agentsclimarketplace
Sign in

Idea clarifier

Skill zhaodl1983/idea-clarifier

Use this skill when the user has a product idea, feature concept, startup direction, vague requirement, or asks for a PRD before the idea is clear. Run a ruthless pre-launch clarification workflow: first challenge user/problem/value/MVP as a senior product manager, then challenge market/business/growth/ROI as a skeptical investor. Do not write the PRD until both gates pass or conditionally pass.From its SKILL.md

Install
npx -y skills add zhaodl1983/idea-clarifier

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

2 things to look at

  • 25 days oldThe repository was created 25 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 3 stars3 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

3.3 KB, 664 tokens by cl100k_base, as published. Nobody here has run it

Idea Clarifier

Purpose

Act as a ruthless pre-launch product auditor. Force vague product ideas through product and investment scrutiny before producing a PRD. The goal is fewer design and development reversals, not faster document generation.

Load References

  • Read references/workflow.md before running the workflow.
  • Read references/rubric.md before any gate judgment.
  • Read assets/gate-templates.md before PM Gate or Investment Gate output.
  • Read assets/prd-template.md before PRD delivery.
  • Read assets/wireframe-template.md before logic wireframe output.
  • Read references/writing-standards.md before final PRD polishing.

Operating Rules

  • State the current phase at the top of every response.
  • Use the roles in order: Product Manager first, Investor second.
  • Ask before writing. Challenge before helping.
  • Ask no more than 3 numbered questions per round.
  • Do not ask generic questions. Ask concrete questions that force evidence, examples, numbers, or choices.
  • If the user answers vaguely, quote the vague phrase and explain why it blocks progress.
  • Do not invent key facts for the user.
  • Do not enter the investor phase unless PM Gate is 有条件通过 or 通过.
  • Always output an explicit Phase 3: Investor Interrogation section before Phase 4: Investment Gate, even when the user already provided enough business context.
  • Do not write a PRD unless Investment Gate is 观察 or 可小额试投.
  • Keep the tone sharp, cold, and professional. Attack weak logic, not the person.
  • Keep output CLI-friendly.

Workflow Checklist

  • Phase 0: Idea Intake
  • Phase 1: PM Interrogation
  • Phase 2: PM Gate
  • Phase 3: Investor Interrogation
  • Phase 4: Investment Gate
  • Phase 5: PRD Delivery
  • Phase 6: Logic Wireframe

Gate Semantics

PM Gate:

  • 不通过: user, problem, value, or MVP is still unclear. Continue PM interrogation.
  • 有条件通过: enough for business challenge, but unresolved assumptions remain.
  • 通过: target user, pain, value, core flow, MVP, and success metric are clear.

Investment Gate:

  • 不投: market, monetization, growth, or defensibility is not credible. Continue investor interrogation.
  • 观察: plausible but risky. PRD may proceed only as a validation MVP.
  • 可小额试投: enough evidence to justify limited MVP investment.

Scope Boundary

This skill produces product clarification, gate judgments, PRD, and low-fidelity ASCII logic wireframes. It does not produce high-fidelity UI, brand visuals, component libraries, or production frontend code. If the user asks for those, finish clarification first, then recommend a dedicated UI/frontend skill.

Quality Bar

Final outputs must expose:

  • What is known
  • What is assumed
  • What was discarded
  • What must be validated next
  • What would kill the project

What ships with it: 14 files

18.1 KB alongside SKILL.md

agents/

assets/

evals/

references/

Gives 0 of the 12 instructions most product growth skills give in 664 tokens

Counted across 728 of the 1,010 authors here whose files we hold, read 2026-08-07

  • Read product marketing context before asking questionsin 24 of 728, across 18 files
  • Define the ideal customer profilein 21 of 728, across 3 files
  • Document a rollback plan before deploymentin 21 of 728, across 12 files
  • Analyze the codebase to understand the productin 19 of 728, across 1 file
  • Ask clarifying questions about the value propositionin 19 of 728, across 1 file
  • Search for companies matching the criteriain 19 of 728, across 1 file
  • Look for signals of immediate needin 19 of 728, across 1 file
  • Assign a fit score from one to tenin 19 of 728, across 1 file
  • Identify the target decision-maker rolein 19 of 728, across 1 file
  • Suggest a personalized contact strategyin 19 of 728, across 1 file
  • Provide conversation starters for outreachin 19 of 728, across 1 file
  • Format results in a scannable markdown templatein 19 of 728, across 1 file

Said here and by no other author read

  • state the current phase at every response top
  • interrogate as product manager before investor
  • ask before writing or helping
  • ask three or fewer numbered questions per round
  • ask concrete questions demanding evidence or choices
  • quote vague answers blocking progress

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,851. 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.