digidai-pm — Claude Code skill: SaaS metrics, PRD, roadmapping
digidai-pm — a skill for Claude Code, Codex, Cursor, and other agents that adds senior PM thinking: SaaS health metrics, PRD critique, discovery, and PLG growth strategy. Targets B2B and consumer digital products.
MIT 204 installs ★ 35 updated 2026-10-21
npx skills add podo/design-agent-skills --skill digidai-pm -a claude-codeWhat digidai-pm does
Once installed, the agent takes on a senior PM perspective: it evaluates SaaS metrics, writes and tears apart PRDs, builds roadmaps, and runs discovery work — interview plans, opportunity-solution trees, and problem statements. There is also a block for PM career coaching and pressure-testing AI product decisions.
Every answer explicitly labels assumptions and calls out tradeoffs rather than presenting one path as obvious. A set of fill-in templates ships alongside the skill.
The license is CC BY-NC-SA 4.0: commercial use and client work are off-limits. The skill's authors point to phuryn-pm-skills (MIT) as the alternative for those cases.
What it helps with
- diagnose a SaaS product against key health metrics
- write or critique a PRD draft
- build a prioritised quarterly roadmap
- run discovery: interview plan and opportunity-solution tree
- design a PLG growth strategy
Example prompts for the agent
- Review this PRD draft and call out weak assumptions and hidden tradeoffs
- Build a Q3 roadmap for a B2B SaaS focused on retention
- Run discovery for the onboarding feature: interview plan and opportunity-solution tree
How to install digidai-pm
1Skills CLI (Vercel)
npx skills add podo/design-agent-skills --skill digidai-pm -a claude-code2Manually: put the files in place
~/.claude/skills/digidai-pm/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/digidai-pm/
1Skills CLI (Vercel)
npx skills add podo/design-agent-skills --skill digidai-pm -a codex2Manually: put the files in place
.agents/skills/digidai-pm/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add podo/design-agent-skills --skill digidai-pm -a cursor2Manually: put the files in place
.cursor/skills/digidai-pm/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install podo/design-agent-skills skills/digidai-pm2Manually: put the files in place
.github/skills/digidai-pm/SKILL.md1Skills CLI (Vercel)
npx skills add podo/design-agent-skills --skill digidai-pm -a gemini-cli2Platform CLI
gemini skills install https://github.com/podo/design-agent-skills --path skills/digidai-pmManually: put the files in place
.devin/skills/digidai-pm/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add podo/design-agent-skills --skill digidai-pm -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about digidai-pm
How do I install digidai-pm in Claude Code?
Run npx skills add podo/design-agent-skills --skill digidai-pm -a claude-code. The skill lands at ~/.claude/skills/digidai-pm/SKILL.md.
What does the digidai-pm skill do?
It gives the agent the knowledge base of a senior product manager: SaaS metrics, PRD writing and critique, roadmapping, discovery, PLG strategy, and PM career coaching. Answers always surface assumptions and name tradeoffs explicitly.
Can digidai-pm be used for commercial or client work?
No. The CC BY-NC-SA 4.0 license prohibits commercial use. The skill's authors name phuryn-pm-skills (MIT-licensed) as the go-to alternative for that context.
Source text
SKILL.md · MIT
--- name: digidai-pm description: | Senior product manager skill with SaaS metrics, PRD critique, roadmapping, discovery, PM career coaching, AI-product decisions, and PLG growth strategy. Ships knowledge domains, templates, and an opinionated style that labels assumptions and names tradeoffs. triggers: - "product manager" - "PM frameworks" - "product roadmap" - "product discovery" - "SaaS metrics" - "product strategy" - "product requirements" das: category: product-pm upstream: "https://github.com/Digidai/product-manager-skills" upstream_path: "SKILL.md" version: latest install: true --- # digidai-pm > Catalogue stub — full skill: [Digidai/product-manager-skills](https://github.com/Digidai/product-manager-skills) <!-- das:install:start — generated from stub.yaml by `npm run generate`; edit stub.yaml, not this block --> ## Decision tree 1. **Is the full skill already installed?** Upstream names this skill `product-manager-skills`, so it installs next to this pointer (the pointer is not replaced). - Global: `f=~/.agents/skills/product-manager-skills/SKILL.md; [ -f "$f" ] && ! grep -q "^das:" "$f" && echo "installed" || echo "pointer"` - Project: `f=.agents/skills/product-manager-skills/SKILL.md; [ -f "$f" ] && ! grep -q "^das:" "$f" && echo "installed" || echo "pointer"` - `installed` → the skill is installed as `product-manager-skills`, invoke it and proceed - `pointer` → go to step 2 2. **Detect scope, then install:** ```bash [ -e ~/.agents/skills/digidai-pm ] && echo "global" || echo "project" ``` **Global:** ```bash npx skills add Digidai/product-manager-skills --skill product-manager-skills -g -y ``` **Project:** ```bash npx skills add Digidai/product-manager-skills --skill product-manager-skills -y ``` > **Claude Code:** send a command as a chat message starting with `!` to run it without leaving the conversation. **Heads-up** - **License:** CC BY-NC-SA 4.0 (non-commercial, share-alike; GitHub reports it as NOASSERTION) <!-- das:install:end --> ## Invoke after install - Skill name: `product-manager-skills` - Trigger phrases: "product manager", "PM frameworks", "product roadmap", "SaaS metrics" ## What it does Brings senior PM thinking to product decisions. Diagnoses SaaS health metrics, critiques and writes PRDs, plans roadmaps, runs discovery (interview plans, opportunity-solution trees, problem statements), coaches PM career transitions, pressure-tests AI product decisions, and designs PLG growth strategies. Ships a set of fill-in templates and examples, and answers in an opinionated style that labels assumptions and names tradeoffs. Oriented toward B2B and consumer digital products. ## When NOT to use - Commercial or client work where a non-commercial licence is a problem (use `phuryn-pm-skills`, which is MIT-licensed) - Design-side research synthesis (use `user-research-cookiy`)
© podo · MIT · podo/design-agent-skills