Skip to content

Add llms.txt for LLM/agent-readable project summary - #261

Open
abyworkings-coder wants to merge 1 commit into
voidcosmos:mainfrom
abyworkings-coder:add-llms-txt
Open

Add llms.txt for LLM/agent-readable project summary#261
abyworkings-coder wants to merge 1 commit into
voidcosmos:mainfrom
abyworkings-coder:add-llms-txt

Conversation

@abyworkings-coder

Copy link
Copy Markdown

This repo doesn't have an llms.txt file yet — a small, curated markdown index (title, one-line summary, and grouped links to the docs that matter) that AI coding agents can read to understand a project quickly, instead of having to crawl and guess through the full README and docs/ tree.

npkill is simple to use interactively but has real depth for scripted/automated use — profiles, a .npkillrc config file, a documented JSON/streaming output mode, and a whole separate Node.js API for embedding it in other tools (API.md). That's the part an agent is most likely to need help with (e.g. "write a script that deletes node_modules older than 30 days using npkill's JSON output"), and right now it's split across the README and three separate docs files with no single index pointing an agent at the right one.

Content is derived entirely from your existing docs (README sections: Installation, Usage, Options, Examples, JSON Output, Set Up Locally, Roadmap, plus docs/profiles.md, docs/npkillrc.md, docs/json-output.md, and API.md) — no new claims, just pointers. Validated against the llms.txt spec with llms-txt-lint (disclosure: a small validator tool I maintain — happy to drop that line from the PR if you'd rather not have it).

Totally understand if this isn't something you want to maintain — no worries either way, feel free to close.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant