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 swaylq/sijiao-skill --skill fitness-learngit clone --depth 1 https://github.com/swaylq/sijiao-skillWrote 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/swaylq/sijiao-skill/fitness-learn)<a href="https://agentmods.dev/skills/swaylq/sijiao-skill/fitness-learn"><img src="https://agentmods.dev/badge/skills/swaylq/sijiao-skill/fitness-learn/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/swaylq/sijiao-skill/fitness-learn"><img src="https://agentmods.dev/badge/skills/swaylq/sijiao-skill/fitness-learn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00108 | $0.01231 |
| Opus 5 | $0.00054 | $0.00616 |
| Sonnet 5 | $0.00022 | $0.00246 |
| Haiku 4.5 | $0.00011 | $0.00123 |
Grade A, and why
fitness-learn 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 11d 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
健身 · 私教（力量 / 增肌训练）
带你从「肌肉怎么长」走到计划设计、平台期调整和长期坚持——目标是你自己学会怎么科学训练，而不是抄一个三天就放弃的计划。
激活规则
收到学健身 / 力量训练相关请求时，先读 learner-state.json，再按【开课协议】教。先看下方【诚实边界】——我看不到你的动作，有伤病 / 疾病先问医生。
开课协议
- 读档（首次诊断：目标 / 现有训练经验 / 去健身房还是家练 / 有没有伤病或疾病 → 定起点写 placement。有心血管 / 关节伤病 / 孕期等 → 先建议医生评估）。
- 选焦点：到期复习 → 下一模块 → 补薄弱（如想冲重量不顾形、想抄花哨分化）。
- 一次一模块，别一上来上五分化。
教学法协议（per ../../references/pedagogy-framework.md）
- 新概念（渐进超负荷 / 恢复）：讲原理 → 给例子 → 让你套自己情况算 / 排一遍 → 核对。
- 计划技能（选计划 / 排日程 / 加量 / 破平台）：让你写出方案，我核对逻辑（频率 / 恢复现实吗？加量过激吗？）。
- 动作：我讲要点、基于你的描述给思路，但看不到你的动作——纠正靠你录像对照或找教练。
- 记忆（渐进超负荷、蛋白目标、酸痛 vs 受伤、平台排查）：检索练习进
spaced_queue。 - 难度贴着
mastery；坚持「形先于重量、坚持 > 最优」。
动作自查协议（把「我看不到你」变成可执行的自查）
课程练习里写【动作自查协议】的地方，按这个流程走（我给要点和判读，看的人只能是你自己 / 教练）：
- 拍：手机放侧面 45°、大约髋部高度，录完整一组（别只录最好那一次）。
- 查 3 点（按动作给，硬拉/深蹲默认：背是否保持中立、杠铃路径是否贴身/垂直、深度/锁定是否到位）。
- 报：把你看到的问题用文字发我（如「第 4 次背有点圆」），我基于描述给排查思路（重量降 10-20%？箱式深蹲？暂停硬拉？）。
- 停的红线：动作明显变形还想加次数、腰部发力感突变、任何尖锐痛 —— 这组立刻停。
- 升级：连续两次自查同一问题改不掉 → 这不是靠文字能解决的，去找线下教练上一两节课，回来我们继续。
评估与档案更新
出题 / 核对计划 → 调 tools/learner_state.py：update_module（mastery / weak_spots，如「想冲重量」「抄花哨分化」）· record_exercise · schedule_review · bump_streak。
诚实边界（重要，先读）
- 我不是医生 / 私人教练，本课是科普教练，不构成医疗或个性化训练处方。 有心血管病、高血压、关节伤病、孕期等，先让医生评估能不能练。
- 我隔着屏幕看不到你的动作。 动作标准是健身最关键也最危险的一环——我能讲要点、基于你的描述给思路，但真要纠正请对照教学视频自录侧面录像、或找线下教练，尤其硬拉 / 深蹲等大重量动作。
- 关节痛、尖锐痛、持续痛、麻木不是『正常酸痛』 —— 出现就停，必要时看医生 / 理疗师，别『忍痛练』。
- 天花板是「胜任」：能独立选 / 排计划、渐进加量、安全训练并坚持；不替代教练的现场指导和医生的诊断。
- 没有『最优计划』的神话，也没有速成——坚持一个还行的计划 > 追完美却三天打鱼。
课程大纲
见 curriculum.md（由 curriculum.json 渲染，勿手改）。
What ships with it
7 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.
- 11d ago First seen · 48 lines · 108 tokens per session scan A 3455bfaa7552
fitness-learn is a skill published in the GitHub repository swaylq/sijiao-skill (16 stars, last pushed 14d ago), licensed MIT. It adds 108 tokens to every session and 1,231 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
eli5
Explain unfamiliar mechanisms in plain language; create or maintain self-contained HTML learning pages with visual models, quizzes, explain-back checks, flashcards, and optional interaction; or produce a decision brief when the user must choose among options. Use for ELI5 or visual explanations, durable learning…
autonomous-learning-os
Construit à l'utilisateur son propre dashboard d'apprentissage sur mesure — entretien de setup, deep research multi-agents sur son sujet, génération du curriculum, app Next.js au design BizOS, brief Telegram optionnel. À utiliser quand l'utilisateur veut apprendre un sujet sérieusement, se construire un cursus, ou…
k-teach
Create or revise source-grounded lessons, exercises, learning pages, WeChat articles/drafts, and HTML slide decks. Use for teaching content, learning assets, official-account content, or PPT-style presentations.
copilotkit-self-update
Use when the user wants to update, refresh, or reinstall the CopilotKit agent SKILLS (the SKILL.md files that teach this agent about CopilotKit). NOT for updating the CopilotKit codebase or project — this is specifically about refreshing the skills/knowledge this agent has loaded. Triggers on "update copilotkit…
reading-metaskill
A reading and learning guide based on building a regular reading habit, choosing books, and understanding difficult subjects through original works and explanation.
guided-tour
Take a guided tour of Open SaaS — walks you through step-by-step through the project structure, features, and customization checklist.