Menu

Not in the top 1,000 by GitHub stars

daxueren666/exam-review-helper

把 PDF/Word/TXT/Markdown 教材浓缩成交互式 HTML 复习文档的 Claude Code / Codex CLI Skill。自动识别文科/理工科模式，5-pass 深度提取，原生支持扫描版 PDF OCR。v1.2 用 pdfium 后端修复 docling std::bad_alloc 崩溃，大 PDF 稳定提取。

Engineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

skills/exam-review-helper/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

c490eba3e807 → c490eba3e807

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → c490eba3e807

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit c490eba3e807ae92e13fa302b8a6ee815121c3ef

31GitHub stars
1star in 7 days
1skill in this repository
0commits in 30 days

Heat

1.7
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Nov 1, 202631

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

exam-review-helper

When your agent uses it

期末考试复习助手 - 将 PDF/Word/TXT/Markdown 教材浓缩为精华知识点并生成交互式 HTML 复习文档。适用场景：理工科教材（数学/物理/计算机/化学/工程）与文科教材（政治/哲学/历史/法学/教育学），自动识别模式。原生支持扫描版 PDF（含 OCR）、Word 讲义、纯文本笔记、Markdown 教材。当用户说"帮我复习这个"、"整理知识点"、"期末复习"，或上传学习资料问"总结一下"时主动使用此 skill，即使用户没明说"复习"。用户上传 PDF/DOCX/TXT/MD 学习资料时必须用本 skill 的 controller.py extract 提取，不要直接用 Read 工具（Read 读 PDF 会乱码、读 DOCX 会丢结构）。

What it loads into context

Frontmatter

212 tokens

Always available to the agent

SKILL.md

5,448 tokens

When the skill is activated

Reference documents

17,127 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. 默认调用模式：对话驱动（零配置）
  2. 5-Pass 工作流概览
  3. 三个防偷懒原则
  4. Skill 边界
  5. CLI 子命令
  6. 多格式输入（重要）
  7. 教材模式（自动识别，用户无需选择）
  8. 输出目录规范
  9. 输出 JSON Schema（HTML 模板兼容）
  10. 快速依赖检查
  11. 大 PDF 处理（重要）
  12. 高级功能（P0-P1 增强）
  13. 章节范围选择（重要）
  14. 标准对话流（参考）
  15. 参考文档
  16. MUST 交付标准

Scripts executed separately

  • scripts/cache.py
  • scripts/chapter_selector.py
  • scripts/config.py
  • scripts/controller.py
  • scripts/enhance_formulas.py
  • scripts/extractors.py
  • scripts/generate_html.py
  • scripts/ocr_corrector.py
  • scripts/run_evals.py
  • scripts/run_pipeline.py
  • tests/conftest.py
  • tests/test_chapter_selector.py
  • tests/test_extractors.py
  • tests/test_generate_html.py
  • tests/test_p0_p1_features.py
  • tests/test_pdf_regression.py
  • tests/test_run_evals.py

Files

  • SKILL.mdcore18,277 bytes
  • SKILL.mdcore18,277 bytes
  • SKILL.mdcore18,277 bytes
  • SKILL.mdcore18,277 bytes
  • SKILL.mdcore18,277 bytes
  • config.yamlasset3,102 bytes
  • docs/demo_3x4_screenshot.pngasset256,611 bytes
  • docs/optimizations-explained.htmlasset15,708 bytes
  • docs/screenshot.pngasset244,902 bytes
  • docs/screenshot_3x4.pngasset313,394 bytes
  • evals/evals.jsonasset11,291 bytes
  • prompts/system_merger.mddoc3,303 bytes
  • prompts/system_reader.mddoc7,237 bytes
  • prompts/system_reader_liberal_arts.mddoc6,112 bytes
  • prompts/system_reviser.mddoc3,908 bytes
  • prompts/system_segment.mddoc1,884 bytes
  • prompts/system_verifier.mddoc3,364 bytes
  • prompts/system_verifier_liberal_arts.mddoc3,804 bytes
  • pyproject.tomlasset1,228 bytes
  • references/advanced-features.mddoc2,777 bytes
  • references/common-failure-modes.mddoc9,406 bytes
  • references/multi-format-input.mddoc5,152 bytes
  • references/multi-pass-workflow.mddoc8,826 bytes
  • requirements.txtdoc1,030 bytes
  • scripts/cache.pyruns3,315 bytes
  • scripts/chapter_selector.pyruns4,498 bytes
  • scripts/config.pyruns6,578 bytes
  • scripts/controller.pyruns62,155 bytes
  • scripts/enhance_formulas.pyruns7,627 bytes
  • scripts/extractors.pyruns14,382 bytes
  • scripts/generate_html.pyruns12,170 bytes
  • scripts/ocr_corrector.pyruns3,790 bytes
  • scripts/run_evals.pyruns9,503 bytes
  • scripts/run_pipeline.pyruns10,847 bytes
  • templates/default.htmlasset90,908 bytes
  • test_data/sample.docxasset37,025 bytes
  • test_data/sample.mddoc996 bytes
  • test_data/sample_gbk.txtasset437 bytes
  • tests/conftest.pyruns1,492 bytes
  • tests/test_chapter_selector.pyruns4,314 bytes
  • tests/test_extractors.pyruns16,454 bytes
  • tests/test_generate_html.pyruns7,335 bytes
  • tests/test_p0_p1_features.pyruns6,373 bytes
  • tests/test_pdf_regression.pyruns7,170 bytes
  • tests/test_run_evals.pyruns10,178 bytes
Read SKILL.md

