Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/LZheng0411/Lzheng-fitnessnpx agentmods add skills/lzheng0411/lzheng-fitness/lzheng-training-expert-libraryWrote 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/lzheng0411/lzheng-fitness/lzheng-training-expert-library)<a href="https://agentmods.dev/skills/lzheng0411/lzheng-fitness/lzheng-training-expert-library"><img src="https://agentmods.dev/badge/skills/lzheng0411/lzheng-fitness/lzheng-training-expert-library/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/lzheng0411/lzheng-fitness/lzheng-training-expert-library"><img src="https://agentmods.dev/badge/skills/lzheng0411/lzheng-fitness/lzheng-training-expert-library.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 | $0.00099 | $0.00717 |
| Opus 5 | $0.00049 | $0.00358 |
| Sonnet 5 | $0.00020 | $0.00143 |
| Haiku 4.5 | $0.00010 | $0.00072 |
Grade A, and why
lzheng-training-expert-library 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 12d 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.
What it actually says
Lzheng 训练专家知识库
这是 Lzheng 健身套件的内部知识层。它让主 Skill 能读取完整蒸馏模块，而不是只依赖一页通用摘要。
使用顺序
- 先读 专家选择协议，把问题拆成会改变结论的变量。
- 再读 专家登记表，选择最少必要专家；通常 1 位，只有独立变量或真实冲突才增加。
- 进入
references/experts/<expert-id>/，先读module.json和入口文件，再按模块内部路由读取知识卡、框架或边界。 - 只把来源限定判断交给计划、周期、复盘或接回 Skill；当前事实、最终处方、写入和安全分流仍归主 Skill。
- 实际采用专家时按 输出协议 展示；没有采用时不增加专家区块。
六个模块
- Alan Aragon：营养、宏量、补给、依从性和维持。
- Brad Schoenfeld：肌肥大机制、训练变量和增长测量。
- Brukner 与 Khan：仅在已获专业允许活动后处理保守康复进阶、返场验证和二级预防。
- Dan John：Point A、训练缺口、回到基础和低疲劳重复。
- Eric Helms：依从性、训练结构、渐进、减载和峰值。
- Greg Nuckols：力量瓶颈、专项性、变量实验、周期化和技术假设。
每个模块都包含版本边界和验证状态。content_ready_entry_acceptance_pending 表示内容、结构和路由已可审计，但真实主入口验收仍待完成；不得改写成“已全面验证”。
安全与版权边界
- 不复制或输出整本书、原始 PDF/EPUB、文章快照或大段原文。
- 不模拟专家本人，不声称代表其最新观点。
- 不用旧版书替代当前医疗指南、专业评估或公共安全标准。
- 疼痛、急性创伤、胸部不适、晕厥、异常气短、进行性神经症状、术后或疾病先走安全分流。
- 专家模块无权覆盖用户当次确认、当前计划、执行基准或动态记录。
验证
修改模块、登记表或选择协议后运行：
python scripts/validate_expert_library.py
只有结构、隐私、链接、路由样例和状态一致性全部通过，才能声明公开专家库可安装、可访问。
What ships with it
60 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.
- agents/openai.yaml 363 B
- references/expert-output-protocol.md 515 B
- references/expert-registry.json 4.7 KB
- references/expert-selection-contract.md 1.9 KB
- references/experts/alan-aragon-flexible-dieting/00-专家总入口.md 1.6 KB
- references/experts/alan-aragon-flexible-dieting/00-立项与来源核验.md 1.4 KB
- references/experts/alan-aragon-flexible-dieting/01-全书覆盖矩阵.md 1.7 KB
- references/experts/alan-aragon-flexible-dieting/02-营养决策框架.md 1.5 KB
- references/experts/alan-aragon-flexible-dieting/03-边界与冲突处理.md 1.1 KB
- references/experts/alan-aragon-flexible-dieting/04-问题路由表.md 2.2 KB
- references/experts/alan-aragon-flexible-dieting/05-主系统接入参考.md 1.4 KB
- references/experts/alan-aragon-flexible-dieting/06-测试与遗漏审计.md 1.7 KB
- references/experts/alan-aragon-flexible-dieting/module.json 624 B
- references/experts/alan-aragon-flexible-dieting/PUBLIC-SOURCE-BOUNDARY.md 650 B
- references/experts/alan-aragon-flexible-dieting/知识卡/01-灵活控制不是放任.md 1.0 KB
- references/experts/alan-aragon-flexible-dieting/知识卡/02-先校验证据再调整饮食.md 1.1 KB
- references/experts/alan-aragon-flexible-dieting/知识卡/03-蛋白质先看全天总量.md 1.1 KB
- references/experts/alan-aragon-flexible-dieting/知识卡/04-碳水按训练需求与偏好分配.md 1.1 KB
- references/experts/alan-aragon-flexible-dieting/知识卡/05-脂肪满足健康与可持续底线.md 1.0 KB
- references/experts/alan-aragon-flexible-dieting/知识卡/06-补剂只做小幅性能优化.md 1.0 KB
