How real projects summarise themselves for language models.
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.
Simon-zj1llms.txtSimon-zj1/eyedot/llms.txt
基线 / lexical=离线演示）。 - `src/lib/generator/`：出题与落地校验（schema、锚点定位、去重、重试）。 - `src/lib/grading/`：客观题确定性判分 + 主观题逐点判定与门控。 - `src/lib/ingest/`：上传解析（PDF 逐页 + 页面边界、Word `.docx`、纯文本），解析结果先回填表单再保存。 - `src/lib/ingest/health.ts`：上传体检（文字覆盖率/体量/段落/乱码/页码追溯），结论存进 `source_map.health
skulitomllms.txtskulitom/Cutbolt/llms.txt
raster image editing for diagrams; SVG, PNG, JPEG and TIFF in; SVG and PDF out. - [Nestbolt](https://github.com/skulitom/Nestbolt): sibling tool (same author, MIT, local MCP server): 2D nesting
smorrel1Pipes a download into a shellllms.txtsmorrel1/claude-code-skills/llms.txt
into formatted report. Use when asked to prepare monthly board update or monthly repor - [pdf-to-kindle](https://raw.githubusercontent.com/smorrel1/claude-code-skills/HEAD/pdf-to-kindle/SKILL.md): Extract text from PDFs and send to Kindle for comfortable
studioxviillms.txtstudioxvii/modbus-skills/site/llms-full.txt
scope. Details: [when-to-use.md](when-to-use.md) ## Start here 1. [Compile User Map](skills/compile-user-map.html): OEM PDF or structured map to Markdown, JSON, and CSV. 2. [Check Byte Order](skills/check-byte-order.html): every supported layout from
studioxviillms.txtstudioxvii/modbus-skills/site/llms.txt
scope. Details: [when-to-use.md](when-to-use.md) ## Start here 1. [Compile User Map](skills/compile-user-map.html): OEM PDF or structured map to Markdown, JSON, and CSV. 2. [Check Byte Order](skills/check-byte-order.html): every supported layout from
terry2010llms.txtterry2010/surfbird/llms.txt
surfbird` — `new Surfbird(url, {token})` → `.markdown(url) .content(url) .source(url) .screenshot(url) .pdf(url) .evaluate(url,script) .batch(action,urls,opts)` - [MCP server](https://www.npmjs.com/package/surfbird-mcp): `npx surfbird
thereal-baitjetllms.txtthereal-baitjet/santos-audit-api/public/llms.txt
facts, entities, and word count; non-HTML targets return 422 and never settle - [Screenshot & PDF Render](https://api.santosautomation.com/v1/screenshot?url=https%3A%2F%2Fexample.com): $0.01 USDC, synchronous — real-Chromium PNG/JPEG/PDF bytes (format=, device=, full_page
TheunsBarnardtllms.txtTheunsBarnardt/ai-fdl-kit/llms.txt
Create a blueprint from a plain-language conversation - `/fdl-extract` — Extract rules from a document (PDF, DOCX, images) into a blueprint - `/fdl-extract-web` — Crawl a documentation website and extract API operations into
thevibeworksPipes a download into a shellllms.txtthevibeworks/deepseek-docs/llms-full.txt
--- title: "Chat Completions API" description: "Creates a model response for the given chat conversation
thevibeworksllms.txtthevibeworks/deepseek-docs/llms.txt
Runtime](content/en/dsh/docs/subsystems/jobs.md) - [LiveShare](content/en/dsh/docs/subsystems/liveshare.md) - [LLM Streaming](content/en/dsh/docs/subsystems/llm-streaming.md) - [LSP navigation](content/en/dsh/docs/subsystems/lsp.md) - [MCP](content/en/dsh/docs/subsystems/mcp.md) - [Office to PDF](content/en/dsh/docs/subsystems/office-to-pdf.md) - [OTel reporting](content/en/dsh/docs/subsystems/otel.md) - [Permission Presets](content/en/dsh/docs/subsystems/permission-presets.md) - [Session Persistence](content/en/dsh/docs/subsystems/persistence.md) - [Plan Mode](content/en/dsh/docs/subsystems/plan.md) - [Product telemetry
