs app connections) in plain English.\n- **[Marketplace Strategy](MARKETPLACE_STRATEGY.md)** — PM-friendly strategy for distributing skills in marketplaces.\n- **[Marketplace Submission Runbook](docs\u002FMarketplace%20Submission%20Runbook.md)** — Step-by-step submission workflow for non-technical teams.\n- **[Marketplace Issue Templates](docs\u002FMarketplace%20Issue%20Templates.md)** — Reusable issue templates for marketplace execution and tracking.\n- **[PM Tooling Operations Charter](docs\u002FPM%20Tooling%20Operations%20Charter.md)** — Pedagogic operating stack across M365 Copilot, Codex, ChatGPT, VS Code\u002FCopilot, Cursor, n8n, and Lovable.\n- **[Add-a-Skill Utility Guide](docs\u002FAdd-a-Skill%20Utility%20Guide.md)** — End-to-end automation guide for generating and validating new skills.\n- **[Building PM Skills](docs\u002FBuilding%20PM%20Skills.md)** — How we distill sources into agent-ready PM skills.\n\n---\n\n## 💼 Real-World Use Cases\n\n### \"I need to align stakeholders on product strategy\"\n→ **Workflow:** [`product-strategy-session`](skills\u002Fproduct-strategy-session\u002FSKILL.md) (2-4 weeks, orchestrates positioning → roadmap)\n\n### \"I need to validate a customer problem before building\"\n→ **Workflow:** [`discovery-process`](skills\u002Fdiscovery-process\u002FSKILL.md) (3-4 weeks, interviews → synthesis → validation)\n\n### \"I need to test a hypothesis quickly before investing in development\"\n→ **Interactive:** [`pol-probe-advisor`](skills\u002Fpol-probe-advisor\u002FSKILL.md) (recommends which prototype type: Feasibility, Task-Focused, Narrative, Synthetic Data, or Vibe-Coded)\n→ **Component:** [`pol-probe`](skills\u002Fpol-probe\u002FSKILL.md) (template for documenting validation experiments)\n\n### \"I want to know if I'm using AI strategically or just for efficiency\"\n→ **Interactive:** [`ai-shaped-readiness-advisor`](skills\u002Fai-shaped-readiness-advisor\u002FSKILL.md) (assesses 5 competencies: Context Design, Agent Orchestration, Outcome Acceleration, Team-AI Facilitation, Strategic Differentiation)\n\n### \"I'm pasting entire docs into AI and getting vague responses\"\n→ **Interactive:** [`context-engineering-advisor`](skills\u002Fcontext-engineering-advisor\u002FSKILL.md) (diagnose context stuffing vs. engineering, define boundaries, implement Research→Plan→Reset→Implement cycle)\n\n### \"I need to write a PRD for a new feature\"\n→ **Workflow:** [`prd-development`](skills\u002Fprd-development\u002FSKILL.md) (2-4 days, problem → solution → stories)\n\n### \"I need to create a Q2 roadmap\"\n→ **Workflow:** [`roadmap-planning`](skills\u002Froadmap-planning\u002FSKILL.md) (1-2 weeks, epics → prioritization → sequencing)\n\n### \"I need to choose a prioritization framework\"\n→ **Interactive:** [`prioritization-advisor`](skills\u002Fprioritization-advisor\u002FSKILL.md) (asks questions, recommends RICE\u002FICE\u002FKano)\n\n### \"I need to split a large epic\"\n→ **Interactive:** [`epic-breakdown-advisor`](skills\u002Fepic-breakdown-advisor\u002FSKILL.md) (Richard Lawrence's 9 patterns)\n\n### \"I need to write a user story\"\n→ **Component:** [`user-story`](skills\u002Fuser-story\u002FSKILL.md) (template + examples)\n\n---\n\n## 💡 Why Skills Beat Prompts\n\n| Prompts | Skills |\n|---------|--------|\n| One-time instructions per task | Reusable frameworks learned once |\n| \"Write a PRD for X\" | Agent knows PRD structure, asks smart questions, handles edge cases |\n| You repeat yourself constantly | Agent remembers best practices |\n| Inconsistent outputs | Consistent, professional results |\n\n**Skills = Less explaining, more strategic work.