Group Discussion Reviewer — methodology (no key, inline)
Apply a disciplined product group-discussion review to a PRD directly in the
conversation. No API key, no Node, no code execution — you (the agent) perform the review
by following the written methodology.
This is the lightweight sibling of the group-discussion-reviewer engine skill. The
engine runs the same pipeline deterministically (and gates P0s with code) but needs an
OpenAI-compatible key. Prefer the engine when a key is available and fidelity matters; use
this methodology skill when there's no key, or for a quick framework-driven review.
Honest limitation: without the engine's deterministic P0 gatekeeper, the strictness of
P0 downgrading depends on your judgment. Hold the P0 bar hard.
How to use
- Get the PRD body as text/markdown (this skill does not fetch URLs or expand sheets).
- Read
methodology.md in this folder and execute its 8 phases in order.
- Produce exactly the output contract:
## 组内准入, ## 模拟评审结果, ## P0 Blockers,
## P1 Questions, ## P2 Questions, ## P1/P2 Improvement Suggestions.
- Respect the mode the user asks for (standard / deep / challenge; default challenge) and
the language (default Chinese).
The core discipline (summary — full detail in methodology.md)
- Two independent axes: 组内准入 (is it concrete enough to discuss?) vs 模拟评审结果
(would it pass?). A PRD can be admitted and still 不通过.
- P0 only for four failures: wrong direction/population, unmeasurable success (for a
formal decision), unsafe launch, or non-viable delivery — each with a concrete product
bridge. Everything else (stats audit, SLA/QPS/monitoring, tracking schema, release
checklist, compliance checklist, naming/icons, missing sections) defaults to P1/P2.
- A clean PRD has 0 P0. Don't inflate P0 to fill a quota.
- Blind review: PRD body only; ignore comments/annotations/post-meeting context. Ask
questions, don't answer them — except every P0 must include a concrete revision.
Always read methodology.md before reviewing; it carries the full P0 gate rules, the
calibration priors, and the reviewer lenses.
1---2name: group-discussion-reviewer-methodology3description: Group Discussion Reviewer — methodology (no key, inline)4---56# Group Discussion Reviewer — methodology (no key, inline)78Apply a disciplined product **group-discussion review** to a PRD **directly in the9conversation**. No API key, no Node, no code execution — you (the agent) perform the review10by following the written methodology.1112> This is the lightweight sibling of the **`group-discussion-reviewer`** engine skill. The13> engine runs the same pipeline deterministically (and gates P0s with code) but needs an14> OpenAI-compatible key. Prefer the engine when a key is available and fidelity matters; use15> this methodology skill when there's no key, or for a quick framework-driven review.16>17> **Honest limitation**: without the engine's deterministic P0 gatekeeper, the strictness of18> P0 downgrading depends on your judgment. Hold the P0 bar hard.1920## How to use21221. Get the PRD body as text/markdown (this skill does not fetch URLs or expand sheets).232. Read **`methodology.md`** in this folder and execute its 8 phases in order.243. Produce exactly the output contract: `## 组内准入`, `## 模拟评审结果`, `## P0 Blockers`,25 `## P1 Questions`, `## P2 Questions`, `## P1/P2 Improvement Suggestions`.264. Respect the mode the user asks for (standard / deep / challenge; default challenge) and27 the language (default Chinese).2829## The core discipline (summary — full detail in methodology.md)3031- **Two independent axes**: 组内准入 (is it concrete enough to discuss?) vs 模拟评审结果32 (would it pass?). A PRD can be admitted and still 不通过.33- **P0 only for four failures**: wrong direction/population, unmeasurable success (for a34 formal decision), unsafe launch, or non-viable delivery — each with a concrete product35 bridge. Everything else (stats audit, SLA/QPS/monitoring, tracking schema, release36 checklist, compliance checklist, naming/icons, missing sections) defaults to **P1/P2**.37- A clean PRD has **0 P0**. Don't inflate P0 to fill a quota.38- Blind review: PRD body only; ignore comments/annotations/post-meeting context. Ask39 questions, don't answer them — except every P0 must include a concrete revision.4041Always read `methodology.md` before reviewing; it carries the full P0 gate rules, the42calibration priors, and the reviewer lenses.