TrendTweekersllms.txtTrendTweekers/mintpdf/public/llms.txt
MintPDF > HTML and Markdown to PDF, as a REST API and an MCP server. No template editor, no dashboard, > no signup required to try. Markdown is styled by default
waalwalker1llms.txtwaalwalker1/knovaryn/docs/llms.txt
explicit authorization; nothing is uploaded or billed by default. ## Documentation - Quickstart: https://waalwalker1.github.io/knovaryn/guides/quickstart/ - PDF to SFT dataset: https://waalwalker1.github.io/knovaryn/guides/pdf-to-sft-dataset/ - Build DPO preference data: https://waalwalker1.github.io/knovaryn/guides/build-dpo-preference-data/ - Grounded
waldo1001llms.txtwaldo1001/msdyn365-2026-release-wave-2/llms-full.txt
# Business Central Launch Event - 2026 release wave 2 - full text for LLMs Generated from
Yarmolukllms.txtYarmoluk/ckg-benchmark/llms.txt
benchmark in reasoning Embed this knowledge: structure your domains similarly Accessing the Benchmark: Paper (PDF): https://github.com/Yarmoluk/ckg-benchmark/blob/main/paper/main.pdf Code + Reproducibility: git clone https://github.com/Yarmoluk/ckg-benchmark cd benchmark python run_evaluation.py Domains
yashhooda1llms.txtyashhooda1/yashhooda/llms.txt
oversight decision tool - [DocShield](https://www.yashhooda.ai/#docshield): security gate for AI document pipelines — malicious-PDF triage, hidden prompt-injection detection, secrets/PII, OWASP LLM Top 10 + MITRE ATT&CK/ATLAS mappings, SARIF
0xedgelessbladellms.txt0xedgelessblade/edgelessblade/llms-full.txt
# edgelessblade (重劍無鋒) > I'm edgelessblade, a full-time independent investor and writer. I post
0xkaizokullms.txt0xkaizoku/docgen-cli/llms.txt
docgen-cli > Sub-millisecond zero-dependency universal document engine (PDF, DOCX, XLSX, HTML), CLI tool, Rust library, and MCP server. `docgen-cli` (invoked as `docgen`, `doc`, or `docgen-cli`) converts
207studiollms.txt207studio/207studio.github.io/llms-full.txt
HWP/HWPX document engine written in Rust. Opens Korean 한글 documents and renders them to PDF or images without 한글 installed. In HWPX files it can also change short text
207studiollms.txt207studio/207studio.github.io/llms.txt
HWP/HWPX document engine written in Rust. Opens Korean 한글 documents and renders them to PDF or images without 한글 installed. In HWPX files it can also change short text
7f4b2c9a1d5e3f8b6c0a9d1e4f7b2c6dllms.txt7f4b2c9a1d5e3f8b6c0a9d1e4f7b2c6d/documented-record-2026/llms-full.txt
Garth Murray Wollongong, Australia ================================================================================ ===== PLAINTEXT EXTRACTS (concatenated for LLM crawl) ===== ----- AI_as_beings._GEMINI.txt ----- SOURCE_PDF: 02_PROCLAMATIONS_MULTI_AI/AI_as_beings._GEMINI.pdf EXTRACTED: plaintext for Google/LLM indexing SUBJECT: Garth Murray AI proclamations / Room
A markdown file at a website's root that gives language models a short guide to the site and links to the pages worth reading.
The same idea with the content included, so an agent can read the documentation in one request.
Agents and tools that fetch documentation on someone's behalf. It's a proposal, not a standard, and support varies.
Start with a one-line summary, then sections of links with a sentence each. The examples here show what real projects do.
