Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add konglong87/superPM --skill pm-prd-reviewgit clone --depth 1 https://github.com/konglong87/superPMWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/konglong87/superpm/pm-prd-review)<a href="https://agentmods.dev/skills/konglong87/superpm/pm-prd-review"><img src="https://agentmods.dev/badge/skills/konglong87/superpm/pm-prd-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/konglong87/superpm/pm-prd-review"><img src="https://agentmods.dev/badge/skills/konglong87/superpm/pm-prd-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00086 | $0.01890 |
| Opus 5 | $0.00043 | $0.00945 |
| Sonnet 5 | $0.00017 | $0.00378 |
| Haiku 4.5 | $0.00009 | $0.00189 |
Grade A, and why
pm-prd-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preamble (run first)
bash "$(dirname "${BASH_SOURCE[0]}")/../../check-update.sh" 2>/dev/null || true
# 创建方案设计目录
mkdir -p docs/02-方案设计
# 检查待评审文档
echo "📋 查找待评审文档..."
for f in "docs/02-方案设计/PRD产品需求文档.md" "docs/02-方案设计/BRD商业需求文档.md" "docs/02-方案设计/MRD市场需求文档.md" "docs/02-方案设计/PRD.md"; do
if [ -f "$f" ]; then echo "✅ 找到: $f"; fi
done
前置门禁
本技能用于评审已有文档,必须先有可评审文件:
- 检查
docs/02-方案设计/下是否存在 PRD/BRD/MRD(或用户提供的其他路径)。 - 若存在 → 读取并进入评审流程。
- 若不存在 → 停止,告知用户先执行
/pm-docs生成文档,或提供文档路径/内容后再评审。
不得在门禁不满足时编造评审对象。
跨 Agent 交互规则
当流程要求与用户交互时:
- 如果当前环境支持 AskUserQuestion,使用 AskUserQuestion(最佳体验)。
- 如果当前环境不支持 AskUserQuestion,必须用普通聊天消息提出同样问题。
- 一次只问一个问题。
- 提问后必须停止当前回合,等待用户回答(STOP and WAIT)。
- 不得在用户回答前生成文档、写入 docs。
- 已有 docs 文件不能替代本轮用户回答。
适用场景
- 用户说"评审 PRD""PRD 写得怎么样""帮我审一下需求文档""文档质量检查""BRD 复盘"
- 与
pm-docs区分:pm-docs 是"写",本技能是"审"——在开发/评审会前做质量把关。
执行流程
步骤 1: 确定评审范围与标准(主 agent - 用户交互)
使用 AskUserQuestion 询问:
🔍 评审设置
你要评审哪个文档 / 哪些维度?
A) 评审 PRD(默认全套维度) B) 评审 BRD C) 评审 MRD D) 自定义维度(仅完整性 / 仅可行性 / 仅风险 …)
评审严格度:
- 快速体检(关键问题)
- 深度评审(逐条清单,推荐用于评审会前)
记录到变量 REVIEW_DOC 与 REVIEW_MODE。
步骤 2: 读取待评审文档(主 agent)
使用 Read 工具读取 REVIEW_DOC。
若文档过大,提取关键章节(背景、目标、范围、功能需求、非功能需求、指标、风险、排期)进入评审上下文。
步骤 3: 逐项评审(主 agent)
按以下清单逐项核对,标注【通过 / 建议 / 严重】:
1. 完整性与背景
- 是否说明背景与要解决的问题
- 目标与成功标准是否明确
- 范围(in/out)是否清晰
2. 清晰度与一致性
- 功能需求是否可测试、无歧义
- 术语/口径是否全文一致
- 与 BRD/MRD/技术文档是否冲突
3. 可行性与资源
- 是否评估技术可行性
- 是否标注依赖与排期
- 是否识别关键资源缺口
4. 指标与验证
- 是否有可度量的验收标准
- 是否定义上线后验证方式(数据/埋点)
5. 风险与兜底
- 是否列出主要风险与应对
- 是否有降级/异常处理方案
6. 用户与体验
- 是否体现目标用户与核心场景
- 关键流程是否有交互/边界说明
步骤 4: 生成评审报告(主 agent)
使用 Write 工具生成 docs/02-方案设计/PRD评审报告.md:
# {文档类型} 评审报告
## 文档信息
- 被评审文档: {路径}
- 评审模式: {快速/深度}
- 评审日期: {当前时间}
- 生成工具: super-pm / pm-prd-review
---
## 一、总体结论
- 评审结果: 【可进入评审会 / 需修改后复审 / 重大缺陷】
- 严重问题数: {n} | 建议数: {m}
## 二、问题清单
| 编号 | 维度 | 级别 | 问题描述 | 修改建议 |
|------|------|------|---------|---------|
| Q1 | 完整性 | 严重 | {问题} | {建议} |
| Q2 | 可行性 | 建议 | {问题} | {建议} |
## 三、亮点
- {文档做得好的地方}
## 四、修改优先级
- P0(必须改): {列表}
- P1(建议改): {列表}
## 五、下一步建议
1. /pm-docs - 按评审意见修订文档
2. /pm-tech - 确认技术可行性
3. /pm-data - 补数据指标体系
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 213 lines · 86 tokens per session scan A 960dbf96c6d0
pm-prd-review is a skill published in the GitHub repository konglong87/superPM (65 stars, last pushed 6d ago), licensed MIT. It adds 86 tokens to every session and 1,890 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
multi-search
A web-search helper that chooses among DuckDuckGo, Tavily, Bing API, and Bing scraping based on the available network.
freeride
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates openclaw.json. Use when the user mentions free AI, OpenRouter, model switching, rate limits, or wants to reduce AI costs.
deepsafe-scan
Preflight security scanner for AI coding agents — scans deployment config, skills/MCP servers, memory/sessions, and AI agent config files (hooks injection) for secrets, PII, prompt injection, and dangerous patterns. Runs 4 model behavior probes (persuasion, sandbagging, deception, hallucination). Supports LLM-enhanced…
mapick
Mapick — Skill recommendation & privacy protection for OpenClaw. Scans your local skills, suggests what you're missing, and keeps other skills from seeing your sensitive data.
douyin-upload-mcp-skill
A guide for publishing videos and image-and-text posts through Douyin's creator website. Douyin is a Chinese social-media platform, and the guide uses its creator platform and available MCP tools.
team-tasks
Coordinate multi-agent development pipelines using shared JSON task files. Use when dispatching work across dev team agents (code-agent, test-agent, docs-agent, monitor-bot), tracking pipeline progress, or running sequential/parallel workflows. Covers project init, task assignment, status tracking, agent dispatch via…