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 agentmods add skills/gzleeon/claude-train-prep/train_prepnpx skills add gzleeon/claude-train-prep --skill train_prepgit clone --depth 1 https://github.com/gzleeon/claude-train-prepWrote 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/gzleeon/claude-train-prep/train_prep)<a href="https://agentmods.dev/skills/gzleeon/claude-train-prep/train_prep"><img src="https://agentmods.dev/badge/skills/gzleeon/claude-train-prep/train_prep.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 | $0.00097 | $0.02048 |
| Opus 5 | $0.00048 | $0.01024 |
| Sonnet 5 | $0.00019 | $0.00410 |
| Haiku 4.5 | $0.00010 | $0.00205 |
Grade B, and why
Train_Prep scanned grade B with 1 finding 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 4d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
Linux:`sudo apt-get install poppler-utils pandoc` How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Train_Prep:AI 赋能行业培训材料制作工作流
技能概述
Train_Prep 封装了一套完整的 AI 咨询培训材料制作流程,从行业痛点调研到最终交付,涵盖:
- 多 Agent 并行调研(行业痛点 × AI 解决方案匹配)
- Word 方案报告生成(Markdown → pandoc → .docx)
- 交互式 HTML 培训幻灯片(多 Agent 并行开发 → 组装)
适用场景:为客户/行业高管准备 AI 赋能解决方案培训,需要同时输出 Word 报告和 HTML 演示材料。
快速启动检查
执行以下检查,确认环境就绪:
which pdftotext # poppler,PDF 文本提取
which pandoc # Markdown → Word 转换
若缺失(macOS):brew install poppler pandoc
Linux:sudo apt-get install poppler-utils pandoc
工作流总览(三阶段)
阶段一:研究调研(多 Agent 并行)
├── PDF 参考资料提取(pdftotext)
├── Agent A:第一业务阶段痛点调研
├── Agent B:第二业务阶段痛点调研
└── Agent C:第三业务阶段痛点调研 + 落地计划
阶段二:Word 报告
├── 组装 Markdown 章节
├── pandoc 转换为 .docx
└── 用户确认质量
阶段三:HTML 交互培训材料(多 Agent 并行)
├── Agent A:HTML 框架 + CSS + JS + 封面/目录幻灯片
├── Agent B:第一业务阶段幻灯片
├── Agent C:第二业务阶段幻灯片
├── Agent D:第三业务阶段 + 落地计划 + 结束幻灯片
└── 主进程:macOS 兼容组装脚本
阶段一:多 Agent 并行研究
第 1 步:提取 PDF 参考资料
将客户行业资料和己方能力介绍 PDF 转为文本:
pdftotext "己方能力介绍.pdf" /tmp/capability.txt
pdftotext "解决方案案例.pdf" /tmp/solutions.txt
注意:优先使用 pdftotext 而非 Read 工具读取 PDF,稳定性更好。
第 2 步:规划业务阶段分工
根据行业特点,将客户业务划分为 3 个阶段(每个 Agent 负责一个),示例:
| 行业 | Agent A | Agent B | Agent C |
|---|---|---|---|
| 轨道交通 | 建设阶段 | 运维阶段 | 运营阶段 |
| 制造业 | 研发设计 | 生产制造 | 供应链/销售 |
| 医疗 | 临床诊断 | 医院运营 | 患者服务 |
| 政务 | 政策制定 | 行政审批 | 公共服务 |
第 3 步:并行启动 3 个研究 Agent
在同一条消息中同时发送 3 个 Agent 调用(最大化并行度),每个 Agent 收到:
- 行业背景和客户信息
- 己方 AI 能力描述(/tmp/capability.txt 内容)
- 该阶段的调研范围
每个痛点的输出格式要求:
## 痛点 N:[名称]
**现状**:[当前存在的问题和挑战]
**AI 解决方案**:[具体方案组件列表]
**预期价值**:效率提升 X%,节省 Y 人力/年
**对应产品/技术**:[匹配的 AI 产品或技术栈]
中间文件约定(可自定义):
/tmp/train_phase1.md- 第一阶段/tmp/train_phase2.md- 第二阶段/tmp/train_phase3.md- 第三阶段(含落地计划)
阶段二:Word 报告生成
组装 Markdown 报告
撰写执行摘要和己方能力介绍,然后组装:
cat /tmp/train_header.md \
/tmp/train_phase1.md \
/tmp/train_phase2.md \
/tmp/train_phase3.md \
> /tmp/train_report.md
报告结构:执行摘要 → 己方能力介绍 → 各阶段方案 → 落地建议计划
What ships with it
1 file 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.
- 4d ago First seen · 210 lines · 97 tokens per session scan B 32013df0cd49
Train_Prep is a skill published in the GitHub repository gzleeon/claude-train-prep (2 stars, last pushed 5mo ago), licensed MIT. It adds 97 tokens to every session and 2,048 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
stage-dsl
The map for reading and editing an OpenMAIC stage document with readstage, patchstage, and grepstage. Load it before patching a structure you have not patched before, when patchstage rejects an operation, or whenever the path from a stage, outline, scene, content object, or action to the field you need is uncertain.…
pptx-import
会话里有上传的 .pptx,且用户要把这份幻灯片填进一节已建的课(先 createstage 建课,再 importpptx 把页面追加进这节课堂,保留原版排版;课堂标题以 createstage 为准,PPT 不接管)。随后逐页检查(有 renderscenepreview 就渲染看)并修 bad case,理解整课之后才写旁白/spotlight,最后 TTS。仅在用户要求时插入 quiz 或 interactive。不要重新规划整课。.
dev-camp-deck
Creates a professional PowerPoint presentation about a Copilot Dev Camp lab or topic. Researches Microsoft Learn documentation, organizes content into a slide structure, and generates a polished deck with speaker notes. Use when user asks to "create a presentation on", "make a deck about", "build a slideshow for"…
read-book
When you want to read and extract structured notes from a book — PDF, EPUB, MOBI, markdown, .txt, pasted text, or URL to a public-domain work. Reads in chunks (by chapter when a TOC exists, by 50-page blocks otherwise), extracts per-chapter TL;DR + key concepts + quotes + action items + frameworks, and offers to…
achievement-qztc
课程目标达成情况分析表生成工具。根据Excel学生数据替换Word模板中的课程目标达成情况,生成新的分析表。.
training-report
Produce a professional training/workshop report as a .docx file. Use this skill whenever the user mentions "training report", "workshop report", "compte rendu", "compte rendu de formation", "formation report", "debriefing a workshop", "write up a training session", "résumé de formation", or any request to document a…