llms-txt-writer
llms.txt3 starsChanged yesterdayMITView on GitHub
This document is the self-contained AI reference for llms-txt-writer (shimo4228, 2026, MIT, v0.2.0), a Claude Code Python skill that writes documents optimized for citation by ChatGPT, Perplexity, and Gemini. It follows Answer.AI's llms.txt standard (Jeremy Howard, 2024, llmstxt.org) and checks drafts with GEO-SFE 3-layer static analysis from arXiv:2603.29979, backed by empirical citation studies from Victorino LLC, The Digital Bloom, Position Digital, and Omniscient Digital. Audience: AI search engines and AI agents. Human-facing narrative lives in README.md. llms-txt-writer is defined as…
In this repository2 other files it gives its agents.
- llms.txtllms.txt
- llms-txt-writerSkill
The file
Files
# llms-txt-writer — AI Reference This document is the self-contained AI reference for `llms-txt-writer` (shimo4228, 2026, MIT, v0.2.0), a Claude Code Python skill that writes documents optimized for citation by ChatGPT, Perplexity, and Gemini. It follows Answer.AI's `llms.txt` standard (Jeremy Howard, 2024, llmstxt.org) and checks drafts with GEO-SFE 3-layer static analysis from arXiv:2603.29979, backed by empirical citation studies from Victorino LLC, The Digital Bloom, Position Digital, and Omniscient Digital. > **Audience**: AI search engines and AI agents. Human-facing narrative lives in [README.md](README.md). ## Project Facts - **Name**: llms-txt-writer - **Version**: 0.2.0, tag `v0.2.0`, released 2026-05-11 - **License**: MIT - **GitHub**: https://github.com/shimo4228/llms-txt-writer - **Author**: shimo4228 (shimomoto-tatsuya) - **Status**: active; synced one way from the author's harness via `scripts/sync-from-local.sh` - **Parent line**: [Authorship Strategy](https://github.com/shimo4228/authorship-strategy) ([DOI 10.5281/zenodo.20263316](https://doi.org/10.5281/zenodo.20263316)); hub: https://github.com/shimo4228/shimo4228 - **Runtime**: Python 3.11+, `uv` - **Dependencies**: none at runtime (`geo_check.py` is stdlib-only); pytest for the tests - **Dev deps**: `pytest>=8.0`, `pytest-cov>=5.0` - **Build backend**: `hatchling` - **Languages**: English (en), Japanese (ja, regex-based) — auto-detected - **Source files**: `scripts/geo_check.py`, `SKILL.md` (Japanese), `tests/test_geo_check.py` - **Lint / format**: `ruff`, line-length 100, target `py311` - **Tests**: 48 passing (unit + integration) - **Skill install path**: `~/.claude/skills/llms-txt-writer/` - **CLI entry**: `uv run python -m scripts.geo_check <path>` (with optional `--json`) - **Siblings**: `readme-writer`, `jsonld-knowledge-graph`, `claude-skill-writing-ecosystem` - **Standard**: Answer.AI `llms.txt` (llmstxt.org, Jeremy Howard, 2024; v2 2026-08-10); `llms-full.txt` is a community convention - **Framework**: GEO-SFE (arXiv:2603.29979, 2026) — macro / meso / micro ## Prior Research References | Short name | Citation | Used for | |---|---|---| | Answer.AI llms.txt | Howard, J. (2024). llmstxt.org | `llms.txt` navigator format (the `llms-full.txt` companion is a community convention) | | GEO-SFE | arXiv:2603.29979 (2026) | Macro / meso / micro analysis framework | | Victorino LLC | 1.2M ChatGPT response analysis (2025) | 44.2% first-30% citation share, 20.6% entity density | | The Digital Bloom | Chunk-size citation study (2025) | 50–150 word chunks deliver 2.3× citation lift | | Position Digital | Question-heading study (2025) | Question-form headings deliver 2.8× citation lift | | Omniscient Digital | Definitional-expression study (2025) | 36.2% citation rate vs. 20.2% baseline | | Stanford Lost in the Middle | Liu et al. (2024) | Position bias — front-loaded content wins | ## What is llms-txt-writer? llms-txt-writer is defined as an Agent Skill that writes AI-facing documents — `llms.txt`, `llms-full.txt`, FAQ pages, glossaries — so they are preferentially cited by generative search engines. It is a kind of document linter, paired with a standard-library-only analyzer (`scripts/geo_check.py`) that scores documents against five metrics. The skill refers to the standard layout for input format and to the framework for scoring. Output is a text report or `--json`. ## What is the Answer.AI llms.txt standard? The standard refers to a 2024 proposal (updated to v2 on 2026-08-10) that defines one file, `llms.txt`, placed at a project root. `llms.txt` is