gongshichen/luminacode/prd-authoring

Claude Code and agent skill by gongshichen/luminacode

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Produce a product requirements document that can drive design, engineering, QA, and review.

Install

npx vskill@latest install gongshichen/luminacode/prd-authoring

SKILL.md

Write the PRD as a durable project artifact, normally <project_root>/PRD.md.

Inputs:

  • User request and any clarified constraints.
  • Current working directory and inferred project root.
  • Existing product/repository context when present.
  • Known time, platform, dependency, data, privacy, and operational constraints.

Required structure:

  1. Title and status
  • Product/workstream name.
  • Authoring date and status: draft, ready for design, revised, or deferred.
  1. Problem and goal
  • Problem statement in user terms.
  • Primary goal and success signal.
  • Non-goals that prevent scope creep.
  1. Users and scenarios
  • Target users or roles.
  • Core scenario and at least one failure or edge scenario.
  1. Scope
  • In scope.
  • Out of scope.
  • Explicit assumptions.
  1. User flows
  • Happy path.
  • Empty/loading/error path.
  • Recovery path when relevant.
  1. Functional requirements
  • Numbered requirements with observable behavior.
  • Required data, persistence, integration, and validation behavior.
  • Requirements that must be verified by QA.
  1. Interface and data requirements
  • Components that must integrate.
  • Data fields, ownership, lifecycle, and privacy/security considerations.
  • Any known API, event, file, command, or storage boundary.
  1. Acceptance criteria
  • User-visible acceptance criteria.
  • Required artifacts and commands.
  • Integration smoke expectations.
  1. Risks, dependencies, and open questions
  • Risks with owner or mitigation.
  • External dependencies.
  • Questions that block work, and questions that can proceed with assumptions.

Quality bar:

  • The PRD must be concrete enough for UX Design to produce a design without inventing product scope.
  • It must be concrete enough for Frontend and Backend to produce separate technical plans.
  • It must avoid implementation choices unless the user or repository already constrains them.
  • It must preserve the user's architecture; do not simplify multi-component work into one direct-file shortcut.

Handoff:

  • Send UX Design an A2A message with the PRD path and a short summary.
  • Keep the PRD path in Team dialogue and the Team Acceptance Contract.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
9
Repository forks
1
7-day trend score
0

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/gongshichen/luminacode/prd-authoring/badge)](https://verified-skill.com/skills/gongshichen/luminacode/prd-authoring)

Something wrong with this skill or its page? Tell us.