agentleFS
formal-youformal-you/agent-skills-suite/skills/workflow/prd-generator/SKILL.md

prd-generator

Skill0 starsChanged 28 days agoMITView on GitHub

Turn an ambiguous product idea into a modular PRD bundle (.specs/01-prd.md and .specs/01-prd/). Use when the user asks for a PRD, product requirements, feature scoping, MVP definition, or a PRD revision. Do not use for architecture decisions or engineering specifications; use spec-generator after the PRD exists.

30 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use user-story-generator, idea-validator 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

  • 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

  • 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

  • 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

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

  • 0

    Common

    Most of the 25 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not use when:

    line 24
  2. Distinctive:

    Review the idea from four perspectives: Prefer independent reviewers when the host provides subagent tools.

    line 53
  3. Very specific:

    Author the artifacts: Follow references/prd-format.md.

    line 62
  4. Very specific:

    All helpers are stdlib-only Python and resolve paths from their own location, so the skill directory can be copied anywhere.

    line 71
  5. Very specific:

    Every functional requirement has a #sec-<kebab-case> anchor.

    line 99
  6. Distinctive:

    Every NFR has a measurable target and a verification method.

    line 102
  7. Distinctive:

    Every relative link resolves.

    line 103
  8. Distinctive:

    Do not add entities, roles, integrations or compliance regimes the user did not provide or imply.

    line 108

“Common” is measured: kept by at least 6 in 10 of the 25 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

Convert an ambiguous product idea into a product requirements document that a downstream architecture review can consume without guessing. The skill supplies judgment (clarification, four-role review, convergence) and templates; it does not invent domain content.

When to use

  • The user asks for a PRD, product requirements, feature scoping, MVP boundaries, or a PRD revision.
  • A one-line idea, a notes dump, or a broken draft must become a structured requirements document.
  • A downstream step needs stable REQ/CON/NFR/FORK identifiers and #sec-* anchors.

Do not use when:

  • The request is an architecture decision, ADR, or engineering specification: use spec-generator after the PRD exists.
  • The user only needs a quick summary of an existing document: answer directly.
  • The task is implementation, test design, or task slicing: use the downstream skills.

Inputs

  • The user's idea, notes, or existing documents. Ask only for what blocks a decision.
  • Optional: domain hint, constraints, target users, non-goals, existing PRD to revise.

Outputs

PathContents
.specs/01-prd.mdAggregate PRD: REQ-###, CON-###, NFR-###, FORK-###, #sec-* anchors
.specs/01-prd/00-overview.mdProblem, value, scope, milestones
.specs/01-prd/01-features.mdFunctional requirements with anchors
.specs/01-prd/02-constraints.mdNon-negotiable constraints
.specs/01-prd/03-nfr.mdMeasurable non-functional targets
.specs/01-prd/04-forks.mdArchitectural unknowns handed to spec-generator

The aggregate file is authoritative; the bundle is its modular copy.

Workflow

  1. Intake and clarify. Extract the goal, users, constraints, non-goals, and measurable outcomes. If a gap blocks the PRD, ask a focused question; do not fill gaps with assumptions from other domains.
  2. Review the idea from four perspectives. Prefer independent reviewers when the host provides subagent tools. Otherwise run the same four roles as an explicit in-context review round. Roles, veto rule, scoring and tie-break are in references/deliberation-protocol.md.
  3. Converge. Record the decisions and the unresolved architectural forks (FORK-*) with at least two viable options and decision drivers. Never pre-select an option in the PRD.
  4. Scaffold (optional). From the repository root: python .agents/skills/prd-generator/scripts/scaffold.py --out .specs (add --dry-run first).
  5. Author the artifacts. Follow references/prd-format.md. Replace every {{UPPER_SNAKE}} placeholder; keep identifiers consistent and each anchor tied to its module.
  6. Lint (optional). python .agents/skills/prd-generator/scripts/lint_prd.py .specs/01-prd.md (or .specs). Fix every error before handing off.
  7. Hand off. State the output paths and the unresolved FORK-* items. The next step is spec-generator.

Tooling (optional)

All helpers are stdlib-only Python and resolve paths from their own location, so the skill directory can be copied anywhere. Run them from the repository root with --help instead of reading the source.

CommandPurpose
python .agents/skills/prd-generator/scripts/scaffold.py --out .specs [--dry-run] [--force] [--json]Copy templates into the output tree
python .agents/skills/prd-generator/scripts/lint_prd.py .specs [--json]Structural gate: placeholders, anchors, required tokens, links
python .agents/skills/prd-generator/scripts/engine.py run --idea "..." --output-dir .specsOptional engine proxy

Exit codes: 0 success, 1 content/gate failure, 2 optional dependency or usage unavailable, 3 unexpected error.

The engine is optional and never required. If it is not installed, engine.py exits 2 with install guidance. Scaffolding, authoring and linting still work.

Manual fallback (no Python)

  1. Create .specs/01-prd/.
  2. Copy each *.template.* file under assets/templates/ into .specs/, removing the .template segment from the name (01-prd.template.md -> 01-prd.md); skip README.md, which is a guide.
  3. Fill every placeholder, then self-check against the quality gate below.
  4. Record the same checks (placeholders, anchors, required tokens, links) in your summary.

Quality gate

  • No {{...}}, [TBD], or TODO tokens remain.
  • Every functional requirement has a #sec-<kebab-case> anchor; repeated references to the same anchor are fine.
  • At least one REQ-###, CON-###, NFR-### and FORK-### (omit a category only when the user's context genuinely has none, and say so).
  • Every NFR has a measurable target and a verification method.
  • Every relative link resolves.
  • Content is traceable to the user's request; no examples from this template or other domains.

Anti-hallucination rules

  • Do not add entities, roles, integrations or compliance regimes the user did not provide or imply.
  • Mark uncertain items as open questions instead of inventing answers.
  • Templates are shapes, not content: never copy their illustrative values into the output.

References

  • references/deliberation-protocol.md - roles, rounds, veto, scoring, tie-break.
  • references/prd-format.md - artifact contract, identifiers and anchors.
  • references/agent-platform-patterns.md - optional domain note; read only when the product is an agent platform.
  • references/zh-CN.md - optional Chinese quick reference.

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.