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 LZheng0411/Lzheng-fitness --skill lzheng-training-systemgit clone --depth 1 https://github.com/LZheng0411/Lzheng-fitnessWrote 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-system)<a href="https://agentmods.dev/skills/lzheng0411/lzheng-fitness/lzheng-training-system"><img src="https://agentmods.dev/badge/skills/lzheng0411/lzheng-fitness/lzheng-training-system/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-system"><img src="https://agentmods.dev/badge/skills/lzheng0411/lzheng-fitness/lzheng-training-system.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 | $0.00121 | $0.02293 |
| Opus 5 | $0.00060 | $0.01146 |
| Sonnet 5 | $0.00024 | $0.00459 |
| Haiku 4.5 | $0.00012 | $0.00229 |
Grade A, and why
lzheng-training-system 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 yesterday.
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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lzheng 本地训练系统
把本 Skill 当作套件总控层：它只做安装、配置、路由、升级保护和验收；训练处方由四个训练处方 Skill 生成，营养系统独立维护 nutrition_contract，专家库只作为共享知识层，工作台只负责展示。
首次使用者引导
当用户刚完成安装、刚下载本套件，或第一次说“开始”“想增肌/减脂/提升力量”“帮我建立健身系统”时，不要要求用户先阅读 README、输入命令或记住 Skill 名称。直接回复：
我来帮你建立个人健身系统。先确定你的主要目标：增肌、减脂、力量，还是综合改善？
随后依次完成：
- 询问目标、近期训练、时间、器械、恢复、限制和可用记录；
- 没有可靠动作重量时安排负荷校准，不让用户自行猜重量；
- 初始化新的空目录、工作台和事实文件；
- 生成第一版正式计划，将它接入当前周期、执行基准、复盘索引和工作台；
- 告诉用户以后只需说“今天练了什么”和主观体感，AI 负责下一次明确处方与刷新。
若当前聊天尚未加载新 Skill，提示用户只需新开对话后说“开始建立我的健身系统”；不得让用户阅读 README 寻找下一步。
先选动作
| 用户意图 | 动作 |
|---|---|
| 新电脑、空文件夹、从零搭建 | bootstrap |
| 检查路径、数据主源、Skill、工作台或链接 | doctor |
| 日常任务读取当前状态，不加载整份工作台 HTML | inspect |
| 升级系统配置并检查界面状态 | upgrade（仅配置；需要界面升级时退出码 2） |
| 修复侧栏或升级已有工作台界面，保留事实和壁纸 | upgrade-workbench-ui |
| 只装/检查某个专业 Skill | install-skill |
| 导入用户自己的知识、书摘或资料包 | import-private-pack |
| 刷新正式工作台并生成可审计回执，可选准备本地发布副本 | refresh-workbench |
| 消费正式计划、复盘或接回后的交接并刷新工作台 | process-handoffs |
| 升级后或发布前做完整回归 | validate |
| 日常训练任务 | 按下方路由转交专业 Skill |
运行前读取 系统契约。涉及交接时读取 交接契约。涉及完整计划、力量周期或工作台 HTML 时读取 单文件 HTML 模板总契约，只允许使用其中登记的三套固定模板。
日常计划修改、训练复盘和状态确认先运行 inspect。--root 可指向含 系统/lzheng-system.json 的完整系统根目录，也可直接指向含 健身工作台.html 的训练项目根目录。它只输出紧凑状态和权威主源路径；随后按任务读取对应的一个计划、基准或复盘文件。除非正在开发视觉模板或检查器已经报告模板结构损坏，不得读取整份 健身工作台.html、工作台模板、历史计划目录或全部专家模块。
日常路由
- 完整建档、长期训练计划、短版降级：
lzheng-fitness-plan。 - 一个动作的 8—12 周力量周期：
lzheng-strength-cycle-planner；结果必须交回完整计划 Skill 合并后才可成为当前计划。 - 单练或周训练复盘、下一次处方：
lzheng-strength-training-review；正式复盘必须更新索引并触发工作台刷新。 - 停训 7 天、连续漏练 3 次、条件明显变化：
lzheng-training-return；改变执行状态时先更新执行基准或当前计划，再刷新工作台。 - 饮食建档、日型目标、餐食确认与两周趋势复盘：
lzheng-nutrition-system；它不按单次训练消耗补吃，也不自动确认照片估算。 - 工作台构建、数据刷新、迁移、发布：
lzheng-fitness-workbench-builder；它只读聚合，不给出处方。
四个训练处方 Skill 与营养 Skill 在需要来源限定判断时内部读取 lzheng-training-expert-library。专家库不是独立处方入口，不拥有当前事实、计划版本、营养协议或工作台写入权。
专业 Skill 执行前按以下优先级解析根目录：本次用户明确路径 → 系统/lzheng-system.json → 环境变量 LZHENG_FITNESS_HOME → 仅用于首次引导的保守默认目录。已存在系统配置时，计划、周期、复盘、状态和接回卡必须优先写入 output_locations 指定的知识库分区，不得继续散落到当前工作目录。未解析到系统时停止写入并说明缺失项，不把示例数据当作训练事实。
What ships with it
10 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 344 B
- assets/knowledge-pack-manifest.schema.json 365 B
- references/handoff-schema.md 2.8 KB
- references/html-template-contract.md 2.5 KB
- references/system-contract.md 3.6 KB
- scripts/lzheng_training_system.py 22 KB runs code
- scripts/Process-LzhengHandoffs.py 9.8 KB runs code
- scripts/Test-LzhengTrainingSystemInspectReadOnly.py 2.9 KB runs code
- scripts/Test-LzhengTrainingSystemPortability.py 3.4 KB runs code
- scripts/validate_ui_contract.py 5.2 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.
- yesterday Changed · +6 lines 5acf5b27c383
- 7d ago Changed · +3 lines 3c4c9042edf8
- 8d ago Changed · +13 lines 760dc3ac6b42
- 12d ago First seen · 76 lines · 121 tokens per session scan A c8898f688bb7
lzheng-training-system is a skill published in the GitHub repository LZheng0411/Lzheng-fitness (65 stars, last pushed 2d ago), licensed MIT. It adds 121 tokens to every session and 2,293 once invoked, about $0.0006 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…