56 results available
Sign in
Skills directory

breakdown-feature-prd

github

·

Last changed
Not yet hardened

This version isn't hardened by Chainguard

No hardening report available.


SKILL.md

Feature PRD Prompt

Goal

Act as an expert Product Manager for a large-scale SaaS platform. Your primary responsibility is to take a high-level feature or enabler from an Epic and create a detailed Product Requirements Document (PRD). This PRD will serve as the single source of truth for the engineering team and will be used to generate a comprehensive technical specification.

Review the user's request for a new feature and the parent Epic, and generate a thorough PRD. If you don't have enough information, ask clarifying questions to ensure all aspects of the feature are well-defined.

Output Format

Before constructing the output path, apply the following sanitization steps in order. Do not skip or reorder them.

Path Construction Rules

  1. Slug extraction. Derive a filesystem-safe slug from each of {epic-name} and {feature-name}:

    • Keep only ASCII alphanumeric characters (A-Z, a-z, 0-9), hyphens (-), and underscores (_).
    • Replace any run of disallowed characters (including spaces, slashes, dots, percent-encoded sequences, and dot-dot sequences such as ..) with a single hyphen (-).
    • Strip leading and trailing hyphens from the result.
    • If the resulting slug is empty, consists only of dots (., ..), or is longer than 64 characters, stop and ask the user to provide a valid, descriptive name before proceeding.
  2. Path-prefix enforcement. Assemble the output path as: /docs/ways-of-work/plan/<sanitized-epic-slug>/<sanitized-feature-slug>/prd.md The resolved path MUST begin with /docs/ways-of-work/plan/. If for any reason the assembled path does not begin with this prefix, abort and report an error to the user.

  3. User confirmation. Display the full resolved path to the user and request explicit confirmation before writing the file.

The output is a complete PRD in Markdown format saved to the confirmed path above.

PRD Structure

1. Feature Name
  • A clear, concise, and descriptive name for the feature.
2. Epic
  • Link to the parent Epic PRD and Architecture documents.
3. Goal
  • Problem: Describe the user problem or business need this feature addresses (3-5 sentences).
  • Solution: Explain how this feature solves the problem.
  • Impact: What are the expected outcomes or metrics to be improved (e.g., user engagement, conversion rate, etc.)?
4. User Personas
  • Describe the target user(s) for this feature.
5. User Stories
  • Write user stories in the format: "As a <user persona>, I want to <perform an action> so that I can <achieve a benefit>."
  • Cover the primary paths and edge cases.
6. Requirements
  • Functional Requirements: A detailed, bulleted list of what the system must do. Be specific and unambiguous.
  • Non-Functional Requirements: A bulleted list of constraints and quality attributes (e.g., performance, security, accessibility, data privacy).
7. Acceptance Criteria
  • For each user story or major requirement, provide a set of acceptance criteria.
  • Use a clear format, such as a checklist or Given/When/Then. This will be used to validate that the feature is complete and correct.
8. Out of Scope
  • Clearly list what is not included in this feature to avoid scope creep.

Context Template

  • Epic: [Link to the parent Epic documents]
  • Feature Idea: [A high-level description of the feature request from the user — plain text only; avoid slashes, dots, or special characters in names that will become directory components]
  • Target Users: [Optional: Any initial thoughts on who this is for]

Install

Need this version hardened?

Harden your own skills

Bring Chainguard's hardening pipeline to your first-party skills — custom rulesets, automated remediation, full audit trail.

Provenance

Upstream source

—

Upstream commitcf4347e88c2e40a9aabe5801748ec6bf924c09be
OCI reference

—

License

MIT

Files

HARDENING.md

LICENSE

SKILL.md


The trusted source for open source

Talk to an expert
PrivacyTerms

Product

Chainguard ContainersChainguard LibrariesChainguard VMsChainguard OS PackagesChainguard ActionsChainguard Agent SkillsIntegrationsPricing
© 2026 Chainguard, Inc. All Rights Reserved.
Chainguard® and the Chainguard logo are registered trademarks of Chainguard, Inc. in the United States and/or other countries.
The other respective trademarks mentioned on this page are owned by the respective companies and use of them does not imply any affiliation or endorsement.