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/wangyendt/wayne-skillsnpx agentmods add skills/wangyendt/wayne-skills/tutor-math-geometryWrote 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/wangyendt/wayne-skills/tutor-math-geometry)<a href="https://agentmods.dev/skills/wangyendt/wayne-skills/tutor-math-geometry"><img src="https://agentmods.dev/badge/skills/wangyendt/wayne-skills/tutor-math-geometry.svg" alt="Measured on agentmods" 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 | $0.00121 | $0.07278 |
| Opus 5 | $0.00060 | $0.03639 |
| Sonnet 5 | $0.00024 | $0.01456 |
| Haiku 4.5 | $0.00012 | $0.00728 |
Grade A, and why
tutor-math-geometry 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 7d 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.
This is a copy
91% identical to tutor — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 738 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tutor - 一对一辅导老师
核心工作流
WORKFLOW = [
# 步骤1: 数学建模
{
"step": 1,
"name": "analyze_problem",
"input": "题目图片/文本",
"output": "math_analysis.md",
"tasks": ["推导数学事实", "建立几何模型", "确定图形构建方法"]
},
# 步骤2: HTML可视化
{
"step": 2,
"name": "html_visualization",
"input": "math_analysis.md",
"output": "数学_{日期}_{题目}.html",
"tasks": ["SVG画图形", "展示画图过程", "标注关键要素"]
},
# 步骤3: 分镜脚本
{
"step": 3,
"name": "storyboard",
"input": "HTML内容",
"output": "{日期}_{题目}_分镜.md",
"tasks": ["定义幕结构(不限制幕数)", "设计画面/字幕/读白", "音频清单(时长留空)"]
},
# 步骤4: TTS生成
{
"step": 4,
"name": "generate_tts",
"input": "分镜脚本",
"output": "audio/audio_{三位幕号}_{幕名}.wav + audio_info.json",
"command": "python scripts/generate_tts.py audio_list.csv ./audio --voice xiaoxiao"
},
# 步骤5: 验证更新
{
"step": 5,
"name": "validate_audio",
"input": "分镜.md + audio/",
"output": "更新后的分镜.md(填充时长) + audio_info.json",
"command": "python scripts/validate_audio.py 分镜.md ./audio",
"check": ["音频存在性", "时长>0", "数量匹配"]
},
# 步骤6: 脚手架
{
"step": 6,
"name": "scaffold",
"input": "分镜.md + audio_info.json",
"output": "script.py (伪代码框架)",
"template": "templates/script_scaffold.py",
"must_include": [
"calculate_geometry() - 几何建模",
"assert_geometry() - 几何验证(题目条件+精度) + 画布范围检查(边界+中心)",
"COLORS - 颜色定义",
"SCENES[] - 幕信息数组(从audio_info.json加载时长)",
]
},
# 步骤7: 生成代码
{
"step": 7,
"name": "implement",
"input": "script.py脚手架 + 分镜.md + audio_info.json",
"output": "完整的script.py",
"rules": [
"根据分镜实现每幕动画",
"读白提到什么就高亮什么",
"画面时长 >= 音频时长",
"calculate_geometry()必须完整实现"
]
},
# 步骤8: 检查与渲染
{
"step": 8,
"name": "check_and_render",
"input": "script.py",
"output": "视频文件 + 关键帧截图",
"command": "python scripts/render.py",
"check": ["代码结构检查(check.py)", "几何正确性", "高亮同步", "字幕清晰", "动画流畅"],
"on_fail": "回到步骤7修改代码"
}
]
# 工作流状态转换
# step1 → step2 → step3 → step4 → step5 → step6 → step7 → step8
# ↑____________↓ (失败时循环)
What ships with it
19 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.
- init.py 6.8 KB runs code
- README.md 1.8 KB
- references/storyboard_sample.md 9.0 KB
- requirements.txt 216 B
- sample/geometry_proof/audio_list.txt 271 B
- sample/geometry_proof/generate_edge_tts.py 10 KB runs code
- sample/geometry_proof/README.md 4.0 KB
- sample/geometry_proof/render.sh 7.0 KB runs code
- sample/geometry_proof/requirements.txt 145 B
- sample/geometry_proof/scene.py 24 KB runs code
- sample/geometry_proof/storyboard.md 3.4 KB
- sample/geometry_proof/几何_20260218_四点共圆证明_分镜.md 8.1 KB
- scripts/audio_list.example.csv 476 B
- scripts/check.py 8.4 KB runs code
- scripts/generate_tts.py 7.8 KB runs code
- scripts/render.py 7.4 KB runs code
- scripts/validate_audio.py 9.4 KB runs code
- templates/script_example.py 16 KB runs code
- templates/script_scaffold.py 13 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.
- 7d ago First seen · 738 lines · 121 tokens per session scan A 78396d2c4d3c
tutor-math-geometry is a skill published in the GitHub repository wangyendt/wayne-skills (8 stars, last pushed 11d ago), licensed MIT. It adds 121 tokens to every session and 7,278 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to tutor, differing in 3 lines, and is treated as a copy.
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.