pm-skills
Skill27 starsChanged 8 months agoApache-2.0View on GitHub
Product management workflows covering the full work lifecycle — discovery, strategy, execution, launch, and growth. Write PRDs, plan OKRs, and structure meeting notes. Useful beyond PMs — applicable to any knowledge worker managing projects, stakeholders, or strategy. Triggers: /write-prd, /plan-okrs, /meeting-notes
16 other projects use a version of this.
Adopted by
Most recently taken up by
- podo/design-agent-skillstheir own version, first seen Nov 8, 2026
- DinakarDbx/claude-skillstheir own version, first seen Oct 15, 2026
- hmzainjamil/claude-skillstheir own version, first seen Oct 9, 2026
- Hassaan146/claude-skillstheir own version, first seen Jul 25, 2026
- mahiunfiltered/claude-code-skillstheir own version, first seen Jul 8, 2026
- Hussain-Elfalah/Agentic-Skillstheir own version, first seen Jun 4, 2026
Other versions16 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 16
- ricneves-ai/flowgrammers-skills★ 115same name
- podo/design-agent-skills★ 32same name
- ArogyaReddy/alirezarezvani-claude-skills★ 31same name
- Hassaan146/claude-skills★ 18same name
- zhangzhang-111-i/claude-skills111★ 3same name
- afaizalam2003/Master-claude-skill★ 2same name
- Hussain-Elfalah/Agentic-Skills★ 2same name
- emiiblesstm-star/claude-skills★ 1same name
- mahiunfiltered/claude-code-skills★ 1same name
- benmoumene/claude-skills★ 0same name
6 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository40 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- webapp-testingSkill
- env-hubSkill
- mcp-builderSkill
- mintlify-docs-updaterSkill
- reviewSkill
- shipSkill
- skill-creatorSkill
- specSkill
- internal-commsSkill
- ml-failure-auditSkill
- changelog-generatorSkill
- algorithmic-artSkill
- canvas-designSkill
- instagram-reel-editorSkill
- remotionSkill
- slack-gif-creatorSkill
- ab-test-setupSkill
- copywritingSkill
- humanizerSkill
- instagram-postingSkill
- marketing-ideasSkill
- seo-auditSkill
- claude-for-legalSkill
- contract-review-risk-scoringSkill
- doc-coauthoringSkill
- docxSkill
- legal-work-pluginSkill
- pdfSkill
- pptxSkill
- xlsxSkill
- resume-tailoringSkill
- last30daysSkill
- brand-guidelinesSkill
- excalidrawSkill
- frontend-designSkill
- open-designSkill
- theme-factorySkill
- web-artifacts-builderSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 14 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 27
Write the problem statement — one paragraph, no solution language yet.
- Distinctive: line 30
Write acceptance criteria for each user story — specific, testable, binary pass/fail.
- Distinctive: line 52
If reviewing existing OKRs: flag key results that are vague, unmeasurable, or don't ladder to the objective.
- Distinctive: line 75
Write a 3–5 sentence summary suitable for sharing with stakeholders who weren't in the meeting.
“Common” is measured: kept by at least 6 in 10 of the 14 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Overview
65 skills and 36 chained workflows covering the full PM work lifecycle. The three core skills below cover the most common PM artifacts: requirements, goal-setting, and meeting capture. Each produces a structured, shareable output ready to hand off to stakeholders or a team.
Source Repository
- GitHub: phuryn/pm-skills
- Install upstream:
npx skills add phuryn/pm-skills
/write-prd
Drafts a full product requirements document from a brief description. Includes problem statement, user stories, assumptions, edge cases, acceptance criteria, and open questions.
Workflow
- Gather: feature name, the problem it solves, primary users, and any known constraints.
- Write the problem statement — one paragraph, no solution language yet.
- Draft user stories: "As a [role], I want [action] so that [outcome]." Cover the primary flow and at least 2 edge cases.
- List assumptions (what must be true for this to work) and open questions (what needs a decision).
- Write acceptance criteria for each user story — specific, testable, binary pass/fail.
- Return the full PRD in a structured format ready to paste into Notion, Confluence, or a doc.
Example prompts
| Use case | Task prompt |
| New feature | Write a PRD for a notification preferences center. Users need granular control over email, push, and in-app alerts by category. Include edge cases for users on multiple devices. |
| Internal tool | Write a PRD for an internal expense reporting tool. Finance team needs to approve, reject, and request more info. Current process is email-based and takes 2 weeks. |
| API product | Write a PRD for a public API rate limiting dashboard. Developers need to monitor usage, set alerts, and upgrade their plan without contacting sales. |
/plan-okrs
Generates a full OKR set from a goal or initiative — key results with measurable targets, leading indicators, and a tracking cadence. Also reviews existing OKRs for clarity and measurability.
Workflow
- Understand the objective: what outcome are we driving toward and over what timeframe?
- Draft 3–5 key results — each must be quantitative, have a baseline and a target, and be achievable in the timeframe.
- For each key result, identify a leading indicator (an early signal that you're on track) and a tracking cadence (weekly/bi-weekly check-in metric).
- If reviewing existing OKRs: flag key results that are vague, unmeasurable, or don't ladder to the objective. Rewrite the weakest ones.
- Return the full OKR set in a format ready for planning docs or OKR tools.
Example prompts
| Use case | Task prompt |
| Quarterly planning | Write OKRs for our growth team next quarter. Goal: improve activation rate for new signups. We currently have a 22% 7-day activation rate and want to reach 35%. |
| OKR review | Review these OKRs and tell me which key results are too vague, which are unmeasurable, and rewrite the weakest three. |
| Team alignment | We have 4 team OKRs but they don't ladder up to the company goal of expanding into enterprise. Rewrite them so the connection is clear. |
/meeting-notes
Turns a raw meeting transcript or bullet-point notes into structured output: decisions made, action items with owners, open questions, and a short summary for stakeholders who weren't there.
Workflow
- Receive the transcript or raw notes (paste or attach).
- Extract decisions — concrete choices that were made and won't be revisited.
- Extract action items — each with a clear owner and, if mentioned, a due date.
- Extract open questions — things raised but not resolved, that need a follow-up.
- Write a 3–5 sentence summary suitable for sharing with stakeholders who weren't in the meeting.
- Return the structured output in this order: Summary → Decisions → Action Items → Open Questions.
Example prompts
| Use case | Task prompt |
| Transcript | Here's the transcript from our roadmap planning meeting. Extract all decisions, action items with owners, and anything that needs a follow-up before next week. |
| Rough notes | I jotted down these notes during the design review. Turn them into a clean meeting summary I can share with the team and stakeholders. |
| Standup digest | Here are this week's daily standup notes. Summarize what each person worked on, what's blocked, and what shipped. Flag anything that needs my attention. |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

