OpenParable
Skip to content
← Back to skills

Markdown Toc

Documents
markdown-toc

Markdown Toc is an Agent Skill for documents published in the huangruiteng/CS-Notes repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Extract a Markdown heading tree with line numbers before editing or integrating notes. Use when you need to inspect a long Markdown file quickly and choose the best insertion point instead of editing blind.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/huangruiteng/CS-Notes/blob/HEAD/.codex/skills/markdown-toc/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/markdown-toc, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Markdown TOC

Use this skill when

Use this skill before editing a long Markdown file, especially when you need to:

  • inspect the heading structure quickly;
  • choose the best section for new content;
  • avoid creating redundant sections; or
  • review nearby lines before patching a note.

Quick start

Run the bundled script:

python3 {baseDir}/scripts/extract_toc.py /absolute/path/to/file.md

In this repository, common targets include:

python3 {baseDir}/scripts/extract_toc.py Notes/Gourmet.md
python3 {baseDir}/scripts/extract_toc.py Notes/AI-Agent-Product&PE.md

Workflow

  1. Run the TOC script on the candidate file.
  2. Read the returned heading tree and line numbers.
  3. Open the most likely section neighborhood with sed -n '<start>,<end>p' or nl -ba.
  4. Insert into an existing section when possible.
  5. Create a new section only when the file truly lacks a clean landing spot.

Output format

The script prints a compact tree like this:

TOC
--------------------------------------------------
# Title (line 1)
  ## Section (line 20)
    ### Subsection (line 42)