agentleFS
ahmadammarmahmadammarm/musyskills/skills/prd-generator/SKILL.md

prd-generator

Skill1 starsChanged 13 days agoMITView on GitHub

Generate a structured Product Requirements Document (PRD) by interviewing the user about a new feature or product idea, and save the result as a markdown file. Use whenever the user asks to write a PRD or define product requirements.

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

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

  • 0

    Common

    Most of the 25 edited versions we read keep these.

  • 8

    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:

    Before beginning the interview process, the agent must:

    line 22
  2. Very specific:

    Search the workspace for a PRD template (e.g., docs/PRD_TEMPLATE.md or .github/PRD_TEMPLATE.md).

    line 23
  3. Distinctive:

    Check if the user has provided an existing partial PRD, notes, or an issue ticket.

    line 24
  4. Very specific:

    Check if there is an existing docs/ folder in the project.

    line 25
  5. Distinctive:

    If the user hasn't provided a specific feature idea, ask them for one.

    line 30
  6. Distinctive:

    Ask clarifying questions to understand:

    line 31
  7. Distinctive:

    Ask the user to review, modify, or confirm the scope and user stories before proceeding to the full draft.

    line 40
  8. Very specific:

    Write the final PRD to a Markdown file in the project's documentation folder (e.g., docs/PRD-[feature-name].md).

    line 47
  9. Distinctive:

    If the user named a location, save the file there.

    line 48
  10. Distinctive:

    No hallucinated requirements: Never generate an entire PRD from a single vague sentence without first confirming the scope and user stories …

    line 54
  11. Distinctive:

    If a repository template is found in Pre-flight checks, use it exactly.

    line 61

“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

Purpose

To systematically interview the user to extract all necessary product requirements for a new feature or product, and structure that information into a comprehensive Markdown Product Requirements Document (PRD). The goal is to ensure that development does not begin until the scope, user stories, and technical constraints are well-defined and agreed upon.

Trigger

Activate this skill when the user:

  • Asks to "write a PRD," "create a product requirements document," or "draft a PRD."
  • Uses the explicit slash command /prd-generator.
  • Asks to define, specify, or formalize a new feature's requirements before coding.

Pre-flight Checks

Before beginning the interview process, the agent must:

  1. Search the workspace for a PRD template (e.g., docs/PRD_TEMPLATE.md or .github/PRD_TEMPLATE.md). If found, use its structure as the target format.
  2. Check if the user has provided an existing partial PRD, notes, or an issue ticket. If so, treat those as the base requirements and identify which sections are missing.
  3. Check if there is an existing docs/ folder in the project. If not, note that one may need to be created.

Workflow

Step 1: Initial Discovery

  • If the user hasn't provided a specific feature idea, ask them for one.
  • Ask clarifying questions to understand:
    • The primary problem being solved (the "Why").
    • The target audience and personas (who will use this feature).
    • Any known technical or business constraints.
  • Tip: Use interactive questions (e.g., the ask_question tool) or present a small, focused list of questions in the chat. Do not overwhelm the user with a massive questionnaire.

Step 2: Define Scope & Stories

  • Based on the initial discovery, propose a discrete list of "In Scope" and "Out of Scope" (Non-Goals) items. This is crucial for preventing feature creep.
  • Draft 3-5 core User Stories with basic Acceptance Criteria, following the format: "As a [persona], I want to [action] so that [benefit]."
  • Ask the user to review, modify, or confirm the scope and user stories before proceeding to the full draft.

Step 3: Draft the PRD

  • Once the user confirms the scope and stories, generate the full PRD according to the Output Format defined below.
  • Flesh out the remaining sections (Technical Considerations, UX/Design, Risks, and Success Metrics) based on best practices, standard patterns, and the context gathered in steps 1 and 2.

Step 4: Save and Present

  • Write the final PRD to a Markdown file in the project's documentation folder (e.g., docs/PRD-[feature-name].md).
  • If the user named a location, save the file there.
  • Otherwise, if a docs/ folder does not exist, create it and save the file there. Tell the user the path so they can move it if they prefer another location.
  • Inform the user that the file has been created, provide a direct link to it, and ask if any sections need further refinement.

Rules

  • No hallucinated requirements: Never generate an entire PRD from a single vague sentence without first confirming the scope and user stories with the user. The interview phase is mandatory.
  • Pacing: Group questions logically and proceed conversationally. Do not dump all questions at once.
  • Save to a file: The final PRD MUST be saved as an actual .md file in the project. Do not just print the entire PRD in the chat response, as this pollutes the context window.
  • Strict adherence to structure: The final PRD must contain all sections listed in the Output Format. If a section is not applicable, include the heading and write "N/A" with a brief reason.

Output Format

If a repository template is found in Pre-flight checks, use it exactly. Otherwise, the generated PRD must be formatted in Markdown and include the following sections exactly:

  1. Title & Meta Information
    • Project/Feature Name, Author, Status (Draft/In Review/Approved), Date, Target Release.
  2. Overview & Problem Statement
    • What: High-level summary of the feature.
    • Why: The specific problem this solves.
  3. Target Audience & Personas
    • Who will use this feature and what are their specific needs.
  4. Goals & Non-Goals
    • In Scope: What is being built.
    • Out of Scope (Non-Goals): What is explicitly NOT being built.
  5. User Stories & Functional Requirements
    • Format: "As a [persona], I want to [action] so that [benefit]."
    • Acceptance Criteria for each story (bulleted list defining when the story is "done").
  6. User Experience (UX) & Design
    • Core user flows, key interactions, or references to wireframes.
  7. Technical Considerations
    • High-level architecture, required API endpoints, database schema changes, etc.
  8. Dependencies, Risks & Mitigations
    • Blockers, security considerations, dependencies on other systems, and mitigations.
  9. Success Metrics
    • Quantifiable metrics to measure the feature's success (e.g., adoption rate, performance metrics).

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.