- references/experts/alan-aragon-flexible-dieting/知识卡/07-从目标到热量与宏量.md 1.2 KB
- references/experts/alan-aragon-flexible-dieting/知识卡/08-依从性是饮食方案的硬约束.md 959 B
- references/experts/alan-aragon-flexible-dieting/知识卡/09-维持与退出追踪也是能力.md 1.1 KB
- references/experts/brad-schoenfeld-hypertrophy/00-专家总入口.md 1.6 KB
- references/experts/brad-schoenfeld-hypertrophy/00-立项与来源核验.md 5.0 KB
- references/experts/brad-schoenfeld-hypertrophy/01-全书覆盖矩阵.md 1.6 KB
- references/experts/brad-schoenfeld-hypertrophy/03-跨章决策与边界.md 2.0 KB
- references/experts/brad-schoenfeld-hypertrophy/04-问题路由表.md 2.2 KB
- references/experts/brad-schoenfeld-hypertrophy/05-主系统接入参考.md 1.8 KB
- references/experts/brad-schoenfeld-hypertrophy/06-测试与遗漏审计.md 1.5 KB
- references/experts/brad-schoenfeld-hypertrophy/module.json 666 B
- references/experts/brad-schoenfeld-hypertrophy/PUBLIC-SOURCE-BOUNDARY.md 693 B
- references/experts/brad-schoenfeld-hypertrophy/知识卡/01-训练应激与适应.md 1.9 KB
- references/experts/brad-schoenfeld-hypertrophy/知识卡/02-肌肥大机制与损伤边界.md 2.1 KB
- references/experts/brad-schoenfeld-hypertrophy/知识卡/03-如何测量真实肌肉增长.md 1.8 KB
- references/experts/brad-schoenfeld-hypertrophy/知识卡/04-训练变量的增肌取舍.md 2.7 KB
- references/experts/brad-schoenfeld-hypertrophy/知识卡/05-高级方法的成本收益.md 1.9 KB
- references/experts/brad-schoenfeld-hypertrophy/知识卡/06-有氧与增肌并行.md 2.0 KB
- references/experts/brad-schoenfeld-hypertrophy/知识卡/07-个体差异与可控变量.md 1.9 KB
- references/experts/brad-schoenfeld-hypertrophy/知识卡/08-最大化增肌的计划设计.md 2.1 KB
- references/experts/brad-schoenfeld-hypertrophy/知识卡/09-增肌营养的优先级.md 2.2 KB
- references/experts/brukner-khan-return-to-sport/00-专家总入口.md 2.1 KB
- references/experts/brukner-khan-return-to-sport/00-立项与来源核验.md 3.0 KB
- references/experts/brukner-khan-return-to-sport/01-全书覆盖矩阵.md 8.7 KB
- references/experts/brukner-khan-return-to-sport/02-康复与返场判断框架.md 2.4 KB
- references/experts/brukner-khan-return-to-sport/03-边界与冲突处理.md 1.5 KB
- references/experts/brukner-khan-return-to-sport/04-问题路由表.md 2.7 KB
- references/experts/brukner-khan-return-to-sport/05-主系统接入参考.md 1.4 KB
- references/experts/brukner-khan-return-to-sport/06-测试与遗漏审计.md 2.0 KB
- references/experts/brukner-khan-return-to-sport/module.json 699 B
- references/experts/brukner-khan-return-to-sport/PUBLIC-SOURCE-BOUNDARY.md 720 B
- references/experts/brukner-khan-return-to-sport/知识卡/01-疼痛不是可自行诊断的伤病标签.md 1.2 KB
- references/experts/brukner-khan-return-to-sport/知识卡/02-急性与过度使用伤病的负荷逻辑.md 1.2 KB
- references/experts/brukner-khan-return-to-sport/知识卡/03-康复从功能缺口而不是固定天数开始.md 1.2 KB
- references/experts/brukner-khan-return-to-sport/知识卡/04-返场必须通过逐级功能验证.md 1.2 KB
- references/experts/brukner-khan-return-to-sport/知识卡/05-区域症状只能指导提问不能自我确诊.md 1.2 KB
- references/experts/brukner-khan-return-to-sport/知识卡/06-特殊人群与医学症状先提高安全门槛.md 1.2 KB
- references/experts/brukner-khan-return-to-sport/知识卡/07-长期症状要重建问题而非不断加码治疗.md 1.2 KB
- references/experts/brukner-khan-return-to-sport/知识卡/08-二级预防把训练负荷恢复与沟通接起来.md 1.1 KB
- references/experts/dan-john-intervention-easy-strength/00-专家总入口.md 2.5 KB
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.
- 12d ago First seen · 46 lines · 99 tokens per session scan A d27b206f0b62
lzheng-training-expert-library is a skill published in the GitHub repository LZheng0411/Lzheng-fitness (65 stars, last pushed 2d ago), licensed MIT. It adds 99 tokens to every session and 717 once invoked, about $0.0005 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.