agentleFS
Sign inStart free
richkuorichkuo/rk-skills/skills/prd-questions/SKILL.md

prd-questions

Skill50 starsChanged 6 days agoMITView on GitHub

Use when the user wants every open question in a PRD resolved interactively — "ask me all questions", "/prd-questions", "let's resolve the open questions". Sweeps the PRD for open questions and ambiguities, asks them in batched multiple-choice form with recommendations, folds every answer back into the owning spec section, and empties the Open Questions section. Stage 2 of the new-app-pipeline.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every item in the Open Questions section.

    line 20
  2. Distinctive:

    Use the AskUserQuestion tool, max 4 questions per call, sequential calls until done:

    line 28
  3. Very specific:

    Put your recommended option first, labeled (Recommended), and base the recommendation on reasons (privacy-preserving, simplest-correct, …

    line 31
  4. Distinctive:

    Update worked examples to match (and remove "unverified" hedges once confirmed).

    line 40
  5. Very specific:

    Commit and push (same PRD PR if still open.

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

prd-questions

Resolve every open decision in the PRD by asking the user directly, then fold each answer into the section it governs and empty the Open Questions section.

Input

A repo containing PRD.md (or a named PRD file).

Steps

1. Sweep for questions

Collect, in order:

  1. Every item in the Open Questions section.
  2. Inline ambiguities elsewhere ("TBD", "confirm", "assumed", hedged examples).
  3. Decisions embedded in Post-MVP / roadmap sections that were deferred without being decided.

"All questions" means all three groups.

2. Ask in batches

Use the AskUserQuestion tool, max 4 questions per call, sequential calls until done:

  • Each question: 2–4 concrete options that name the actual competing designs and their tradeoffs. No bare yes/no options.
  • Put your recommended option first, labeled (Recommended), and base the recommendation on reasons (privacy-preserving, simplest-correct, matches the PRD's stated priorities).
  • One question per decision. Never bundle two decisions into one option.
  • Post-MVP questions are fair game but mark them as such in the question text, and offer "Defer to scoping" as a legitimate recommended option when deciding now has no benefit.

3. Fold answers into the spec

For every answer:

  • Edit the owning section — pricing answers into the pricing tables/rules, privacy answers into the privacy section, failure-handling into billing/lifecycle. The spec text states the decision plainly; no "per user decision on <date>" hedging inside the rule itself.
  • Update worked examples to match (and remove "unverified" hedges once confirmed).
  • Cross-reference where a rule spans sections (§-refs).

4. Close out

  • Replace the Open Questions list with a one-paragraph note: "None — all prior open questions resolved <date> and folded into the spec:" followed by a decision → section map.
  • Commit and push (same PRD PR if still open; footer verb Updated).

Output

One reply listing each decision in a compact sentence series, plus where it landed. Note the PRD PR is ready to merge if this was the last blocker.

Failure modes

SituationDo this
User picks "Other" with free textTreat as the answer; fold it in verbatim, ask one follow-up only if it's internally contradictory
An answer contradicts existing spec text elsewhereUpdate every affected section; call out the ripple in your reply
More than ~12 questions foundStill ask them all; batch each AskUserQuestion call by theme (pricing, privacy, lifecycle)
A "question" is really a research task, not a user decisionDon't ask it; note it as a scoping task in the roadmap section

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free