# LLMS-Explorer > A research hub for agents: installable skills, context files and per-concept facts files to load whole (listed in /context.md), the concept tree behind them, plus the llms.txt reference and rubric, a directory of every known llms file with its conformance grade, and a recorded keyword/vector/hybrid run. Companion files: llms-full.txt (every page in full), llms-small.txt (the reference, essays and examples layers within ~50k tokens), llms-facts.txt (source-anchored units), llms-vocabulary.txt (the terms of this niche). To load context rather than read pages: /context.md lists every context file and every concept's facts file with absolute URLs, filed by concept-tree root — one fetch to choose, one more to load; /skills/llms.txt lists every installable skill. ## Sections - [Overview](overview/llms.txt): 17 pages, ~842 tokens — About LLMSX, Your account, Context files and 14 more - [Reference](reference/llms.txt): 15 pages, ~771 tokens — The API: what it is, and how to call it, The attribute rubric, Changelog: spec v1 to v2, and the hub pipeline and 12 more - [Examples](examples/llms.txt): 14 pages, ~906 tokens — Worked example: the Anthropic hiring concept pack, Which layer answers which question, Recipe 01 — Two hops with requests and 11 more - [Blog](blog/llms.txt): 43 pages, ~3,091 tokens — A Closed-Loop System for Autonomous Skill-Knowledge Acquisition, Abstracting one concept out of many docsets, Anchors that point nowhere and 40 more - [Explorer](explorer/llms.txt): 1 pages, ~85 tokens — LLMSX Explorer User Guide - [Skills](skills/llms.txt): 21 pages, ~1,359 tokens — braindump, code-deep-optimizer, concept-family-explorer and 18 more