lecture-note-writer
Use when the user wants course notes or study notes written from local slide PDFs, PPTs, or existing markdown notes, especially when the notes should match…
Skill by lyh843
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/lyh843-lecture-note-writer
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, presentations, writing, productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/lecture-note-writer
What's inside
- Skill name
lecture-note-writer- Description
- Use when the user wants course notes or study notes written from local slide PDFs, PPTs, or existing markdown notes, especially when the notes should match the user's existing style. This skill reads the source material, samples nearby notes to infer structure and tone, then writes or rewrites the target markdown in a consistent format.
- License
- MIT
- Instructions
- 91 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Lecture Note Writer ## Overview This skill is for note-production workflows where source material and house style both matter. Use it when the user wants you to read lecture slides or existing notes, infer the user's note style from nearby files, and then create or rewrite a target markdown file in that same style. ## When To Use - The user asks to read a local PDF or PPT and turn it into a markdown note. - The user asks to rewrite a note based on nearby notes in the same subject folder. - The user wants multiple note files written in the same format and tone. - The user explicitly asks to "match my style", "follow my existing notes", or similar. Do not use this skill for: - Plain summarization of text the user already pasted inline with no file work. - Creative writing unrelated to study notes. - Cases where the user wants a brand new format and does not want style matching. ## Workflow 1. Identify inputs. Required inputs are: - source material such as a local PDF, PPT, or existing note - target markdown path to create or rewrite Helpful context: - neighboring notes in the same topic directory 2. Read the source material first. - Prefer direct text extraction from PDF when possible. - Capture the chapter flow, definitions, examples, formulas, and any explicit comparisons. - Ignore slide boilerplate such as teacher name, school logo, and duplicate headings unless useful. 3. Infer the user's note style from nearby notes. Sample 2-5 related notes from the same subject area and extract: - heading style such as `#`, `##`, numbered sections, and separators like `---` - language mix such as English titles with Chinese terminology notes - density of bullets vs prose - typical formula formatting - how examples and summaries are labeled - whether the notes are terse outline style or more explanatory 4. Build the target outline from content, not from the slide page order alone. Preferred structure: - intro / motivation - core idea - mechanism or algorithm - worked examples - pros / cons / trade-offs - summary - connection to next topic when relevant 5. Write or rewrite the target markdown. - Preserve the user's existing style where it is stable. - Normalize obvious inconsistencies only when they make the note clearer. - Keep terminology accurate even if the user's style is informal. - If the target file is empty, create a full note from scratch. - If the target file already has useful content, integrate rather than overwrite blindly. 6. Verify coherence before finishing. Check: - section order is logical - formulas and numeric examples are correct - terminology is consistent across the note - the note connects cleanly with adjacent topics ## Writing Rules - Match the user's local note style before introducing your own preferences. - Prefer concise bullets over long paragraphs unless nearby notes are prose-heavy. - Keep titles and subsection naming consistent with neighboring files. - Use bilingual terminology naturally when the user's notes do that. - Keep examples concrete; do not leave placeholder text such as `==ppt中图片==` unless the user uses that intentionally. - Do not pad the note with generic textbook filler. - If a slide deck is shallow, produce a short note; if the deck is dense, produce a fuller note. ## Output Pattern When the local notes follow the style seen in this workspace, a good default shape is: - `# Topic Name` - `---` - `## 01. Intro` - `## 02. Core Idea` - `## 03. Example / Translation / Mechanism` - `## 04. Problems / Trade-offs` - `## 05. Summary` - `## 06. Connection to Next Part` Adjust this shape if nearby notes clearly use a different one. ## Fast Prompt Patterns Use prompts like: - `Use $lecture-note-writer to read slides/operationSystem/2_7-虚拟化-快速地址转换.pdf, infer my style from Note/operationSystem, and rewrite Note/operationSystem/内存虚拟化/快速地址转换.md.` - `Use $lecture-note-writer to read this PDF and rewrite the target note in the same style as nearby markdown files.` - `Use $lecture-note-writer to complete the missing notes in this folder with the same structure as the existing ones.`
From lyh843/AgentSkills, MIT.
More from lyh843/AgentSkills
- 0.552score
codebase-map
lyh843
Generate an interactive, self-contained HTML map of any codebase — a dependency graph of its modules, a zoomable lines-of-code treemap, and stack-specific…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
ning-python-scientific-plotting
lyh843
Create, refine, or review scientific figures in Python using the bundled plotting notes.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
codebase-summary
lyh843
Generate a structured summary of any codebase — architecture overview, tech stack, module map, and full API inventory with a Mermaid diagram.
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
book-to-skill
lyh843
Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills, extracting frameworks…
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
codebase-overview
lyh843
Systematic codebase exploration and architecture mapping.
SkillBFreshness: B★ 1Claude Code +9 - 0.502score
battery-status
lyh843
Check the current battery and charging information on this Linux machine, especially when the user asks for charging wattage, battery percentage, charging…
SkillCFreshness: C★ 1Claude Code +9 - 0.502score
grounded-file-qa
lyh843
Read one or more local files, especially PDFs, and answer follow-up questions grounded in those sources.
SkillCFreshness: C★ 1Claude Code +9 - 0.502score
ai-paper-digest
lyh843
Collect and summarize recent AI papers with emphasis on major ML/AI venues, journals, arXiv, and paper-discovery sites.
SkillCFreshness: C★ 1Claude Code +9 - 0.493score
concept-wiki-html
lyh843
Build a static, local-source-grounded HTML knowledge page from course notes and slides, organized as one big topic with clickable concept nodes and deeper…
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 30, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/lyh843/AgentSkills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from lyh843
- 0.552score
codebase-map
lyh843
Generate an interactive, self-contained HTML map of any codebase — a dependency graph of its modules, a zoomable lines-of-code treemap, and stack-specific…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
ning-python-scientific-plotting
lyh843
Create, refine, or review scientific figures in Python using the bundled plotting notes.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
codebase-summary
lyh843
Generate a structured summary of any codebase — architecture overview, tech stack, module map, and full API inventory with a Mermaid diagram.
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
book-to-skill
lyh843
Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills, extracting frameworks…
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
codebase-overview
lyh843
Systematic codebase exploration and architecture mapping.
SkillBFreshness: B★ 1Claude Code +9 - 0.502score
battery-status
lyh843
Check the current battery and charging information on this Linux machine, especially when the user asks for charging wattage, battery percentage, charging…
SkillCFreshness: C★ 1Claude Code +9
Cite this page
lecture-note-writer skill. Agent Mart. https://agentmart.dev/skills/lyh843-lecture-note-writer (last updated 2026-10-24)