**\n\n---\n\n## 🌟 What Makes These Skills Different\n\n### ✅ Battle-Tested Frameworks\nBuilt on proven methods from Geoffrey Moore, Jeff Patton, Teresa Torres, Amazon, Richard Lawrence, MITRE, and more.\n\n### ✅ Real Client Work\nBased on decades of PM consulting across healthcare, finance, manufacturing, and tech.\n\n### ✅ Agent-Ready Format\nOptimized for AI comprehension—not blog posts, not books, not courses. **Executable frameworks.**\n\n### ✅ Zero Fluff\nEvery word earns its keep. No filler, no buzzwords, no generic advice.\n\n### ✅ Example-Rich\nShows both \"good\" and \"bad\" examples so you know what works and what to avoid.\n\n---\n\n## 📚 Skill Structure (What's Inside Each File)\n\nEvery skill follows the same format:\n\n```\n## Purpose\nWhat this skill does and when to use it.\n\n## Key Concepts\nCore frameworks, definitions, anti-patterns.\n\n## Application\nStep-by-step instructions (with examples).\n\n## Examples\nReal-world cases (good and bad).\n\n## Common Pitfalls\nWhat to avoid and why.\n\n## References\nRelated skills and external frameworks.\n```\n\n**Clean. Practical. Zero fluff.**\n\n---\n\n## 🤝 Contributing\n\nFound a gap? Have a PM framework you'd like to see included?\n\n**Ways to contribute:**\n- Open an issue with your suggestion\n- Submit a pull request (we'll help you format it)\n- Share feedback on what's working or missing\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for detailed guidelines.\n\n---\n\n## 🎓 Philosophy\n\n**Principles:**\n- **Outcome-driven** over output-driven (solve problems, don't just ship features)\n- **Evidence over vibes** (validate with data, not opinions)\n- **Clarity beats completeness** (simple and usable beats comprehensive and confusing)\n- **Examples beat explanations** (show, don't just tell)\n\n**No hype. No buzzwords. Just frameworks that work.**\n\n---\n\n## 📖 Related Resources\n\n- **[Product Manager Prompts](https:\u002F\u002Fgithub.com\u002Fdeanpeters\u002Fproduct-manager-prompts)** — Task-specific prompts for ChatGPT, Claude, Gemini\n- **[Productside](https:\u002F\u002Fproductside.com)** — AI-powered product management training and consulting\n- **[Dean's LinkedIn](https:\u002F\u002Flinkedin.com\u002Fin\u002Fdeanpeters)** — Essays on AI-amplified product work\n\n---\n\n## 📜 License\n\nCC BY-NC-SA 4.0 — non-commercial use with share-alike.\n\nSee [LICENSE](LICENSE) for full details.\n\n---\n\n## 📞 Questions?\n\n- **GitHub Issues:** [Report bugs or suggest features](https:\u002F\u002Fgithub.com\u002Fdeanpeters\u002FProduct-Manager-Skills\u002Fissues)\n- **LinkedIn:** [Connect with Dean Peters](https:\u002F\u002Flinkedin.com\u002Fin\u002Fdeanpeters)\n- **Productside:** [Learn more about AI PM consulting](https:\u002F\u002Fproductside.com)\n\n---\n\n**v0.79 — May 15, 2026**\n\nHighlights in this release:\n- Added `pm-skill-creator` interactive skill for guided skill design\n- Added configurable input length guard to `run-pm.sh` (env var `PM_MAX_INPUT`, default 4000)\n- Added adapter name validation and path traversal protection to `add-a-skill.sh`\n- Fixed missing `.claude-plugin\u002Fplugin.json` that blocked Claude Code skill discovery\n\n**v0.78 — April 26, 2026**\n\nHighlights in this release:\n- Added one-command release packaging with `.