agentsclimarketplace

Create prd

Skill Karthick-Ramachandran/persist-os/.agents/skills/create-prd

Local-first CLI that gives your repo durable, AI-ready memory - features, ADRs, modules, architecture, standards & tests and a deterministic doctor that validates health, evidence & drift.

Install
npx -y skills add Karthick-Ramachandran/persist-os --skill create-prd

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

One thing to look at

  • 8 stars8 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

1.9 KB, as published. Nobody here has run it

Skill: Create PRD

Purpose

Create a useful feature PRD that helps humans and AI agents understand what should be built and why.

Inputs

  • Feature name or problem statement.
  • User goal or business reason.
  • Any existing product notes, tickets, or change requests.

Required Reading

  • docs/00-product/BRD.md
  • docs/00-product/PRD.md
  • Relevant existing docs/40-features/<feature>/
  • Relevant accepted ADRs in docs/adrs/

Output Files

  • docs/40-features/<feature>/PRD.md
  • docs/40-features/<feature>/ACCEPTANCE.md, when acceptance criteria are part of the request.
  • docs/40-features/<feature>/CHANGE_REQUESTS.md, when changing existing requirements.

Process

  1. Identify the user, problem, desired outcome, and non-goals.
  2. Link the feature to product goals and existing source-of-truth docs.
  3. Define acceptance criteria that can be tested.
  4. Capture security, privacy, file write, dependency, and MCP implications.
  5. Identify architecture areas that require follow-up review.
  6. Keep the PRD concise and implementation-guiding.

Stop Conditions

Stop and request human decision if:

  • Product intent is contradictory.
  • A requested behavior conflicts with an accepted ADR.
  • The feature adds network, telemetry, AI API, cloud, MCP runtime, auth, secrets, or file write behavior without explicit approval.
  • Scope is too broad to define testable acceptance criteria.

Quality Bar

  • The PRD states goals, non-goals, users, acceptance criteria, risks, and source links.
  • Acceptance criteria are concrete enough to drive tests.
  • Security and architecture implications are not generic filler.
  • The PRD does not duplicate full architecture docs.

Keep looking

Skills are one crate of 328,083. 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.