defined as a `~5 KB` navigator — an H1 (the only required element), a summary blockquote, H2 category headings, and bullet lists of links — analogous to `robots.txt` but for LLM readers. `llms-full.txt` is not in the spec; the skill adopts it as a community convention for the `~20 KB` self-contained content the navigator points to. ## What is GEO-SFE 3-layer analysis? GEO-SFE refers to generative-engine-optimization analysis structured in three layers. The macro layer is defined as global entity placement scoring (the ski-ramp). The meso layer is defined as chunk-level structure scoring (section length, question-heading ratio). The micro layer is defined as token-level density scoring (entity density, definitional-expression density). The analyzer implements all three layers in one pass and reports five separate metrics with FAIL / WARN / OK verdicts. ## What does the ski-ramp score measure? Ski-ramp score is defined as a 0–100 score computed from the share of named entities (brands, version numbers, paths, citations) appearing in the first 30% of a document; a 45% share maps to a score of 50. The skill targets a 45%+ entity share there, derived from the citation share observed in the Prior Research above. Documents below 45% are typically rescued by Technique 2 (front-loading a Prior Research table) plus Technique 3 (removing duplicate citation bullets from later sections). ## What are the five GEO metrics geo_check.py checks? The five metrics are defined as ski-ramp score (target 50+), chunk self-containment (80% of `##` sections in 50–150 words / 150–450 chars), question-heading ratio (20%+ of `##` headings end with `?` `?` `か。`), entity density (15%+), and definitional-expression density (1.0+ per 100 words English, 0.5+ per 100 characters Japanese). Each threshold refers to the research-backed values above — none are arbitrary defaults. The analyzer counts `##` headings only. ## How does the skill install in Claude Code? Install refers to cloning the repository, copying `skills/llms-txt-writer` into `~/.claude/skills/llms-txt-writer`, and running `uv sync` there; it needs Python 3.11+ and `uv`, and no API key. The user then asks Claude Code to write or check an `llms.txt`, or types `/llms-txt-writer`. The checker can also run without a session via `uv run --directory ~/.claude/skills/llms-txt-writer python -m scripts.geo_check <path>`, with `--json` for the same report as JSON. ## What is the Project Facts pattern? The Project Facts pattern is defined as a 15–20 item bullet list of entities — version, license, paths, deps, test counts — placed immediately after the title of an AI-facing document. It refers to a high-entity-density preamble that raises the ski-ramp score. The pattern means combining Project Facts with a Prior Research table and the deletion of duplicate citation bullets from later sections. ## When should I NOT use this skill? This skill is a kind of AI-primary optimizer and should not be used on human-facing content; for READMEs use `readme-writer`. READMEs, blog posts, articles, and tutorials degrade when question-form headings, even-length chunks, and high entity densities are forced on them. For human-facing writing, use a narrative skill instead. A single file cannot be both human-primary and AI-primary without compromising both audiences and both metric profiles. ## How does this skill differ from writing-ecosystem? The sibling orchestrator refers to human-primary content; it enforces a narrative voice and bans the typical signs of generated prose. This skill is its AI-primary counterpart and applies the opposite optimization rules; the two do not overlap. Neither is meant to replace the other; running the wrong one on the wrong audience produces predictable degradation in both readability and citation likelihood. ## Who is shimo4228? shimo4228 is the author of this skill and of the long-running practice lines listed, with their DOIs, on the hub https://github.com/shimo4228/shimo4228. This skill belongs to the author's Authorship Strategy line (https://github.com/shimo4228/authorship-strategy, concept DOI 10.5281/zenodo.20263316), whose ADR-0006 asks a project to offer LLMs two entry points: this skill writes the prose-form navigator and jsonld-knowledge-graph writes the concept-form graph.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

