A general-purpose AI agent is a blank slate. Product on Purpose fills it in: open-source skills, tools, and libraries that turn an everyday agent into a capable partner for product work, one composable piece at a time.

• 🧭 pm-skills - 68 plug-and-play product management skills covering the full product lifecycle.
• 🤔 thinking-framework-skills - Evidence-graded thinking methods an agent can run to reason, not just chat.
• 🤖 agent-skills-toolkit - A standard and toolkit for grading skill libraries to a Bronze/Silver/Gold bar.
• ✍️ writing-style-catalog - Composable writing instructions so AI prose lands in the voice you actually want.
• 🔍 critique-skills - Critique that cites a published rubric on every finding, and publishes how often it is right.
• 📐 product-lifecycle-templates - Governed document templates that ship with the research, the guide, and a worked example.
• 🧩 agent-plugins - The marketplace that puts every Product on Purpose plugin one command away.
• 🧰 pm-skills-mcp - The PM catalog as an MCP server (maintenance mode).

Get started. Most of these install as Claude Code plugins. Add the marketplace once, then grab any plugin below:

/plugin marketplace add product-on-purpose/agent-plugins

🟢 Active · 🚀 Flagship · v2.31.1 · 68 skills · 6 sub-agents · 12 workflows · 200+ samples

/plugin install pm-skills@product-on-purpose

The flagship of the portfolio and the place most people should start. It hands your agent a curated set of best-practice product workflows to run on demand, end to end.

• Stop prompting PM work from scratch. Each skill is a best-practice workflow (PRDs, hypotheses, user stories, sprint facilitation) that you invoke by name instead of re-explaining the method every time.
• Covers the whole lifecycle. From Foundation Sprint and Design Sprint at the fuzzy front end through discovery, delivery, and iteration, with sub-agents and workflow orchestrators that chain skills into full routines.
• Quality you can see. 200+ real-world sample outputs set the bar, and CI-enforced contracts keep every skill conformant as the catalog grows.

🟢 Active · v0.13.0 · 63 frameworks · 4 meta-tools · 9 recipes · evidence-graded · Advanced (Gold)

/plugin install thinking-framework-skills@product-on-purpose

Structured reasoning your agent can actually execute, not just name-drop. Think of it as a toolbox of decision-making moves, each one graded so you know how far to trust it.

• Agents reason better with a method. Canonical thinking tools (premortems, first principles, parallel-perspective review) packaged so an agent runs the actual move, not a vague impression of it.
• Honest about the evidence. Every skill carries a transparent grade, from replicated research down to practitioner heuristic, so you know how far to trust it. No laundered statistics.
• Always ends in an artifact. Each run hands back something usable, a risk register, an option matrix, an argument map, rather than more prose.

🟢 Active · v1.9.0 · Standard v0.12 · 24 skills · 30 checks · Gold-in-CI

/plugin install agent-skills-toolkit@product-on-purpose

The meta-layer for anyone authoring skills at scale. It defines what a great, multi-agent skill library looks like, then gives you the tooling to prove yours measures up.

• For people building skills, not just using them. A toolkit and a normative Standard for authoring skill libraries that work across Claude Code and Codex from a single source.
• A quality bar you can climb. Grades a whole library against a tiered Bronze/Silver/Gold rubric and returns a burndown of exactly what blocks the next tier.
• Deterministic, not vibes. Zero-dependency Node validators with real exit codes, and the repo self-validates at Gold in its own CI as the proof.

🟢 Active · 🧪 Experimental · v0.13.0 · 97 entries · 1,164 examples · 158 diff-pairs · 14 recipes · 4 axes (Voice/Tone/Style/Format)

/plugin install writing-style-catalog@product-on-purpose

Composable control over how an agent sounds on the page. It turns "make it sound professional" into a precise, reusable instruction you can drop onto any writing task.

• Make AI writing stop sounding like AI. Compose precise, reusable instructions from named building blocks instead of retyping "make it sound professional" and hoping.
• Four orthogonal axes. Mix Voice, Tone, Style, and Format independently to dial in exactly the register and shape a piece needs.
• Worked examples, not vibes. Every entry ships with samples that show what it actually produces, so you can see a style before you commit to it.

🟢 Active · 🆕 New · v0.1.1 · 6 skills · 1 sub-agent · 96 criteria · 502 recorded runs · Convergent (Silver)

/plugin install critique-skills@product-on-purpose

Review you can check instead of just trust. Ask a general-purpose model to critique your work and you get fluent, confident, forgettable commentary; these skills answer to a published rubric instead, and report how often they actually catch what is there.

• Every finding cites a source. Each skill operationalizes a published external standard (WCAG 2.2, Nielsen's heuristics, Diataxis, the Toulmin model, the Federal Plain Language Guidelines), so every defect it raises carries a permanent criterion ID you can look up and argue with.
• Findings are records, not prose. Output conforms to a frozen JSON Schema, so a critique can be diffed, filtered, tracked across revisions, or handed to another tool rather than read once and lost.
• It publishes its own scorecard. Measured against a corpus with deliberately planted defects, unflattering numbers first: recall, precision, and run-to-run consistency, with the weak axes named rather than buried.

🟡 Beta · v0.1.0 · 25 bundles · 8 families · lean/full sizes · CI-gated

git clone https://github.com/product-on-purpose/product-lifecycle-templates.git

The document layer underneath the work. Where pm-skills runs the method, this decides what the resulting artifact should actually look like, and defends that shape with research rather than taste.

• A bundle, not a blank file. Every document type ships five pieces together: the blank shape you fill in, a companion explaining why it is shaped that way, a fast operator card, a fully worked example, and machine-readable metadata an agent can route on.
• Sized to your context window. Each type offers lean and full variants with published token budgets, so an agent pulls the version that fits the job instead of blowing context on a template built for a different scale.
• Cited, and gated on staying that way. Shapes are argued from primary sources, and CI enforces the claims: bundle completeness, link health, research logs, manifest freshness, and even the repo's own self-reported counts.

🟢 Active · Marketplace · 5 plugins · Claude Code

/plugin marketplace add product-on-purpose/agent-plugins

The registry that ties the whole ecosystem together. It is how every plugin above becomes a one-line install inside Claude Code.

• One front door to everything. The Claude Code marketplace registry for the whole portfolio: add it once and every Product on Purpose plugin is a single command away.
• Deliberately thin. No plugin code lives here, just the index, so it stays fast to load and easy to trust.

🟤 Maintenance · v2.9.3 · MCP server · 59 tools (40 skills, 11 workflows, 8 utilities)

npm install -g pm-skills-mcp

The same product management catalog, delivered over the Model Context Protocol for agents that prefer native tools to files.

• The PM catalog over Model Context Protocol. Exposes 59 tools to any MCP-aware agent with no file setup.
• Stable, but paused. Fully functional at v2.9.3; active development is on hold, so new users are better served by the file-based install from pm-skills.