licanfu/multica-best-practices/multica-review-product

Claude Code and agent skill by licanfu/multica-best-practices

Trust tier 3
  • community
Source check pending

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

Requirements/PRD dedicated review framework. Called by ProductReviewer to professionally analyze ProductManager's PRD (scope clear/goal explicit/acceptance testable/constraints complete/open items), output PASS/FAIL + fix list, report to Leader.

Install

npx vskill@latest install licanfu/multica-best-practices/multica-review-product

SKILL.md

Requirements (PRD) Professional Review (ProductReviewer)

Structured professional review framework for PRD / requirement artifacts. Called by ProductReviewer; reviews the PRD link ProductManager returns via multica-pm-artifact-publish.

When to use

  • ProductReviewer receives a "review PRD" dispatch from Leader.
  • Entering a re-review round after PRD changes (check previous round's fix list item by item).

Review dimensions (conclusion per item)

  1. Scope clear: boundaries unambiguous, splittable, no implied scope.
  2. Goal explicit: problem measurable, no vagueness.
  3. Acceptance testable: every AC- objectively verifiable, no "good experience" vagueness.
  4. Constraints complete: permissions, exceptions, compliance, dependencies, data口径 listed.
  5. Open items: OP- fully listed, not blocking downstream dev (blocking OP- = blocking item).

Output format

【PRD Review】<PRD link>
Conclusion: PASS / FAIL
Blocking items (required on FAIL, each: rationale / involved point / fix direction):
- ...
Suggestions (non-blocking):
- ...
Previous fix-list check (re-review): resolved X / unresolved Y
Round: N / 3

Conclusion + fix list reported to Leader; don't modify PRD or notify ProductManager yourself.

Boundaries

  • Review only PRD/requirements, not design, code, test cases, or UI.
  • Don't replace Leader's generic gate (multica-verification skill).
  • Technical feasibility goes to ArchReviewer; you own requirement-layer quality.
  • Still FAIL at round 3 → mark "escalate to human", hand to Leader, stop looping.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

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

Source

Popularity

7-day trend score
0

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/licanfu/multica-best-practices/multica-review-product/badge)](https://verified-skill.com/skills/licanfu/multica-best-practices/multica-review-product)

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