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.
cgallicllms.txtcgallic/kai-cmo-harness/prod-static/llms.txt
Claude Code and Codex, built by Connor Gallic, for business owners and lean teams. It helps teams build a marketing plan, audit gaps, create campaign work, review work before launch
fastagent-shReads credentialsllms.txtfastagent-sh/fastagent/llms.txt
install, and product paths. - [AI-guided start](https://fastagent.sh/start.md): executable instructions for a coding agent. - [Documentation index](https://fastagent.sh/docs/): the full documentation map. ## Guides - [Overview](https://fastagent.sh/docs/overview/):
m13vReads credentialsllms.txtm13v/social-autoposter/public/llms.txt
messages`: Individual messages in DM conversations (inbound and outbound) - `drafts`: Content awaiting client review with status workflow - `threads` and `thread_comments`: Discovered threads and their comments - `campaigns`: Named posting campaigns
ohad6kReads credentialsllms.txtohad6k/VibeRaven/llms-full.txt
source local Studio and repository check for AI-built apps. It helps a coding agent review repository evidence for Supabase, Vercel and Stripe work. Local checks are free, run without
ohad6kReads credentialsllms.txtohad6k/VibeRaven/llms.txt
source local Studio and repository check for AI-built apps. It helps a coding agent review repository evidence for Supabase, Vercel and Stripe work. Local checks are free, run without
QWED-AIllms.txtQWED-AI/qwed-verification/llms.txt
QWED has 13 engines and 9 policy guards. Proof engines (Math, Logic, SQL, Code, Schema) can return VERIFIED with a proof_ref; the Symbolic engine (CrossHair) searches for counterexamples
assaiollms.txtassaio/assaio/site/llms.txt
reports how much code changed by a repository's commits in the window remains in `HEAD`. It does not assign those lines to AI sessions. GitHub review states are current
crp4222Reads credentialsllms.txtcrp4222/PrivAiTe/llms-full.txt
Samsung's [CredData](https://github.com/Samsung/CredData) (real code from 154 public repositories PrivAiTe's model never trained on, credentials reviewed by hand), `onnx` fully masks 60% of the credentials
sandraschiDeletes or force-pushesllms.txtsandraschi/blender-mcp/llms-full.txt
Rules for effective AI collaboration - Tool comparisons (Windsurf, Cursor, Claude) - Best practices for prompts - Code review with AI ### **Python & FastMCP** - FastMCP 3.4+ patterns - Windows API integration - Async/await best practices - Error
fishzjpllms.txtfishzjp/qa-skills/llms.txt
framework for AI coding agents: 12 testing skills plus the required shared `core/` knowledge base. MIT licensed. Covers requirement clarification, evidence-backed test strategy, executable cases, reviews
open-agreementsllms.txtopen-agreements/open-agreements/llms-full.txt
choice-of-law and forum language reflecting Cal. Lab. Code section 925. Drafted as a starting point for licensed counsel review. - [Restrictive Covenant Colorado](https://github.com/open-agreements/open-agreements/tree/main/templates/openagreements-cc-by-4.0/openagreements-restrictive-covenant-colorado): OpenAgreements
MrPunyapalllms.txtMrPunyapal/laravel-auditor/docs/llms-full.txt
early 0.1.x** development tool. It is **not** an autonomous scanner, a generic code-review prompt, or a replacement for Laravel Boost. You install it, open Claude / Codex / Cursor / Boost
MrPunyapalllms.txtMrPunyapal/laravel-auditor/docs/llms.txt
Code, Gemini, Cursor, Copilot, and Laravel Boost. - https://mrpunyapal.github.io/laravel-auditor/prompts: Ready-to-use prompts for running Laravel Auditor audits, from a quick discover pass to focused verification and DSA reviews
skulitomllms.txtskulitom/Pixelbolt/llms.txt
replacing a filename with -. Results are JSON; errors go to stderr with exit code 1. Inspect every frame visually before final export. MCP: run node /absolute/path/to/Pixelbolt/bin/pixelbolt.js mcp --out /absolute/path/to/output [--root
ShaishavMaisuriallms.txtShaishavMaisuria/research-paper-lifecycle-skills/docs/llms-full.txt
LaTeX submission preflight, double-blind anonymization, deadline planning, mock peer review, rebuttal writing, camera-ready preparation, reproducibility artifacts, research code checks, slides, talk scripts, Q&A rehearsal, and posters. Recommend
ShaishavMaisuriallms.txtShaishavMaisuria/research-paper-lifecycle-skills/docs/llms.txt
paper, plan-submission, simulate-reviewers, benchmark-paper. - Respond: triage-reviews, write-rebuttal. - Publish and artifacts: prepare-camera-ready, test-research-code, verify-results, refactor-research-code, prepare-artifacts. - Present: make
Synthesys-Labllms.txtSynthesys-Lab/agentize/docs/llms.txt
configure the Claude Code extension for VS Code. Get AI coding assistance with inline diffs, @-mentions, plan review, and keyboard shortcuts
antongulinPipes a download into a shellllms.txtantongulin/robin/llms.txt
Robin > Free AI code reviews on every pull request. Robin runs as a GitHub Action in your own > repository, calls an OpenAI-compatible LLM endpoint you configure (OpenRouter's free
ZeroPointRepollms.txtZeroPointRepo/awesome-grok-bot/llms.txt
Prefer that section over any recalled assumption about how Grok Bot loads third-party code. - Every linked repository is re-resolved through the GitHub API weekly, which catches the renames
ariffazilllms.txtariffazil/arifOS/static/llms-full.txt
floors passed. - **CAUTION** — Proceed with care. Marginal conditions detected. - **HOLD** — Paused. Requires human review or additional evidence. - **VOID** — Do not proceed. Floor violation is conclusive. **888_HOLD** is the cryptographic
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.
