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 ssmurfgg04-gif/context-m --skill cheat-sheetgit clone --depth 1 https://github.com/ssmurfgg04-gif/context-mWrote 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/ssmurfgg04-gif/context-m/cheat-sheet)<a href="https://agentmods.dev/skills/ssmurfgg04-gif/context-m/cheat-sheet"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/cheat-sheet/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/ssmurfgg04-gif/context-m/cheat-sheet"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/cheat-sheet.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 | $0.00127 | $0.01766 |
| Opus 5 | $0.00063 | $0.00883 |
| Sonnet 5 | $0.00025 | $0.00353 |
| Haiku 4.5 | $0.00013 | $0.00177 |
Grade A, and why
cheat-sheet scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cheatsheet 生成器
你做什么
把用户的学习资料(PDF/Word/Markdown/文本)压缩成一份双栏、小字、信息密度高的 Cheatsheet 文档(PDF 格式)。
核心原则:只保留干货,砍掉废话。
⚠️ 铁律:避免重复创建
生成 Cheatsheet 前,先扫描输出目录检查是否已有同主题文件:
- 已存在 → 问用户"已经有一份 [文件名] 了,覆盖 / 新建一份 / 跳过?" 等用户回复再动手
- 不存在 → 直接生成
- 绝不未经询问直接覆盖
工作流程
步骤 1:接收资料
用户提供学习资料文件,支持格式:
.pdf— 调 PDF skill 的 process 路线提取文本.docx— 调 PDF skill 的 process 路线提取文本.md/.txt— 直接读取
提取文本命令:
# PDF 提取文本
python3 "$PDF_SCRIPTS/pdf.py" extract.text <file_path>
# Word 转 PDF 后提取(如需要)
python3 "$PDF_SCRIPTS/pdf.py" convert.office <file_path>
其中 $PDF_SCRIPTS 为 PDF skill 的 scripts 目录路径,需从 PDF skill 的 SKILL.md 位置推导。
如果用户没有提供文件而是直接贴了文本内容,跳过提取步骤,直接用文本。
步骤 2:选择风格
必须询问用户想要哪种风格(不要自己替用户选):
向用户展示以下选项:
- 📋 知识点速查卡 — 核心概念 + 定义 + 关键公式/要点,一眼扫到,适合考前突击
- 🌳 思维导图式 — 按层级结构组织(大标题→子标题→要点),有大纲感,适合梳理体系
- ❓ Q&A 式 — 把知识点变成"问题→答案"对,适合自测复习
用户选择后进入步骤 3。
步骤 3:LLM 提炼内容
根据用户选择的风格,构建不同的 prompt 让 LLM 从原文中提炼 cheatsheet 内容。
风格 1:知识点速查卡
提炼规则:
- 提取所有核心概念、定义、公式、关键数据
- 每个知识点用 术语:一句话解释 的格式
- 相关知识点分组,每组有小标题
- 重要公式/代码片段原样保留
- 砍掉所有举例、过渡句、背景铺垫
输出结构:
## [分组标题]
- **术语A**:一句话定义
- **术语B**:一句话定义
- 📐 公式:`公式内容`
## [分组标题]
...
风格 2:思维导图式
提炼规则:
- 提取文档的层级结构(章→节→要点)
- 每个节点用最简短的语言概括
- 最多 3 级深度(再深就塞不进一页了)
- 用缩进和符号表达层级关系
输出结构:
# 主题
## 一级分支
├─ 二级要点
│ ├─ 细节 1
│ └─ 细节 2
└─ 二级要点
└─ 细节
风格 3:Q&A 式
提炼规则:
- 把每个知识点转化成一个问题
- 答案控制在 1-3 句话
- 问题从基础到进阶排列
- 易混淆的概念出辨析题
输出结构:
## [主题分组]
**Q:什么是 XXX?**
A:一句话回答。
**Q:XXX 和 YYY 的区别?**
A:简短对比。
步骤 4:用户确认与调整
LLM 生成内容后,先以文本形式展示给用户,询问:
"内容整理好了,你看看有没有要调整的?比如:
- 某些部分要加重点标记?
- 某些内容要删掉或补充?
- 排版上有什么偏好?(比如字号再小一点、分区颜色区分等)"
用户确认"可以"后,进入步骤 5。 用户提出修改 → 调整内容 → 再次展示 → 等待确认。
步骤 5:生成 PDF
调用 PDF skill 的 Report 路线(ReportLab) 生成双栏 PDF。
排版规格(默认值):
| 参数 | 默认值 | 说明 |
|---|---|---|
| 页面大小 | A4 | 可按用户要求调整 |
| 栏数 | 双栏 | 默认双栏,用户可选单栏 |
| 正文字号 | 8pt | 信息密度优先,可按用户要求调整 |
| 标题字号 | 10pt(一级)/ 9pt(二级) | |
| 行距 | 1.2 | 紧凑但可读 |
| 页边距 | 上下左右各 12mm | 最大化内容区域 |
| 字体 | 中文用 UniSong/UniHei,英文用 Helvetica |
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.
- 10d ago First seen · 211 lines · 127 tokens per session scan A a95fa566ae4e
cheat-sheet is a skill published in the GitHub repository ssmurfgg04-gif/context-m (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 127 tokens to every session and 1,766 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 2026-08-31.
Other skills, from other repositories
prospect
Run a structured pre-mortem on a plan or approach BEFORE execution. Per-step risk enforcement, active evidence-sourcing pass (autonomous lookups + targeted user-asks for anything that could become objective), simpler-alternative discipline, plan-formation diagnosis, action verdicts (PROCEED/SHRINK/SPLIT/DEFER/KILL)…
pptx
A guide for turning a paper, outline, or structured text into a PowerPoint presentation. It covers an 8–12-slide structure, concise slide points, and generation of a .pptx file.
pptx-import
A method for adding an uploaded PowerPoint presentation to an existing classroom as extra pages while keeping the slides' original layout. PowerPoint is Microsoft's presentation file format.
ov-add-paper
Load when the user asks to add, import, compile, or ingest a research paper/PDF into OpenViking, especially when they mention ov-add-paper, ARA, claims, evidence, figures, tables, or paper-to-OV knowledge resources.
ocr-document
Extract text from PDFs, images, and scanned documents. Uses pymupdf (local) or optional cloud OCR APIs.
liteparse
Parse documents into LLM-ready content entirely on the local machine — PDF / DOCX / XLSX / PPTX / images → Markdown, structured JSON (with bounding boxes), or page screenshots, via the lit CLI. No cloud, no LLM, works offline. Use whenever the user attaches or points to a document that must be read before reasoning…