Help us improve
Share bugs, ideas, or general feedback.
From llms-keeper
This skill should be used when the user asks to "generate llms.txt", "create llms-full.txt", "update llms.txt", "regenerate llms-full.txt", "create AI context files for this project", "обновить llms.txt", "сгенерировать llms-full.txt", "создать контекст проекта для AI", or mentions "llms.txt", "llms-full.txt", "llmstxt", "llmstxt.org standard", "project context for AI agents", "контекст проекта для AI". Also applicable when user asks about the llmstxt.org format, wants to know how to structure llms.txt, or asks "what should llms-full.txt contain".
npx claudepluginhub spumer/i-m-senior-developer --plugin llms-keeperHow this skill is triggered — by the user, by Claude, or both
Slash command
/llms-keeper:llms-keeperThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Generate and maintain `llms.txt` and `llms-full.txt` files following the [llmstxt.org](https://llmstxt.org) standard to give AI agents quick project understanding.
Creates minimal, high-signal CLAUDE.md and AGENTS.md context files for repos using empirical best practices. Triggers on /init, create/update requests, or missing context during brainstorming.
Generates llms.txt and llms-full.txt from git repo wikis for LLM-readable project docs per llms.txt spec. Resolves repo URL/branch first.
Optimizes project docs and READMEs for LLMs like Claude/Copilot via c7score scoring, llms.txt generation, question restructuring, and quality analysis.
Share bugs, ideas, or general feedback.
Generate and maintain llms.txt and llms-full.txt files following the llmstxt.org standard to give AI agents quick project understanding.
"Find the smallest set of high-signal tokens that maximize the likelihood of desired outcome."
Every sentence must answer: "Will an AI agent produce worse results without this information?" If no — delete without hesitation.
| File | Purpose | Audience | Length |
|---|---|---|---|
llms.txt | Navigation index | AI needing quick orientation | 50-100 lines |
llms-full.txt | Complete context | AI needing full understanding | 200-600 lines |
Delegate analysis and generation to the documentation-keeper agent.
The agent handles the full process: framework auto-detection, codebase scanning, pattern extraction, file generation, and quality verification.
For manual or informational use, the workflow is:
llms-full.txt first (self-contained content)llms.txt from it (navigation index linking to sections)references/llmstxt-spec.mdFor format details, structure requirements, and quality checklist, see references/llmstxt-spec.md.