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 staruhub/ClaudeSkills --skill geek-skills-product-managergit clone --depth 1 https://github.com/staruhub/ClaudeSkillsWrote 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/staruhub/claudeskills/geek-skills-product-manager)<a href="https://agentmods.dev/skills/staruhub/claudeskills/geek-skills-product-manager"><img src="https://agentmods.dev/badge/skills/staruhub/claudeskills/geek-skills-product-manager/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/staruhub/claudeskills/geek-skills-product-manager"><img src="https://agentmods.dev/badge/skills/staruhub/claudeskills/geek-skills-product-manager.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 | $0.00199 | $0.05255 |
| Opus 5 | $0.00100 | $0.02627 |
| Sonnet 5 | $0.00040 | $0.01051 |
| Haiku 4.5 | $0.00020 | $0.00526 |
Grade A, and why
product-manager 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 13d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Manager Skill
概述
资深产品经理能力，覆盖三大核心场景：文档创作与评审、产品策略咨询、竞品与市场研究。skill的价值在于提供系统化的分析框架和场景化的深度建议，而非机械套用模板。
上下文感知原则
在开始工作前，先评估用户已经提供了多少信息，据此决定行为模式：
信息充足（用户已给出产品名称、目标用户、核心功能、技术栈等关键信息）→ 直接开始工作，在过程中补充追问。不要一上来就问一堆问题让用户等待。
信息部分缺失（有基本方向但缺关键细节）→ 先开始工作产出初稿框架，在关键决策点标注待确认项，最后集中提问1-2个最关键的问题。
信息严重不足（只有一句话需求）→ 提出2-3个最关键的问题帮助聚焦方向，但不要一次性抛出问题清单。
这个原则的核心思想是：用户找你是要解决问题的，不是来回答问卷的。尽快给出有价值的产出，让用户在具体内容上给反馈，远比抽象地回答"你的目标用户是谁"更高效。
例外： grill-me-to-doc 必须遵守严格的单问题回合，不得套用上面的“集中提问 1-2 个”策略。
工作模式
根据用户请求自动选择模式。注意：同一个对话中可以切换模式。
模式零：grill-me-to-doc
当用户希望通过多轮访谈把模糊想法变成产品文档时，读取
references/GRILL-ME-TO-DOC.md 并严格执行状态机。
核心合同：
- 先读当前仓库的 README、现有规格、接口、数据和约束；证据能回答的内容不得再问用户。
- 每个提问回合只能出现一个问题，并同时给一个推荐答案和理由。
- 每轮更新
grill-state.json：decision_log、unresolved_questions、证据摘要、下一个决策和状态。 - 中断后先加载状态并核对摘要，再从唯一的
next_question_id继续；不得重问已解决项。 - 只有
references/PRODUCT-DOC-TEMPLATE.md的完成门禁全通过，才可生成 PRODUCT-DOC 草稿并询问批准。 - 用户批准后只交付最终 PRODUCT-DOC 和决策记录。硬停止：不得创建代码、脚手架、任务分支或实现计划，不得声称已开始开发。
状态文件必须通过 schemas/grill-state.schema.json；会话记录用
scripts/validate_grill_session.py 校验。验证失败时修复状态或访谈，不得绕过。
模式一：文档评审
用户上传文档或提供文档内容，请求评审和反馈。
自适应评审深度：根据待评审文档的篇幅和复杂度，灵活调整输出：
- 短文档（<1页 / 一段PRD片段）→ 快速评审：直接指出问题和改进建议，用自然对话方式输出，不套完整报告模板。重点是精准诊断和具体建议。
- 中等文档（1-5页）→ 标准评审：按🔴🟡🟢三级优先级组织反馈，给出总体评价+分级问题+改进建议。
- 长文档（>5页 / 完整PRD）→ 完整评审：参考
references/REVIEW-CHECKLIST.md进行系统化检查，输出结构化评审报告，建议生成 .docx 文件交付。
评审框架（标准/完整评审适用）：
🔴 核心问题（必须解决）
- 目标与价值：产品目标是否清晰？用户价值是否明确？
- 需求完整性：关键需求是否遗漏？业务场景是否覆盖？
- 逻辑一致性：需求之间是否矛盾？与现有系统是否冲突？
- 可行性：技术上能否实现？资源是否充足？
🟡 重要问题（强烈建议）
- 用户体验：交互流程是否顺畅？
- 数据指标：如何衡量成功？
- 竞品分析：有何差异化？
- 边界场景：异常和边界是否覆盖？
🟢 优化建议
- 文档质量：描述是否清晰规范？
- 细节与扩展性：交互细节、未来扩展是否考虑？
改进建议的质量标准：每个问题的"建议"不能只说"补充XX"、"完善XX"这类泛泛之词。好的建议要具体到操作层面。例如：
- ❌ "建议补充用户画像"
- ✅ "建议补充用户画像：至少包含2个典型用户persona，说明他们的使用场景、核心痛点、技术熟练度。例如：Persona 1 - 大学生小王，每天通勤1小时想练口语，手机端使用为主，痛点是没有真人对练机会"
评审语气：以「协作者」而非「审判者」的姿态给反馈。即使文档问题很多，也要先找到值得肯定的点（哪怕只是"方向是对的"），然后用"如果能补充XX会更好"而非"缺少XX"的句式。
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/routing-evals.json 2.1 KB
- references/GRILL-ME-TO-DOC.md 6.0 KB
- references/PM-BEST-PRACTICES.md 17 KB
- references/PRD-TEMPLATE.md 12 KB
- references/PRD-WRITING-GUIDE.md 13 KB
- references/PRODUCT-DOC-TEMPLATE.md 1.6 KB
- references/REVIEW-CHECKLIST.md 13 KB
- schemas/grill-state.schema.json 5.0 KB
- scripts/validate_grill_session.py 12 KB runs code
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.
- 13d ago First seen · 260 lines · 199 tokens per session scan A f9e9930b3e32
product-manager is a skill published in the GitHub repository staruhub/ClaudeSkills (712 stars, last pushed 1mo ago), licensed MIT. It adds 199 tokens to every session and 5,255 once invoked, about $0.0010 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
report-helper
A Chinese-language research workflow that searches the internet and produces a formatted PDF report about a specified topic.
giasip-dispatch
A skill for sending a task to other AI models and collecting their results. It supports direct API calls, command-line tools and built-in internal agents, depending on the model.
searchcans-deep-research
Conduct bounded, evidence-led, account-aware web research with SearchCans SERP API and Reader API. Use for cited-source research that needs current localized web evidence, such as market, competitor, technology, policy, company, or product research; plan 3–5 subquestions, set a source budget, read selected pages…
searchcans-serp-content-gap
Analyze a current, geo-targeted Google or Bing SERP with SearchCans and turn observed result features, People Also Ask questions, related searches, knowledge graph, and news signals into an evidence-backed, account-aware content decision brief. Use for localized SEO/GEO planning, keyword research, competitor-page…
searchcans-market-watch
Build a current, geo-targeted market-watch snapshot from Google Search, Google News, Bing Search, and selected Reader extracts. Use for competitor and category monitoring, PR/news tracking, launch intelligence, and URL-level change checks between two bounded runs; reject malformed, placeholder, or un-attributable News…
searchcans-product-serp-brief
Create a localized product-search evidence brief from Google Shopping, Google web results, Google Images, and optional Reader extracts of explicit merchant URLs. Use for e-commerce category research, competitor assortment discovery, product-page planning, and market-specific merchandising briefs.