# 期末考试复习助手

将 PDF / Word / TXT / Markdown 教材转化为结构化精华复习文档，生成交互式 HTML。

---

## 默认调用模式：对话驱动（零配置）

本 skill **在宿主 agent（Claude Code / Codex / OpenCode）里对话式执行**。宿主自己就是 LLM，按本文档和 `references/` 下的指令执行 5-pass。**不需要 API key、不需要任何外部配置**。

```
用户: "帮我复习这个"（上传 textbook.pdf 或 notes.docx 或 chapter.txt 或 module.md）
  ↓
宿主读 SKILL.md → 检测文件格式 → 按 5-pass 工作流执行
View the complete source on GitHub

Skills included

  • exam-review-helper

Repository facts

License
MIT
Created
Jun 15, 2026
Last pushed
Jun 27, 2026
Forks
3
Open issues
0
Project activity
Slowing

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 7, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 4 notes
  • skills/exam-review-helper/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/exam-review-helper/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/exam-review-helper/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/exam-review-helper/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 23 signals by file

skills/exam-review-helper/SKILL.md

  • Network accessline 240
    docling 默认的 `DoclingParseDocumentBackend`（C++ 解析层）在处理复杂页面时会触发 `std::bad_alloc` 崩溃（[docling issue #3671](https://github.com/docling-project/docling/issues/3671)）。

skills/exam-review-helper/scripts/cache.py

  • Executable scriptline 1
    Executable file

skills/exam-review-helper/scripts/chapter_selector.py

  • Executable scriptline 1
    Executable file

skills/exam-review-helper/scripts/config.py

  • Executable scriptline 1
    Executable file

skills/exam-review-helper/scripts/controller.py

  • Executable scriptline 1
    Executable file

skills/exam-review-helper/scripts/enhance_formulas.py

  • Executable scriptline 1
    Executable file

skills/exam-review-helper/scripts/extractors.py

  • Executable scriptline 1
    Executable file
  • Possible obfuscationline 239
    img_path.write_bytes(base64.b64decode(b64_data))

skills/exam-review-helper/scripts/generate_html.py

  • Executable scriptline 1
    Executable file

skills/exam-review-helper/scripts/ocr_corrector.py

  • Executable scriptline 1
    Executable file

skills/exam-review-helper/scripts/run_evals.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Dangerous shell operationline 216
    print(f"共 {len(evals)} 个 eval（位于 {evals_file}）")

skills/exam-review-helper/scripts/run_pipeline.py

  • Executable scriptline 1
    Executable file

skills/exam-review-helper/templates/default.html

  • Network accessline 16
    }; </script> <script src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-svg.js"></script>
  • Network accessline 17
    </script> <script src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-svg.js"></script> <style>
  • Network accessline 18
    <script src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-svg.js"></script>

skills/exam-review-helper/tests/conftest.py

  • Executable scriptline 1
    Executable file

skills/exam-review-helper/tests/test_chapter_selector.py

  • Executable scriptline 1
    Executable file

skills/exam-review-helper/tests/test_extractors.py

  • Executable scriptline 1
    Executable file

skills/exam-review-helper/tests/test_generate_html.py

  • Executable scriptline 1
    Executable file

skills/exam-review-helper/tests/test_p0_p1_features.py

  • Executable scriptline 1
    Executable file

skills/exam-review-helper/tests/test_pdf_regression.py

  • Executable scriptline 1
    Executable file

skills/exam-review-helper/tests/test_run_evals.py

  • Executable scriptline 1
    Executable file

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 20 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md skills/exam-review-helper/SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md skills/exam-review-helper/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md skills/exam-review-helper/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md skills/exam-review-helper/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md skills/exam-review-helper/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md skills/exam-review-helper/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

addyosmani/agent-skills

Production-grade engineering skills for AI coding agents.

113.8kGitHub stars

ComposioHQ/awesome-claude-skills

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

79kGitHub stars

blader/humanizer

Rewrite AI-sounding text so it reads like the writer without changing what it says. Use when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line closers, stag…

65.8kGitHub stars

OthmanAdi/planning-with-files

Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against…

27.9kGitHub stars

titanwings/distilly

Set up the owner profile so a personal agent knows who it works for (first-run setup, "get to know me"), or distill colleague, relationship, or celebrity source material into reus…

26.4kGitHub stars

KKKKhazix/khazix-skills

数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader（帮你定义目标）, neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents

22kGitHub stars