agentleFS
haqalizhaqaliz/assay/.claude/skills/prd-generator/SKILL.md

prd-generator

Skill0 starsChanged 3 days agoApache-2.0View on GitHub

Generate, critique, and refine PRDs, spec files, and roadmaps for initiative-level planning. Use to pressure-test and strengthen a PRD before planning. Triggers on "prd-generator", "prd generator".

32 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use user-story-generator, ui-ux-design and 7 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • nek1987Skill

    user-story-generator

    Generate user story generator operations. Auto-activating skill for Enterprise Workflows. Triggers on: user story generator, user story generator Part of the Enterprise Workflows skill category. Use when working with user story generator functionality. Trigger with phrases like "user story generator", "user generator", "user".

    Also in 3 projects that use this

  • rogue-dev-studioSkill

    ui-ux-design

    Expert UI/UX design for product interfaces: user flows, information architecture, wireframes, interaction patterns, accessibility, and a mandatory theme/brand alignment gate against the active project (PROJECT.md, design docs, existing tokens/visual language). Use before or alongside frontend work when designing screens, reviewing mockups, or validating that proposed UI matches the project theme already in progress or about to ship.

    Also in 3 projects that use this

  • dipaulavsSkill

    idea-validator

    Validates app ideas before building. Analyzes market saturation, competitors, real demand vs stated interest, solo builder feasibility (2-4 weeks timeline), and monetization potential. Use when user asks to validate an idea, evaluate a concept, check if idea is worth building, or before starting a new project.

    Also in 3 projects that use this

  • u9401066Skill

    bug-fix

    Structured bug fixing workflow with root cause analysis and regression prevention. Triggers: BF, 修 bug, fix bug, debug, 除錯, 錯誤, error, 問題, issue, 修復, fix, 故障, fault, 異常, exception, 失敗, failure, 不能用, broken, 壞掉.

    Also in 3 projects that use this

  • AnthropicSkill

    competitive-analysis

    Framework for building competitive landscape decks — market positioning, competitor deep-dives, comparative analysis, strategic synthesis. Use when the user asks for a competitive landscape, competitor analysis, peer comparison, market positioning assessment, strategic review, or investment memo deck. Also triggers on "who are the competitors to X", "benchmark X against peers", "build a market map", or any request to systematically evaluate competitive dynamics across an industry.

    Also in 3 projects that use this

  • SentrySkill

    skill-creator

    Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.

    Also in 5 projects that use this

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 8 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 27 edited versions we read keep these.

  • 8

    Distinctive

    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:

    Default to critical feedback over validation.

    line 17
  2. Distinctive:

    Never critique based on partial reads.

    line 40
  3. Very specific:

    Always include: explicit assumptions, open questions, a "Risks & Mitigations" section.

    line 82
  4. Distinctive:

    Run Workflow 1 against your own output.

    line 87
  5. Very specific:

    Default document format is markdown into docs/planning/{slug}/.

    line 120
  6. Distinctive:

    Use tables for comparisons and severity indicators (🔴🟡🟢).

    line 121
  7. Distinctive:

    Never prescribe a single framework.

    line 126
  8. Distinctive:

    Never generate a PRD without flagging its own gaps.

    line 127
  9. Distinctive:

    Never give generic advice.

    line 128
  10. Distinctive:

    Never skip the hard question.

    line 129

“Common” is measured: kept by at least 6 in 10 of the 27 edited versions of this file we could read. “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 Generator

Philosophy

This skill is framework-neutral. When coaching, always present multiple applicable frameworks, explain tradeoffs between them, and let the user choose.

Default to critical feedback over validation. Always identify gaps, challenge assumptions, and ask hard questions — then offer constructive paths forward.

Context

This skill supports planning at initiative scope. In the assay-begin-fast pipeline it is Phase 4: refine and self-critique the prd.md that prd-interview produced, then surface the gaps before the review gate.

For collaborative PRD creation from a brief, use the prd-interview skill.

