AF product-review-panel
Convene a multi-expert panel to review a Product Requirements Document (PRD) and deliver a binding verdict (GO / NO-GO / CONDITIONAL GO) with dissenting opinions preserved as first-class output. Use when a Product Manager wants critical review of a written PRD, when deciding whether to build a specific feature, when stress-testing a proposal across product / UX / business-model dimensions, or for a structured "second opinion" before committing engineering resources. The panel adapts to the user's conversation language (Chinese → Cagan + 俞军 + 大厂 P9 产品总监 + situational like 张小龙; English/other → Cagan + Christensen + Senior PM Director + situational like Norman, Jobs, Hoffman, Torres). Every review ends with a verdict from "The Closer" (魔鬼裁判) plus observable failure signals to monitor. Do NOT use for pre-PRD idea brainstorming, purely technical architecture reviews, non-product strategy questions, or user research synthesis — use other skills for those.
Convene a multi-expert panel to review a Product Requirements Document (PRD) and deliver a binding verdict (GO / NO-GO / CONDITIONAL GO) with dissenting…
As a process F 39/100 · Will not run — References files that are not bundled: references/personas/experts-{cn|intl}.md
How to improve
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 17. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/personas/experts-{cn|intl}.md
Process rating: all ten parameters 39/100
- 0Tools and files. 1 referenced file(s) missing: references/personas/experts-{cn|intl}.md
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (product-review-panel) differs from the folder (product-review-panel-skill)
- 50When it triggers. No condition that starts the skill
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 51 steps, 2 vague phrases
- 100Execution cost. Instruction body is 1725 tokens
- 100Progress reporting. Reports progress
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +3Description length 963: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 17 headings
- +3Step-by-step instructions: 51 items
- +4Has examples (0 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.