Product Manager Skills
Senior-PM persona with SaaS metric formulas, PRD critique and 12 artifact templates
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 17, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · dd25c37
Task: diagnose unit economics with a solution embedded in the problem statement — «MRR $80k, churn 8%/month, CAC $1200, ARPU $90, GM 75%, want to build a dashboard to fix churn». The baseline run without the skill gave the correct direction (a dashboard does not fix churn, go to churned customers), but linear arithmetic: 8%×12 ≈ 96% annual churn. The skill caught exactly this trap — knowledge/finance-metrics.md explicitly stated «3% monthly != 36% annual»; by the formula 1-(1-0.08)^12, it came out to 63.2%, a difference of 33 points. Further, the module's formula table gave a harsh verdict instead of feelings: LTV(better) = ARPU×GM%/churn = $843.75, LTV:CAC = 0.70:1, which by its own benchmark was «<1:1 unsustainable», payback = 17.8 months. Plus, the framing gate marked solution smuggling. The repository's stated numbers matched upon recalculation: 7 knowledge modules, 12 templates, 54 routing lines against the promised «40+ frameworks». The skill was purely prompt-based — there was no executable code; the gain was measured by arithmetic and thresholds, not by machine verification.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 5/5
What Product Manager Skills does
Routes PM requests to one of seven knowledge modules — discovery, strategy, artifacts, finance metrics, career, growth/PLG, AI product craft — each carrying real formulas, benchmarks and quality gates. Triggers on diagnosing SaaS metrics, critiquing a PRD, planning a roadmap, writing user stories or pressure-testing an AI product decision, and answers with labeled assumptions, named tradeoffs and a completion status.
How to install Product Manager Skills
git clone https://github.com/Digidai/product-manager-skills.git
mkdir -p ~/.claude/skills
cp -r product-manager-skills ~/.claude/skills/product-manager-skills
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Product Manager Skills
-
/product-manager-skillsSenior-PM persona with SaaS metric formulas, PRD critique and 12 artifact templates
It also activates on plain-language prompts like these:
-
Diagnose our SaaS health: $80k MRR, 8% monthly churn, $1200 CAC, $90 ARPU -
Critique this PRD before I send it to engineering for estimation -
Calculate our LTV to CAC ratio and tell me if it's sustainable
Frequently asked questions
- Is the Product Manager Skills skill free?
- Yes. The skill itself is free from Digidai/product-manager-skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Product Manager Skills work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Tested · Works. Task: diagnose unit economics with a solution embedded in the problem statement — «MRR $80k, churn 8%/month, CAC $1200, ARPU $90, GM 75%, want to build a dashboard to fix churn». The baseline run without the skill gave the correct direction (a dashboard does not fix churn, go to churned customers), but linear arithmetic: 8%×12 ≈ 96% annual churn. The skill caught exactly this trap — knowledge/finance-metrics.md explicitly stated «3% monthly != 36% annual»; by the formula 1-(1-0.08)^12, it came out to 63.2%, a difference of 33 points. Further, the module's formula table gave a harsh verdict instead of feelings: LTV(better) = ARPU×GM%/churn = $843.75, LTV:CAC = 0.70:1, which by its own benchmark was «<1:1 unsustainable», payback = 17.8 months. Plus, the framing gate marked solution smuggling. The repository's stated numbers matched upon recalculation: 7 knowledge modules, 12 templates, 54 routing lines against the promised «40+ frameworks». The skill was purely prompt-based — there was no executable code; the gain was measured by arithmetic and thresholds, not by machine verification.
- What is the Product Manager Skills SkillProof Score?
- 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
- How do I install Product Manager Skills?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Product Manager Skills with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.