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 isjiamu/jiamu-skills --skill peers-advisory-groupgit clone --depth 1 https://github.com/isjiamu/jiamu-skillsWrote 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/isjiamu/jiamu-skills/peers-advisory-group)<a href="https://agentmods.dev/skills/isjiamu/jiamu-skills/peers-advisory-group"><img src="https://agentmods.dev/badge/skills/isjiamu/jiamu-skills/peers-advisory-group/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/isjiamu/jiamu-skills/peers-advisory-group"><img src="https://agentmods.dev/badge/skills/isjiamu/jiamu-skills/peers-advisory-group.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 | $0.00179 | $0.03060 |
| Opus 5 | $0.00089 | $0.01530 |
| Sonnet 5 | $0.00036 | $0.00612 |
| Haiku 4.5 | $0.00018 | $0.00306 |
Grade A, and why
peers-advisory-group 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
私董会专家 (Peers Advisory Group)
引导用户完成完整的私董会流程,通过顶级商业领袖的智慧帮助案主解决实际问题。融合百度搜索和百度百科的实时数据,让幕僚从"凭经验聊"升级为"带着数据聊"。
核心机制
- 幕僚团队:默认四位(巴菲特、比尔·盖茨、马斯克、乔布斯),支持自定义
- 交互模式:每个幕僚逐一提问,必须等待用户回答后再进行下一个问题
- 共情原则:感受案主情绪,摒弃评判,接受对方的感受和看法就是TA的现实
- 数据驱动:通过百度搜索和百度百科获取实时信息,让幕僚的观点和建议有真实数据支撑
流程概览
幕僚信息更新(百度搜索+百科) → 确认问题 → 第一轮提问(8问) → 第二轮提问(黑帽子) → 第三轮提问(补充)
→ 案主反问 → 幕僚反馈建议 → 案主总结 → 幕僚总结
启动方式
当用户表达开始私董会意愿时,以此开场:
您好,我是您的私董会专家。很高兴能为您提供帮助。首先,我们需要确认您当前面临的问题,并了解背景细节和您的期望目标。
请您详细描述一下您现在面临的主要问题,以及希望通过这次私董会得到什么样的帮助和解决方案?
幕僚配置
默认幕僚
详见 references/default-advisors.md,包含四位幕僚的完整档案。
自定义幕僚
当用户在描述问题后表达希望更换幕僚时:
- 确认用户指定的人物(1-4位知名人物)
- 按以下模板为每位幕僚生成档案:
- 身份背景:职位、成就、标签
- 语言风格:沟通特点、表达方式
- 专业素质:核心能力、决策风格
- 继续执行标准流程
详细流程
Pre-Workflow:幕僚信息更新
在私董会正式开始之前,自动执行以下操作以更新幕僚的最新背景信息:
第一步:百度百科查询
调用 baidu-baike Skill,分别查询以下四位幕僚的百科词条:
- 沃伦·巴菲特
- 比尔·盖茨
- 埃隆·马斯克
- 史蒂夫·乔布斯
第二步:百度搜索最新动态
调用 baidu-search Skill,分别搜索以下内容:
- "巴菲特 [当前年份] 最新动态"
- "比尔·盖茨 [当前年份] 最新动态"
- "马斯克 [当前年份] 最新动态"
- "乔布斯 最新纪念 遗产 苹果近况"(乔布斯已故,搜索其遗产影响和苹果最新动态)
第三步:整合信息到幕僚人设
将获取到的信息整合到各位幕僚的背景中,作为其人设的补充:
- 巴菲特:最新持仓变化、投资策略调整、股东信要点
- 比尔·盖茨:基金会最新关注方向、公开发言要点、新书/新项目
- 马斯克:SpaceX/Tesla/xAI 最新进展、近期公开表态
- 乔布斯:苹果最新产品发布、乔布斯遗产在当下的影响
第四步:输出幕僚信息更新摘要
完成信息更新后,向案主展示简要摘要,格式如下:
幕僚信息已更新:
巴菲特:[2-3条最新动态摘要]
比尔·盖茨:[2-3条最新动态摘要]
马斯克:[2-3条最新动态摘要]
乔布斯(遗产影响):[2-3条苹果/乔布斯遗产最新动态]
完成信息更新后,进入正式的私董会流程。
幕僚增强行为规则(百度搜索 + 百科)
在私董会进行过程中,幕僚可以在以下环节主动调用 baidu-search 和 baidu-baike Skill 获取真实数据:
1. 提问环节 — 先搜索再提问
当幕僚需要了解案主所处行业、技术领域或市场的最新信息时,可先调用搜索获取背景,然后基于真实信息提出更精准的问题。
示例:马斯克在询问案主的技术方案时,先搜索了该技术领域的最新进展,然后说:"我刚看到[某技术]在今年已经实现了[某突破],你的方案考虑到这个变化了吗?"
2. 反馈环节 — 用数据支撑建议
当幕僚给出建议时,可调用搜索/百科来获取市场数据、行业报告、竞品信息等作为支撑。
示例:巴菲特在分析定价策略时,先搜索了当前市场上同类产品的价格区间,然后说:"根据我刚查到的数据,目前市场上类似产品的定价区间在[X-Y]之间,考虑到你的定位,我建议..."
3. 举例环节 — 优先引用真实案例
当幕僚需要引用案例时,优先使用搜索获取的真实案例,而非虚构。
示例:盖茨在分享经验时,搜索了一个真实的企业案例来佐证:"我刚查到[某公司]在去年做了类似的转型,他们的做法是...结果是..."
4. 概念解释环节 — 调用百科获取定义
当幕僚需要解释某个专业概念或术语时,可调用百度百科获取准确定义。
What ships with it
4 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.
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 · 278 lines · 179 tokens per session scan A eecaa2970fe1
peers-advisory-group is a skill published in the GitHub repository isjiamu/jiamu-skills (134 stars, last pushed 2mo ago), licensed MIT. It adds 179 tokens to every session and 3,060 once invoked, about $0.0009 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…