Capabilities

CapabilityTrigger PhrasesOutput
Critique PRDs/Specs"review my PRD", "critique this spec", "what's missing"Structured critique with severity ratings
Generate PRDs"write a PRD for", "create a spec", "draft requirements"Complete PRD document (markdown)
Coach on Frameworks"how should I prioritize", "explain RICE", "opportunity sizing"Framework comparison with worked examples
Review Roadmaps"review my roadmap", "prioritization feedback", "sequencing"Prioritization analysis with alternative orderings

Workflow 1: Critique PRDs/Specs

Step 1 — Read the full document

Never critique based on partial reads.

Step 2 — Score across dimensions

Rate each dimension as 🔴 Critical Gap, 🟡 Needs Work, or 🟢 Strong:

  1. Problem Definition — Is the problem clearly stated? Evidence it's real?
  2. User Understanding — Are target users defined and validated?
  3. Success Metrics — Measurable, time-bound, tied to outcomes?
  4. Scope Clarity — In/out of scope explicit? Hidden assumptions?
  5. Edge Cases & Risks — Failure modes, dependencies, technical risks?
  6. Stakeholder Alignment — Who approves, builds, is impacted?
  7. Feasibility Signal — Engineering reality considered?
  8. Verdict Honesty & Sandbox Discipline (Assay-specific) — Does the work keep the sandboxed, observed run as the only thing that assigns CLEAN/FLAGGED/MALICIOUS? Does the always-on floor stay intact? Is MALICIOUS reserved for a captured, reproduced behavior, never an inference from a skill's text? Is UNVERIFIED honestly used when the sandbox can't run the skill or the dangerous path never fires?

Step 3 — Identify the top 3 gaps

Step 4 — Ask the hard question

End every critique with ONE pointed question the author probably hasn't considered.

Workflow 2: Generate PRDs

Step 1 — Gather inputs

Step 2 — Select PRD depth

TemplateBest ForDepth
Lightweight BriefSmall features, experiments1-2 pages
Standard PRDMid-size features3-5 pages
Full SpecLarge initiatives5-10+ pages

Problem Statement → Goals & Success Metrics → Users & Scenarios → Requirements → Technical Considerations (incl. sandbox/verdict impact) → Risks & Mitigations → Out of Scope.

Step 3 — Generate the PRD

Always include: explicit assumptions, open questions, a "Risks & Mitigations" section. Reference the roadmap's R1..R9 and the capability (A1..A10) the work belongs to.

Step 4 — Self-critique

Run Workflow 1 against your own output. Flag 🔴/🟡 areas as "Areas to strengthen before sharing."

Workflow 3: Coach on Frameworks

Prioritization: RICE, ICE, MoSCoW, Kano, Weighted Scoring, Cost of Delay / WSJF. Problem discovery: Jobs-to-Be-Done, Opportunity Solution Trees, Double Diamond. Strategy: Porter's Five Forces, Blue Ocean, Wardley Mapping. Sizing: TAM/SAM/SOM, Fermi estimation.

Workflow 4: Review Roadmaps & Prioritization

ApproachOptimizes ForTradeoff
Impact-firstMaximum outcome per unit timeMay defer foundational work
De-risk firstReduce uncertainty earlySlower visible progress
Quick wins firstMomentumMay delay strategic bets
Dependencies-firstUnblock parallel workFront-loads less exciting work

Visual-First Preview

PRD: {slug}
├─ Problem ........... {one line}
├─ Goals/Metrics ..... {one line}
├─ Users/Scenarios ... {one line}
├─ Requirements ...... must:{n}  should:{n}  nice:{n}
├─ Technical ......... {sandbox/verdict impact in a phrase}
├─ Risks ............. {top risk}
└─ Out of scope ...... {one line}

Output Format

  • Default document format is markdown into docs/planning/{slug}/.
  • Use tables for comparisons and severity indicators (🔴🟡🟢).

Anti-Patterns (Never Do These)

  1. Never just validate.
  2. Never prescribe a single framework.
  3. Never generate a PRD without flagging its own gaps.
  4. Never give generic advice.
  5. Never skip the hard question.
  6. Never wave through a static-only verdict dressed as verification — if a PRD's verdict rests on a pattern match or a model's reading of the skill's text rather than an observed sandbox run, or lets either assign MALICIOUS/CLEAN, or renders UNVERIFIED as CLEAN, that's a 🔴 regardless of how good the rest is.

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.