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/cita-777/hfut-awesome-marp-themenpx agentmods add skills/cita-777/hfut-awesome-marp-theme/hfut-marp-slidesWrote 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/cita-777/hfut-awesome-marp-theme/hfut-marp-slides)<a href="https://agentmods.dev/skills/cita-777/hfut-awesome-marp-theme/hfut-marp-slides"><img src="https://agentmods.dev/badge/skills/cita-777/hfut-awesome-marp-theme/hfut-marp-slides/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/cita-777/hfut-awesome-marp-theme/hfut-marp-slides"><img src="https://agentmods.dev/badge/skills/cita-777/hfut-awesome-marp-theme/hfut-marp-slides.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 | $0.00082 | $0.05869 |
| Opus 5 | $0.00041 | $0.02934 |
| Sonnet 5 | $0.00016 | $0.01174 |
| Haiku 4.5 | $0.00008 | $0.00587 |
Grade A, and why
hfut-marp-slides 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 12d 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 — 585 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HFUT Awesome Marp Slides
Overview
使用 HFUT Awesome Marp 主题快速创建专业的学术演示文稿。基于 Markdown 语法,支持多种布局、导航栏、代码高亮、数学公式等特性。
工程目录分析(Project-Aware Mode)
当用户的 PPT 工作目录中存在工程项目文件夹时,PPT 内容必须严格基于工程事实。
检测条件
生成 PPT 前,先扫描 PPT 工作目录(即用户指定的 ws_src/xxx/ 目录)下是否存在工程项目文件夹。识别标志:
| 标志文件 | 语言/框架 |
|---|---|
Cargo.toml |
Rust |
package.json |
Node.js / 前端 |
go.mod |
Go |
pom.xml / build.gradle |
Java |
CMakeLists.txt / Makefile |
C/C++ |
pyproject.toml / setup.py / requirements.txt |
Python |
*.sln / *.csproj |
C# / .NET |
如果检测到任何一个标志文件,立即进入 Project-Aware Mode。
Project-Aware Mode 工作流
检测到工程文件夹
↓
Step 1: 深度代码分析(必须先完成,再写任何 PPT 内容)
↓
Step 2: 建立事实清单(Fact Sheet)
↓
Step 3: 基于事实清单生成 PPT 内容
↓
Step 4: 逐页交叉验证
Step 1: 深度代码分析(强制)
在写任何一行 PPT 内容之前,必须完成以下分析:
-
读取项目元数据 —
Cargo.toml/package.json/go.mod等,提取:- 项目名称、版本、作者、描述
- 所有依赖及其版本号(直接依赖,非传递依赖)
- 构建配置、feature flags
-
读取所有源代码文件 — 逐个读取
src/、lib/、app/等目录下的每一个源文件,提取:- 模块结构和文件组织
- 核心数据结构(struct、class、interface 定义)
- API 端点 / 路由定义
- 关键算法和业务逻辑
- 错误处理方式
-
读取配置文件 —
config/、.env、*.yaml、*.toml等 -
读取测试文件 —
tests/、*_test.*、*.spec.* -
读取文档 —
README.md、docs/
硬性禁止:未读取的文件中的内容不得出现在 PPT 中。
Step 2: 建立事实清单
分析完成后,在生成 PPT 前必须先整理出事实清单(不写入文件,在生成过程中作为内部参照):
事实清单示例:
- 项目名:webserver
- 语言:Rust 2021 Edition
- 核心依赖:tokio 1.36.0, serde 1.0.197, flate2 1.0.28, brotli 3.5.0, ...
- 模块:main.rs, request.rs, response.rs, config.rs, cache.rs, param.rs, util.rs, exception.rs
- 支持的 HTTP 方法:GET, HEAD, OPTIONS(代码依据:param.rs 中 ALLOWED_METHODS)
- 压缩算法:Gzip, Deflate, Brotli(代码依据:response.rs 中 compress 逻辑)
- 缓存策略:FIFO(代码依据:cache.rs 中 FileCache 实现)
- ...
每一条事实必须标注代码依据(文件名 + 具体位置)。
Step 3: 严格事实约束规则
以下规则在 Project-Aware Mode 下为强制执行,违反任何一条都是不可接受的:
| 规则 | 说明 | 违反示例 |
|---|---|---|
| 禁止编造技术栈 | 所有技术栈必须来自依赖文件 | 项目没用 Redis 却写"使用 Redis 缓存" |
| 禁止编造功能 | 只写代码中实际实现的功能 | 代码没有 HTTPS 却写"支持 TLS 加密" |
| 禁止编造架构 | 架构描述必须与代码模块结构一致 | 代码是单体却写"微服务架构" |
| 禁止编造性能数据 | 性能数据必须来自项目文档/README | 没有 benchmark 却写"QPS 达到 10 万" |
| 禁止美化描述 | 不得将简单实现描述为复杂高级方案 | FIFO 缓存却写"智能缓存淘汰策略" |
| 代码展示必须真实 | PPT 中的代码片段必须从源码中提取精简 | 不得凭空编写"示例代码" |
| 禁止推测设计意图 | 只描述代码做了什么,不猜测为什么 | 不得写"考虑到高并发场景特别设计了..." |
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.
- 12d ago First seen · 585 lines · 82 tokens per session scan A 750eae2f8004
hfut-marp-slides is a skill published in the GitHub repository cita-777/hfut-awesome-marp-theme (26 stars, last pushed 7mo ago), licensed MIT. It adds 82 tokens to every session and 5,869 once invoked, about $0.0004 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
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.