Skip to content

skilldrop·docs·How-to

Stage 1 · discover

Use the Product manager pack

Install the Product manager pack, run its first task, and follow a typical session step by step.

Direction to requirements: PR/FAQs, strategy frameworks, OKRs, business cases, interviews, PRDs, journey maps, and success measurement.

Reach for it when: You are deciding what to build and need a requirement a human has agreed to before design starts.

1. Install it

npx skilldrop-cli install --pack product-manager                 # Claude Code, your user folder
npx skilldrop-cli install --pack product-manager --project       # Claude Code, this repo
npx skilldrop-cli install --pack product-manager --ide cursor    # or kiro, codex, antigravity, copilot
npx skilldrop-cli install --pack product-manager --local         # this repo, hidden from git

In Claude Code you can also add the marketplace once (/plugin marketplace add sananthanarayan/skilldrop) and run /plugin install product-manager@skilldrop.

It brings core with it, so the shared skills are there too.

2. Run the first task: pressure-test a product idea before anyone builds it

Paste this into your agent:

Write a PR/FAQ for a feature that lets customers pause their subscription for up to three months instead of cancelling.

How to tell it worked: prfaq returns a launch press release, a customer FAQ and an internal FAQ that names the hard questions.

If nothing happens: If prfaq does not activate, ask for it by name ("use prfaq") and check that its folder exists in your skills folder (~/.claude/skills/ by default).

3. A typical session

Bring:

A session takes about 1–2 hours of working time, plus the interviews themselves.

  1. requirements-interview: Describe the feature idea and list the stakeholders. You get: An interview kit per stakeholder with up to seven questions ranked by how much the answer changes the design, at least one disconfirming question each, and an assumptions ledger.
  2. brief-intake: Paste the interview notes once you have run the interviews. You get: One brief with every field tagged explicit, implied, inferred or missing, quoting the source. You decide: Resolve the missing fields yourself; the PRD must not invent them.
  3. prd-draft: Hand it the resolved brief. You get: A PRD with an evidence-backed problem statement, numbered MoSCoW requirements, non-goals, and a success line per goal.
  4. doc-critique: Run it on the PRD, then take the result to whoever owns the decision. You get: A severity-tagged critique of the PRD with a verdict and a fix for each finding. You decide: Gate G0, a human call: PROCEED, PROCEED WITH CONDITIONS, REVISE (back to the brief), RECONSIDER (wrong problem) or BLOCKED.
  5. success-metrics: Once the PRD is ratified, ask how you will know the feature worked. You get: One primary metric with baseline, target and timeframe, guardrail metrics, the events to instrument, and a decision rule if the target is missed.

You end with: Interview kits, a tagged brief, a ratified PRD, and a measurement plan agreed before anyone builds.

4. Run it as a loop

A loop runs the skills in order and stops at each gate for a verdict. Install and start one:

npx skilldrop-cli install --loop --pack product-manager

Next

Edit this page on GitHub · View source