\u002Fscripts\u002Fbuild-release.sh`\n- Added Claude Desktop\u002FWeb ZIP packs for starter, discovery, strategy, delivery, AI PM, and all-skills use cases\n- Added a Codex ZIP that installs `.agents\u002Fskills` plus `AGENTS.md`\n- Added GitHub Actions to validate, build, upload artifacts, and publish release assets on `v*` tags\n- Added install docs for Claude Desktop\u002FWeb, Claude Code, Codex, and release maintainers\n- Updated the README with a clearer Start Here path for people who just want to use the skills\n\n**v0.7 — March 9, 2026**\n\nHighlights in this release:\n- Tightened skill descriptions so they communicate both what the skill does and when to use it\n- Added `intent` as a repo-standard frontmatter field to separate trigger metadata from deeper purpose\n- Added `scripts\u002Fcheck-skill-triggers.py` and wired trigger-readiness auditing into `test-library.sh`\n- Added `find-a-skill.sh --mode trigger` so users can discover skills through `description`, `best_for`, and `scenarios`\n- Added a Streamlit (beta) `Find My Skill` mode with plain-English discovery, recommended-first results, and direct preview\u002Frun actions\n- Updated authoring docs and templates so the stronger metadata standard sticks\n\n**v0.65 — March 8, 2026**\n\nHighlights in this release:\n- Added comprehensive PM-first onboarding and setup guide: `docs\u002FUsing PM Skills 101.md`\n- Added platform chooser: `docs\u002FPlatform Guides for PMs.md`\n- Added slash-command playbook: `docs\u002FUsing PM Skills with Slash Commands 101.md`\n- Added and linked practical platform docs for Claude Code\u002FDesktop\u002FCowork, ChatGPT Desktop, OpenClaw, n8n, LangFlow, and Python agents\n- Updated `START_HERE.md` and docs navigation so new users can pick the right setup path faster\n\n**v0.6 — March 6, 2026**\n\nHighlights in this release:\n- Added `commands\u002F` with reusable workflow wrappers over local skills (`discover`, `strategy`, `write-prd`, `plan-roadmap`, `prioritize`, `leadership-transition`)\n- Added `START_HERE.md` for 60-second onboarding\n- Added generated `catalog\u002F` artifacts for fast skill and command navigation\n- Added tooling for discovery\u002Fvalidation\u002Fexecution: `find-a-command.sh`, `run-pm.sh`, `check-command-metadata.py`, `test-library.sh`, `generate-catalog.py`\n\n**v0.5 — February 27, 2026**\n\nHighlights in this release:\n- Added 4 Career & Leadership skills distilled from The Product Porch episodes on PM→Director and Director→VP\u002FCPO transitions\n- Launched Streamlit (beta) local playground in `app\u002F` with multi-provider\u002Fmodel selection\n- Improved workflow UX in beta app: phase detection, explicit run controls, and per-phase output tracking\n\n**v0.4 — February 10, 2026**\n\nHighlights in this release:\n- Fixed a facilitation protocol regression where brevity-focused rewrites could remove expected guided-question behavior\n- Promoted `workshop-facilitation` to canonical source of truth for interactive facilitation\n- Added consistent opening heads-up, context-dump bypass path, and best-guess mode\n- Applied protocol linkage across interactive skills and facilitation-heavy workflow skills\n\n**v0.3 — February 9, 2026**\n\nHighlights in this release:\n- 42 total skills, including Phase 7 finance skills and the new `skill-authoring-workflow`\n- New skill tooling: `add-a-skill`, `build-a-skill`, `find-a-skill`, `test-a-skill`, `zip-a-skill`\n- New onboarding docs for Claude, Codex, ChatGPT, and non-technical \"rule-of-thumb\" setup\n\nBuilt by Dean Peters (Principal Consultant and Trainer at Productside.com) with Anthropic Claude and OpenAI Codex.\n\n*Helping product managers work smarter with AI.*\n","该项目旨在提供一套经过实践验证的产品管理技能框架，以帮助产品管理者及其AI助手提升专业水平。核心功能包括49种实战技能和6种命令工作流，支持Claude Code、Codex等多种AI代理工具。技术特点上，它利用了Teresa Torres、Geoffrey Moore等业界知名人士提出的框架，以及来自亚马逊、MITRE的最佳实践，能够有效指导用户如何定义问题、探索机会、搭建验证实验并快速淘汰不良决策。适合于希望提高自身产品管理能力的非技术背景PM，以及希望通过终端操作增强工作效率的技术型产品经理使用。","2026-06-11 03:51:12","high_star"]