PM Skills

A product-management library of 68 skills in nine plugins, with commands that chain several skills into one workflow: product discovery and assumption mapping, strategy, market and user research, requirement documents, job stories, OKRs, roadmaps, prioritization frameworks, sprint planning, retrospectives, pre-mortems, go-to-market and growth, A/B-test and cohort analysis, SQL queries, release notes, and a review of AI-built software before shipping. Aimed at product managers who want an agent to walk through an established product-management framework step by step.

Task planning
Competitive research

Source: phuryn/pm-skills · pinned commit 18468a9

View source on GitHub

LuluSkill lists this project so you can find it. A listing is not a security review or an endorsement, and nothing on this page is installed or run for you.

EDITORIAL GUIDE

Turn product assumptions into decisions you can test

A product-management framework can structure uncertainty. It cannot supply missing customer evidence, validated demand or a reliable forecast.

LuluSkill’s own reading of this project, not a summary of its README. About 3 minutes to read

This guide is LuluSkill’s own judgement about when this project fits, written from the pinned version named above. It is not the author’s documentation, not a security review and not a recommendation. LuluSkill did not install, run or test the project to write it, and the guide is shown only while this listing still points at the commit it was written against.

When this project fits

This collection fits a product question that needs a chosen method: discovery, assumptions, prioritization, specifications or experiments. The README separates skills from workflow commands and plugin groups; select a method for the current decision rather than treating the collection as a complete product strategy.

When to choose something else

Do not ask the assistant to invent interview quotations, customer counts or market evidence to fill a framework. Numerical prioritization can create false precision when its inputs are guesses. Label assumptions before scoring or writing a persuasive product narrative.

What to provide and what to expect

Provide the product context, target user, available evidence and decision deadline. Expect an explicit assumption map, draft specification or experiment proposal. Separate what users actually said from the team’s interpretation and from the next thing that needs testing.

Tools, permissions and boundaries

Many methods can start from supplied text without external tools. Connections to product data or collaboration services require separate authorized access. A method naming an experiment does not authorize contacting participants, changing a live product or spending a test budget.

The tradeoff and an alternative

A one-page decision note may beat a large framework for a small reversible choice. Use the collection when it makes an assumption observable or aligns several people on the same question. Extra documentation has little value if it merely repeats confidence without new evidence.

A small acceptance exercise

Proposed exercise: choose one uncertain product assumption and design a bounded test. Specify what observation would support it, what would reject it and what decision follows either result. Reject a plan that invents expected participants or uses a score without explaining its input evidence.

Source, version and what was actually read

The pinned README opening catalogue and skill/workflow/plugin distinctions were read. Individual frameworks, customer research and product outcomes were not evaluated. LuluSkill did not install or run this project; the exercise above is a proposed reader check, not a reported result.

How to use this listing

LuluSkill publishes the description and the source link only. The skill itself stays in its author’s repository, and nothing here is installed, copied or run for you.

Read what the skill helps with The summary above says which job the project is for. If that is not the job you have, this is probably not the listing you want.
Open the original source and follow the author’s own instructions The link to the original project opens its author’s page. That page, not this one, is where the setup steps and any copying instructions live.
Use it in a compatible AI assistant Skills of this kind are normally used inside an AI assistant that can read a folder of files on your computer. Which assistants support them is the author’s decision, so check their page before you start.

Who it is for

Somebody who already wants this one job done and is willing to follow the author’s setup steps. No programming knowledge is assumed, and this listing cannot tell you whether the project suits you.

Before you start

You need an AI assistant that supports skills, and you will be following somebody else’s instructions on your own computer. Read them before you run anything.

What you end up with

Whatever the author’s project produces. LuluSkill never runs it, so this page cannot promise a result, a file, or a level of quality.

Where it is normally used

Projects like this are usually used in an AI assistant that supports skills, such as an AI coding assistant. The author’s repository says which assistants it is written for; LuluSkill has not tested it with any of them.

Version checked

The source was checked at this commit: 18468a9

Changes made to the repository after this commit have not been checked.

License

MIT, from the licence file in the source repository at the listed commit. Check the repository’s licence before you use or copy the project.

Listing only

LuluSkill lists this project only. It does not host, download or run its code.

What this page does not include

The project’s files and setup steps stay in its own repository. LuluSkill has not security-tested the project or confirmed which AI assistants it works with.

Report a problem or request removal

Rights holders and users can report licence, attribution, security or accuracy problems with this page. We respond within 48 hours and record every request in our review log.

Report or request removal How copyright complaints work

Opens your email app. You can also write to contact@luluskill.com and include this page’s address.

More Productivity projects in the directory

Personal OS Skills
Seven skills that connect an Obsidian vault with personal tools: syncing meeting notes from a local meeting-notes app cache, importing notebooks from a research notebook service, loading podcast episode lists from a video channel, recalling earlier notes and session history, exporting coding-agent session transcripts to Markdown, managing tasks through a local task plugin, and analysing voice-dictation history. Several skills read data that other applications store locally. Aimed at people who keep their notes and tasks in Obsidian and want an agent to work with them.
Obsidian Skills
Five skills that teach an agent the open formats and tools of the Obsidian note-taking app: Obsidian Flavored Markdown with wikilinks, embeds, callouts and properties; Bases files with views, filters and formulas; JSON Canvas files with nodes, edges and groups; the Obsidian command-line interface for reading, creating and searching notes and tasks; and a web-page cleaner that extracts readable Markdown. Aimed at people who keep notes in Obsidian and want an agent to edit their vault files correctly.
Tutor Skills
Two study skills: the first turns a source such as PDF, Markdown, HTML or EPUB files or a code project into a structured, interlinked set of study notes in an Obsidian vault; the second quizzes the learner on those notes in rounds of four questions, grades the answers and records which concepts need more practice. Aimed at students and self-learners who want to study a document or codebase with an agent.
Planning With Files
A planning skill that keeps three Markdown files on disk for a multi-step task: a task plan, a findings log and a progress log. Lifecycle hooks read the plan back into the agent's context on each turn and check completion before the agent stops, so work can resume after the context is cleared or a session ends. The same skill is packaged for many agent hosts and translated into several languages. Aimed at people running long coding or research tasks with an agent who want the plan to survive across sessions.