How real projects summarise themselves for language models.
mateffyllms.txtmateffy/struktur/docs/llms.txt
data to enrich existing records. - [Extract Invoice Data](/docs/examples/extract-invoice): Extract structured invoice data from PDF or text files. - [Extract Real Estate Listings](/docs/examples/extract-realestate): Extract property data from PDF real estate
techhorizonlabsllms.txttechhorizonlabs/thl-open/llms.txt
report-kit](https://github.com/techhorizonlabs/thl-open/tree/main/tools/audit-report-kit): turns an audit's JSON into a branded client PDF plus compile-checked JSON-LD, ready to paste. - [GEO skill suite](https://github.com/techhorizonlabs/thl-open/tree/main/skills): citability
thevibeworksllms.txtthevibeworks/claude-reads-hn/llms.txt
# Claude Reads HN > AI-curated HN digests every 5 hours. Check story IDs before
jimy-rllms.txtjimy-r/agent-workspace-architecture/docs/llms-full.txt
# Agent Workspace Architecture — full text > A redacted reference for building agent workspaces: the roles
klausnersllms.txtklausners/course-builder/llms.txt
scout agent that finds unexplored opportunities - Incremental mode to add modules to existing courses - PDF export via pandoc - Research transparency metadata (sources read, failures, quorum stats) ## Installation Copy `.claude/agents/course-builder.md
Microsoftllms.txtmicrosoft/vivainsights-py/docs/llms.txt
microsoft.github.io/vivainsights-py/_api/vivainsights.network_p2p.html): `network_p2p()`; input: Person-to-person query; return_type: plot, plot-pdf, table, data, network, sankey; privacy: Network outputs can identify individuals; apply organizational privacy and disclosure policy
Mnemosyne-OSllms.txtMnemosyne-OS/Mnemosyne-Neural-OS/llms.txt
social data, so it | `pluginReaderActions.ts` | | `reader.renderPage` | `vault:read` | Render one page of the original PDF → JPEG (base64) for the reader's side-by-side "compare with the source" view (host
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
sandraschillms.txtsandraschi/qcad-mcp/llms-full.txt
plan_export(file_name, format, output_name)` -- Export a DXF file to SVG, PDF, or PNG. Tries QCAD Pro for high-fidelity output first (SVG, PDF), falls back to ezdxf
Brandcode-Studiollms.txtBrandcode-Studio/brandsystem-mcp/llms.txt
what's already true. ## Key capabilities - Adopt: brand_start accepts a website URL, PDF guidelines, Figma file key, or a Brandcode Studio brand — and discovers local sources (guideline PDFs, token
ChanMeng666llms.txtChanMeng666/archlang/llms-full.txt
# ArchLang — full agent context (llms-full.txt) This is the complete context for driving **ArchLang**, a
oyi77llms.txtoyi77/1ai-skills/llms.txt
testing, Git workflows - **Content** (62 skills) — Video generation, audio, design, writing, document creation (docx, pdf, pptx, xlsx), UI design, themes - **Mindset** (55 skills) — Negotiation, leadership, critical thinking, emotional intelligence, productivity
minicoursegeneratorllms.txtminicoursegenerator/skills-for-course-creators/llms-full.txt
policy documents. - Audience: instructional designer, course creator - License: See source - First party: false pdf - Source: https://github.com/anthropics/skills/tree/main/skills/pdf - Owner: anthropics - Summary: Extract, inspect, merge, and annotate PDF source material before
urmzdllms.txturmzd/incipit/llms.txt
resume/](https://github.com/urmzd/incipit/blob/main/resume/): Resume data model, validation, JSON/Markdown parsing - [compilers/](https://github.com/urmzd/incipit/blob/main/compilers/): PDF compilation (LaTeX engines, Rod/Chromium) - [templates/](https://github.com/urmzd/incipit/blob/main/templates/): Built-in templates - [Skill](https://github.com/urmzd/incipit/blob/main/skills/resume/SKILL.md):
event4u-appllms.txtevent4u-app/agent-config/llms.txt
regulatory-delta. Triggers on 'should we enter market X', 'which segment first'. markitdown: Convert PDF, DOCX, XLSX, PPTX, EPUB, images, or audio to Markdown via the markitdown-mcp server — 'extract
JAYcodrllms.txtJAYcodr/claude-code-ultimate-guide-zh/llms-full.txt
issue-triage/` — GitHub issue prioritization - `landing-page-generator/` — Landing page from repo - `pdf-generator.md` — Professional PDF generation (Quarto/Typst) - `pr-triage/` — PR review prioritization - `release-notes-generator/` — Multi-format release notes
JAYcodrllms.txtJAYcodr/claude-code-ultimate-guide-zh/llms.txt
/optimize, /git-worktree - Hooks: dangerous-actions-blocker, prompt-injection-detector, secrets-scanner (bash + PowerShell) - Skills: pdf-generator, tdd-workflow, guide-recap, landing-page-generator, skill-creator - Scripts: session-search, audit-scan
txn2llms.txttxn2/mcp-data-platform/docs/llms-full.txt
# mcp-data-platform > MCP server for AI-assisted data exploration. DataHub semantic layer with
txn2llms.txttxn2/mcp-data-platform/docs/llms.txt
copy, NDJSON, CSV/TSV tables, image zoom and pan, audio and video with seek, embedded PDF, a Parquet viewer that reads the file by byte range (schema with the Trino type
31Carlton7llms.txt31Carlton7/mac-cli/site/llms.txt
keynote add-slide Deck --title "Q3" --body "Revenue up" mac keynote export Deck --format pdf --out ~/deck.pdf mac pages docs mac pages set-body Letter --text "Dear team," mac pages
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.
