How real projects summarise themselves for language models.
Bordallms.txtBorda/vision-delivery/docs/llms-full.txt
Codex plugin hooks require explicit trust review after installation or changes. On malformed hook input, the hook may write only a fixed diagnostic code and timestamp under host-managed plugin
chiragmangaldev3112llms.txtchiragmangaldev3112/agent-playbooks/docs/llms.txt
provides 37 playbooks -- reproduce-before-fix bug fixing, test-first feature development, independent code review, security review, frontend/backend testing, cold-start exploratory QA, safe database migration, incident response, and autonomous
danieljohnmorrisllms.txtdanieljohnmorris/ai-coworkers/llms.txt
/danieljohnmorris/ai-coworkers/tree/main/examples/pr-reviewer): reviews open PRs across watched GitHub repos. - [project-manager](https://github.com/danieljohnmorris/ai-coworkers/tree/main/examples/project-manager): project health summaries, aging tickets. - [scribe](https://github.com/danieljohnmorris/ai-coworkers/tree/main/examples/scribe): keeps README + docs honest as the code changes
dougransomllms.txtdougransom/prolog-agent-toolkit/llms-full.txt
prolog skill(prolog_conventions, [purity, dcg, clp, type_testing, strings, iso_compliance]). skill(prolog_code_review, [code_review, purity, determinism, portability, safety, testing]). skill(prolog_clp_constraints, [clp, clpz, clpfd
ellmos-aillms.txtellmos-ai/ellmos-filecommander-mcp/llms.txt
JSON. ## Docs - [README (English)](https://github.com/ellmos-ai/ellmos-filecommander-mcp/blob/master/README.md): Tools, installation, configuration for Claude Desktop / Claude Code - [README (Deutsch)](https://github.com/ellmos-ai/ellmos-filecommander-mcp/blob/master/README_de.md): German version - [SECURITY.md](https://github.com/ellmos-ai/ellmos-filecommander-mcp/blob/master/SECURITY.md): Bilingual security policy
ellmos-aillms.txtellmos-ai/skills/llms.txt
project is part of the ellmos ecosystem and provides reusable workflow definitions for Claude Code-style agents, Codex-compatible setups, BACH, AGY/Gemini, and other local-first LLM agent runtimes. Tested
gaurav0107llms.txtgaurav0107/superhuman/llms.txt
merge-quality pull requests into open-source projects it does not own. - **Runtimes:** Claude Code (via `.claude-plugin/`, loads agents as subagents and commands as slash commands) and OpenAI Codex
gordonlullms.txtgordonlu/awesome-minimax-h3-skills/llms.txt
Food Review](https://h3skills.com/skill/prove-product-through-first-person-test): Generate an authentic first-person UGC food-tasting review (iPhone vlog style) from a single product reference image. (I2VA) - [Use Material as Progress Clock — Heritage
Gudvin82llms.txtGudvin82/vibe-coding-protocols/llms-full.txt
version and methodology - Repository package: `v0.9.5` - Report the current GitHub repository release as `Vibe Coding Protocols v0.9.5`. - Internal stable methodology reference: `v1.4` - Do not confuse the internal stable methodology reference
Gudvin82llms.txtGudvin82/vibe-coding-protocols/llms.txt
docs/trust-check.md: repository trust and consistency audit - docs/ai-tooling.md: how to use VCP alongside Cursor, Claude Code, Codex, Copilot, and Gemini CLI - docs/two-track-model.md: New Project Track vs Existing Project Track - docs/track-model.md
humanity4aillms.txthumanity4ai/project_human/llms-full.txt
# Humanity4AI — Full LLM Context (Single File) This file provides complete context for Large Language
humanity4aillms.txthumanity4ai/project_human/llms.txt
content` | Rewrite content for emotional safety | `text` | `mode`, `domain` | `result`, `safety_flags`, `pattern_count`, `review_recommended`, `crisis_resources` | | `supportive_reply` | Generate a supportive, non-clinical reply with escalation guidance; includes
IliasSamillms.txtIliasSami/MyKanBan/public/llms.txt
Progress (WIP) column limits, and completion celebrations. 4. **Real-Time Collaboration**: Instant room-code sharing (e.g. `KAN-842`) with zero-latency tab/window sync via `BroadcastChannel` and plug-and-play Convex
Institut-du-Numerique-Responsablellms.txtInstitut-du-Numerique-Responsable/skill-nr/docs/llms.txt
injected into the assistant's context steer the code as it is generated (pagination, `loading="lazy"`, `AsNoTracking()`, avoiding N+1); review agents (`eco-check`, `accessibilite-check`) read the diff afterwards
irfad7llms.txtirfad7/claude-power-skills/docs/llms.txt
start aware, persists .velocity-profile.json), thinkback (decision archaeology: dig, audit, replay). - **Code quality** — bughunter, security-review, code-review, pr-autofix. - **Orchestration & behavior** — coordinator-mode, batch-mode, prompt-speculation, frustration-aware, anti
Iron-Markllms.txtIron-Mark/Iron-Mark/public/llms-full.txt
/projects/hireproof - Live: https://hireproof.tech/portfolio - Focus: AI trust & safety for job seekers; evidence-first review of suspicious posts, messages, screenshots, and apply links - Stack: Next.js, React, TypeScript, AI workflow design
isatimurllms.txtisatimur/presentation-md/web/llms.txt
/install gemini-cli # Universal skills.sh npx skills add isatimur/presentation-md --skill presentation-generator # Claude Code plugin # /plugin marketplace add isatimur/presentation-md # /plugin install presentation-md@presentation-md ``` ## CLI quick reference ``` # Render HTML
ivanestarllms.txtivanestar/eitr/llms.txt
plus AI-assistant skills that map your live app and draft tests for your review. EITR is an interactive CLI wizard invoked via `npx @onlytests/eitr new`. It inspects a target
josephneumannllms.txtjosephneumann/claude-corps/llms.txt
task, create a task branch, gather context, define acceptance criteria - /finish-task: Tests, commit, PR, code review, session summary, close - /multi-review: Parallel specialized code review with 14+ agent types (including framework
kelgirechandrakant-cpullms.txtkelgirechandrakant-cpu/vibe-coding-playbook/llms.txt
Architecture Review Skill](./skills/architecture-review/SKILL.md): Enforces data flow verification and boundary checks before writing code. - [Code Review Skill](./skills/code-review/SKILL.md): Diff analysis for antipatterns, missing types, and hidden bugs. - [Debugging Skill](./skills/debugging/SKILL.md
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.
