agentsclimarketplace
Sign in

Idea discovery interview

Skill bglglzd/agent-workflows/plugins/agent-workflows/skills/idea-discovery-interview

Interview a user with a vague product, feature, or application idea before planning implementation. Use when Codex must ask at least ten high-signal questions, capture a durable discovery brief, expose constraints and risks, and produce an evidence-based plan without inventing requirements.From its SKILL.md

Install
npx -y skills add bglglzd/agent-workflows --skill idea-discovery-interview

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.8 KB, 303 tokens by cl100k_base, as published. Nobody here has run it

Idea Discovery Interview

Turn an initial idea into an agreed, buildable brief before committing to a plan or implementation.

Interview workflow

  1. Inspect existing project docs, issues, briefs, and code first. Do not ask for facts that are already documented.
  2. Restate the idea in one sentence and identify the key unknowns.
  3. Ask one to three focused questions per turn. Ask at least ten substantive questions before producing a full plan.
  4. Cover the problem and user, success metrics, core journey, MVP and non-goals, platforms, data lifecycle, auth/privacy/security, integrations, technical and operating constraints, quality bar, risks, and launch criteria.
  5. Ask follow-up questions when an answer affects a decision. Do not silently choose a product requirement, stack, budget, timeline, or compliance posture for the user.
  6. Keep a living brief. Reuse existing product-discovery documentation or create docs/ai/discovery/<idea-slug>.md when the project is writable.

Deliverable

After sufficient answers, produce a discovery brief with: problem and users; goals and success metrics; core journey; MVP scope; non-goals; requirements and acceptance criteria; data, privacy, and security; integrations and constraints; recommended architecture plus alternatives; milestones and validation; risks, assumptions, and open decisions; and first implementation steps.

Clearly label confirmed decisions, assumptions, and unanswered questions. Ask for approval or revision before starting implementation.

What ships with it: 1 file

210 B alongside SKILL.md

agents/

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.