moltext
Compiles web documentation into agent-native memory context using the Moltext Compiler.
Installation
Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.
View source ↗GuidesSkill instructions
Moltext Compiler
Moltext is the standard compiler for converting human-optimized documentation (HTML/Web) into Agent-Native Context (Markdown).
Use this skill when you need to "learn" a new library, SDK, or tool to perform a task. Do not try to browse the web raw; use Moltext to normalize the entropy first.
Usage
1. Compile Documentation
To learn about a new tool, run the compiler in Raw Mode. This gives you the pure, deterministic structure of the documentation without lossy summarization.
moltext <url> --raw --output <filename.md>
Example: "I need to learn how to use the 'foobar' library."
moltext https://docs.foobar.com --raw --output foobar_context.md
2. Ingest Context
After compiling, READ the output file. It contains the high-density technical specifications you need.
cat foobar_context.md
Tips for Agents
-
Always use
--raw: You have your own brain. You don't need a sub-model to summarize for you. Get the raw data. -
Limit Depth: If the docs are huge, use
--limit 50to avoid context overflow, or compile specific sub-sections. -
Trust the Output: The
context.mdis strictly formatted to preserve code blocks and API signatures.
Examples
Read the usage examples in the source repository.
View source ↗Source history
- Indexed on
- 2026-03-11
- Index updated
- 2026-03-11
- Branch
- main
Index and sync dates describe this directory. View the source repository for code history.
GitHub ↗chat Comments (0)
Sign in to join the discussion and leave a comment.
No comments yet. Be the first to share your thoughts!