ProductMind Skills
ProductMind Skills gives an agent 17 skills where the product decision comes before code: feature vetting, MVP or SLC, pricing.
- 82 ★ on the repository
- Last commit
Minimal access
Why this level
- The skills give instructions and write board and decision files into the project.
- Some skills keep files with decisions and cards, so check what the agent writes into the repository.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/productmind-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skills give instructions and write board and decision files into the project.
- Some skills keep files with decisions and cards, so check what the agent writes into the repository.
This is third-party code. Review the repository files before installing.
What it does
ProductMind Skills is a collection of 17 skills for founders, product managers and engineers. Fourteen of them apply frameworks from the book "Building Rocketships" by Oji and Ezinne Udezue: a problem sharpness test, MVP versus SLC, reverse freemium, tiered pricing math, the aha moment, roadmap ordering. Reading the book is not required, as each skill defines its terms and thresholds. Three others work with a project: `new-project-scaffolding` starts from a viability check and a product brief, `auto-kanban` keeps a card board for agent workflows, `vibememo` stores the reasons behind architecture and product decisions. Among the book skills, `vet-a-feature` decides whether a feature is worth building and what its smallest version is.
Who it is for. Founders and product managers who work with an agent and want it to judge what to build before writing code.
Good fit when
- A new project starts with a viability check and a product brief rather than folders.
- A proposed feature has to be checked for value and cut to its smallest version.
- Prices for several tiers are derived from cost and market anchors.
- A roadmap is ordered by problem sharpness instead of effort.
Not a fit when
- Only code skills are wanted: the collection blends product and engineering.
- A strict fidelity check of the book frameworks is needed: the authors run such evals outside this repository.
- There is no customer data: the skills refuse to invent customer facts.
Example request
Vet the proposed "share reports by link" feature: is it worth building and what is the smallest version.Limitations
The license is split: skill texts and documentation are CC BY-SA 4.0, tooling in `scripts/` and tests are MIT. Redistributing the texts requires keeping the author attribution and link at the end of each skill and releasing derivative works on the same terms. Book links lead to a shop, and the depth of the frameworks in the skills is limited to their own texts. The automated check in the repository verifies skill structure and links, not fidelity to the book. The last commit was made on 14 October 2026.
How to disable. Delete the skill folders from the project `.claude/skills/` or the user skills directory. Saved boards and decision records live in the project and are removed separately.
FAQ
How do I install one skill?
With `claude install-skill` and a link to the skill folder, for example `.../tree/main/skills/new-project-scaffolding`. Or clone the repository and copy the folder into the project `.claude/skills/`.
Do I need to read "Building Rocketships"?
No. Each skill defines its terms and thresholds as it runs, and the book is for going deeper.
Which skills work with the project rather than the book frameworks?
`new-project-scaffolding`, `auto-kanban` and `vibememo`. The first creates a project with a viability check, the second keeps a card board, the third stores the reasons behind decisions.
Which agents run the skills?
The skills follow the SKILL.md standard and are portable across Claude Code, Codex CLI, Cursor and Gemini CLI.
What does the sharpness test return?
`sharp-problem-test` returns SHARP, NOT_SHARP or NEEDS_MORE_EVIDENCE with evidence per axis and a check of the threefold improvement bar.
Discussion
No questions or reviews yet.
Related
SkillsA large library of product frameworks as skills: discovery, strategy, PRDs, prioritization and unit economics
A Claude Code skill collects product context in Markdown and links decisions to interviews, documents and hypotheses
A product management skill library for agents: product phases, sprints, templates and sample outputs
A collection of skills for decisions and projects: strategy, market research, thinking, data analysis, docs and slides.
A CLAUDE.md and AGENTS.md file with seven principles: the agent frames the problem and scope before it writes code
Lenny's Product Skills
Lenny's Product Skills for Claude Code
A set of product skills for Claude Code and SKILL.md agents: strategy, discovery, launch, growth and team work
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| ProductMind Skills (this card) | no | 82 | |
| PM Skills | no | 27,935 | a product manager plugin marketplace across the whole cycle; ProductMind Skills blends product decisions with engineering steps and uses frameworks of one book |
| Product Manager Skills | no | 8,006 | a large library of product frameworks as skills; ProductMind Skills adds project scaffolding, a card board and a decision log |
README in short
The README splits the skills into book frameworks and project tools, gives a table with the lifecycle stage and a description of each, lists quality standards and explains the split license.