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-returngit 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-return)<a href="https://agentmods.dev/skills/lzheng0411/lzheng-fitness/lzheng-training-return"><img src="https://agentmods.dev/badge/skills/lzheng0411/lzheng-fitness/lzheng-training-return/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-return"><img src="https://agentmods.dev/badge/skills/lzheng0411/lzheng-fitness/lzheng-training-return.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 | $0.00152 | $0.02324 |
| Opus 5.5 | $0.00061 | $0.00930 |
| Sonnet 5.5 | $0.00030 | $0.00465 |
| Haiku 4.5 | $0.00015 | $0.00232 |
Grade A, and why
lzheng-training-return 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 6d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lzheng 训练中断恢复
主动同步个人工作台(每轮必须检查)
用户提供或更正个人信息、确认训练计划、补充实际训练或体感后,同轮将已知内容写入其对应主源,并主动运行工作台 refresh-workbench,检查正式 HTML 成功后再交付。不要等待用户再次说“刷新”,不要只写计划/交接文件就结束。没有待处理交接不代表页面已更新;必要时直接运行刷新闭环。
个人资料、训练计划与动作负荷校准分别判断。已经提供真实计划时立即展示,不能因体重、训练经验、部分重量或其他非阻断字段未知而把整套系统继续显示为“待建档”。未知字段分别标“待填写”“待校准”或留空,已知信息与处方照常展示;缺失且会影响训练执行的信息只限制对应执行建议,不隐藏其他已知资料。过程中每次取得新事实继续增量刷新,不补造数据、不自动改正式计划、不部署网站、不建立后台监听。刷新失败则说明具体缺口并继续修复,不能报告已更新。
共同训练判断协议
处理训练数据、RPE、下一次调整、计划渐进或失败反馈时,先读 训练数据判断与渐进协议。它统一力量、增肌、减脂保肌三类目标,允许有理由的多变量联合调整;优先于旧参考中的固定单变量和机械重复规则,不覆盖本 Skill 的数据读取、正式记录及计划写入权限。未知 RPE、体感或休息不抹掉已完成组;先给能确定的分析,影响具体决定的未知再轻量核实,不循环追问用户已表示不记得的内容。
维护内置 AI 或训练 Skill 的共同决策规则时,执行该协议末尾的联动维护检查,不仅更新一端。
目标
把“中断了,不知道怎么回来”变成一条安全、低阻力、能在 48 小时内启动的接回路径。先判断是否适合恢复,再依据当前事实调整原计划;不把恢复期做成惩罚性补课,也不重写与中断无关的长期目标。
使用边界
满足任一条件时使用本 Skill:
- 停训达到 7 天;
- 连续漏练 3 次;
- 生病后恢复,或伤病已经过适当评估并获准恢复;
- 训练场地、器械、时间或身体能力明显变化;
- 4 周内反复中断;
- 用户主动询问中断恢复或重新开始训练。
以下情况不在本 Skill 内直接安排普通训练:
- 胸痛、晕厥、异常气短等需要医疗评估的症状;
- 疼痛加重、麻木、明显功能受限或尚未明确能否恢复运动;
- 急性发热、全身症状仍在持续;
- 用户无法确认关键安全信息。
漏练 1 次不补课,按原顺序继续。漏练 2 次由主 Skill 生成 30 分钟或状态差版,完成后接回原计划。
必读资料
开始诊断前完整读取:
references/knowledge-routing.mdreferences/return-workflow.mdreferences/return-card-spec.mdreferences/evidence-base.md../lzheng-training-expert-library/references/expert-selection-contract.md(仅在独立专家变量会改变接回路径时)
再按知识路由读取与当前情况相关的内置资料;容易变化的恢复安全标准应联网核验官方来源。不得仅凭模型记忆作出处方。
目标含糊、反复中断或“回到基础”是关键变量时可读取 Dan John;只有用户已经获得合格专业人员评估并允许活动,且问题是功能进阶、返场验证或二级预防时才读取 Brukner 与 Khan。未评估疼痛、急性创伤、术后未获许可、疾病或红旗症状先走安全分流,不进入专家讨论。专家不能批准恢复训练,也不能覆盖医疗限制、当前事实和本 Skill 的最终接回决定。
工作流
1. 读取当前执行基准
优先收集:
- 最近一份带时间戳的状态快照;
- 中断前正在执行的计划及最近完成训练;
- 本次用户确认的动态事实;
- 用户授权且当前环境可访问时,读取外部训练记录服务中的当前记录、日记和恢复状态;
- 中断前后的器械、时间和生活条件变化。
找不到原计划时明确标记 unknown,不得虚构原重量、频率或动作。必要时输出保守的重新评估周,而不是假装“接回原计划”。
2. 做最小恢复问诊
至少确认:
- 最后一次训练日期和中断时长;
- 中断原因与过去 4 周的反复情况;
- 当前症状、疼痛、活动受限及医疗建议;
- 睡眠、压力、食欲、主观精力;
- 当前可训练时间、场地与器械;
- 中断前计划、主要动作及可复现重量;
- 用户现在最愿意完成的最小训练任务。
把信息分为 confirmed、inferred、unknown,生成新的不可覆盖时间快照。不得覆盖中断前快照。
What ships with it
6 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.
- 6d ago Changed · +18 lines a255226a8100
- 2mo ago First seen · 131 lines · 152 tokens per session scan A fb085a3c5237
lzheng-training-return is a skill published in the GitHub repository LZheng0411/Lzheng-fitness (140 stars, last pushed 6d ago), licensed MIT. It adds 152 tokens to every session and 2,324 once invoked, about $0.0006 per session on Opus 5.5. 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.
lzheng-training-return compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| lzheng-training-returnLZheng0411/Lzheng-fitness | Skill | 140 | 6d ago | MIT | A | 152 | Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |