Markdown TOC
v1.0.0Generate a table of contents from Markdown headings with configurable levels, formats, and unique anchors, excluding headings inside code blocks.
⭐ 0· 88·0 current·0 all-time
byhaidong@harrylabsj
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description align with the included script and README. The Python script implements heading extraction, slug generation, duplicate handling, and output formatting as described.
Instruction Scope
SKILL.md instructs running the included Python script against a user-supplied file and only reads/writes the specified input/output paths. It explicitly avoids headings inside code blocks. Minor note: the instructions reference an installation path (~/.openclaw/skills/markdown-toc/markdown_toc.py) which assumes the skill is installed there; otherwise README uses a relative invocation. No instructions ask the agent to read unrelated files or env vars.
Install Mechanism
There is no install spec (instruction-only) and the repository contains a single small Python script. No downloads or external installers are used.
Credentials
The skill declares no required environment variables or credentials. Minor inconsistency: SKILL.md/README show invoking the script with the 'python' command but required-binaries lists none; the platform will need Python available to run the script.
Persistence & Privilege
always is false and the skill does not request persistent system modifications or access to other skills/configs. disable-model-invocation is false (normal) so the agent could invoke it autonomously, but that is expected for user-invocable skills.
Assessment
This skill appears to do exactly what it says: local processing of Markdown files to generate a TOC. Before installing, ensure your environment has Python available (the SKILL.md calls 'python'), and only pass files you trust (the script will read the input file and optionally write the output path you provide). There are no network calls or secret/env var requirements. If you want to be extra cautious, inspect the included markdown_toc.py (present here) and run it manually on a sample file to confirm behavior before allowing autonomous agent invocation.Like a lobster shell, security has layers — review code before you run it.
latestvk972swn68dbvfjymnhzh7w9c75839d7d
License
MIT-0
Free to use, modify, and redistribute. No attribution required.