How real projects summarise themselves for language models.
joris887llms.txtjoris887/exosuit/scaffold/llms.txt
server vs built-in tool selection guide with decision matrix ## Native Agents (.claude/agents/) - .claude/agents/code-reviewer.md: Code review with severity classification (correctness, conventions, security lenses) - .claude/agents/spec-reviewer.md: Spec compliance verification with file:line
vassiliylakhoninllms.txtvassiliylakhonin/global-think-tank-analyst/llms.txt
concrete watch-next indicators and decision triggers; - examples, a learning path, and a human review checklist for the above. What this repository is not: - not a factuality verifier, source retriever
ahnafnafeellms.txtahnafnafee/ahnafnafee.dev/public/llms-full.txt
people and games you care about. A game library carries critic and player scores, reviews, and trivia. Quests hand out XP and collectibles, and a customizable Player Card pulls cosmetics
imMamdouhaboammarllms.txtimMamdouhaboammar/get-fable/public/llms.txt
coding agents. - [External Integrations Guide](https://github.com/imMamdouhaboammar/get-fable/blob/master/docs/INTEGRATIONS.md): - **GitHub**: Automatic PR reviews, branch status checks, issue triage. - [Fable Coding Lifecycle v2](https://github.com/imMamdouhaboammar/get-fable/blob/master/docs/LIFECYCLE.md): │ (route task / intent) - [ChatGPT, Codex
MSKazemillms.txtMSKazemi/novafabric/llms.txt
agent, a model run, an HPC training job, a notebook cell — with no application code changes, and produces a portable, schema-valid, secret-redacted evidence folder called a **capsule**. Capsules
ndisisndllms.txtndisisnd/msg/llms.txt
specialist subagents per wave - [eng](https://raw.githubusercontent.com/ndisisnd/msg/main/.claude/skills/eng/SKILL.md): `--plan` / `--build` / `--review` — the only skill that writes product code - [pre-merge](https://raw.githubusercontent.com/ndisisnd/msg/main/.claude/skills/pre-merge/SKILL.md): the CI gate — manifest-driven pipeline executor
PIsbergllms.txtPIsberg/skill3/llms-full.txt
security-critical. Do not weaken security properties. Every change requires security review. ### se.deversity.skill3.llm.AnthropicChatModel - Security-critical code (aspect: Anthropic API credential handling and hosted-provider network egress). - Never weaken security properties
PIsbergllms.txtPIsberg/skill3/llms.txt
network egress]. Do not weaken security properties. Flag any change for security review. - [LlmProviderFactory](se.deversity.skill3.llm.LlmProviderFactory): Security-critical code [LLM provider credential resolution and model selection]. Do not weaken security properties
purinzanllms.txtpurinzan/gx3-cli-mcp/llms.txt
right boundary. - Static review: duplicate coils, multi-writers, latches with no reset, contacts that can never close, contradictory comments. - Letting an AI agent (Claude Desktop, Claude Code, Cursor
0spoonllms.txt0spoon/seamless/docs/llms-full.txt
setup covers code sessions inside the Claude desktop app - they share `~/.claude`. See [Claude Code setup](/claude-code/). **Codex:** Start Codex in any git repo - restart it first
berkayturancillms.txtberkayturanci/keel/website/llms.txt
turns coding agents into work owners. It is a project-neutral, multi-agent > workflow backbone that drives a GitHub issue from intake to done: select → > branch → implement → CI → review → test
bootgsllms.txtbootgs/skills/llms.txt
against the live Google Workspace Marketplace review checklist and guides publishing. ## Reference - [README](README.md): Installation for Claude Code, Gemini CLI, Cursor, and any agent via `npx skills add`; the CRUD
KhaledSaeed18llms.txtKhaledSaeed18/dotclaude/site/llms.txt
accurate but nobody can follow it. Plugins: docs. - [adversarial-reviewer](https://github.com/KhaledSaeed18/dotclaude/tree/main/skills/engineering/adversarial-reviewer) (engineering): Review code through three hostile personas - the Saboteur, the New Hire, and the Security Auditor - each
littlebearappsllms.txtlittlebearapps/contextdocs/llms-full.txt
breaking changes before they affect your context files - 🔌 **Works with 8 AI tools** — Claude Code and OpenCode natively; generated files also work with Codex CLI, GitHub Copilot, Cursor, Windsurf, Cline
ma-nucho-prollms.txtma-nucho-pro/Wonder-Woman-Claude-Code/llms.txt
verification, source verification, citation entailment, adversarial review, multi-agent verification, 16 judge AI, reality filter, LLM factuality, evidence-based AI, Claude skill, Claude Code subagents, ChatGPT Agent Skills, Codex skills
melaya-labsllms.txtmelaya-labs/melaya/llms.txt
Every order waits for your approval. ## Core capabilities - 8,000+ agentic tools across web, code, data, ops, communication, files, cloud, social, RAG, device actions, an MCP bridge
nikolay-ellms.txtnikolay-e/diffctx/docs/llms.txt
range, or an uncommitted working tree), and the output is the surrounding code needed to review it — callers, type definitions, imports, config dependencies — packed to fit a token budget. This
omar-y-abdillms.txtomar-y-abdi/furl-ctx/llms.txt
import compress` ## Docs - [Get started](README.md#quick-install): two-command installs for Claude Code (automatic hooks + MCP + skill) and Codex (MCP + skill); no `pip install` needed. - [How it works](LIBRARY.md
opencuellms.txtopencue/cuecards/docs/llms-full.txt
clinerules + cline_mcp_settings.json - Google Gemini CLI → ~/.gemini/skills/*.md - GitHub Copilot → .github/copilot-instructions.md - Windsurf → .windsurfrules + .windsurf/mcp.json - Roo Code → .roo/rules/*.md + .roo/mcp.json - Sourcegraph Amp → AGENTS.md + .amp/mcp.json - Aider → .aider.conventions.md Common flags: --all, --profile
Pseudogiant-xrllms.txtPseudogiant-xr/Pseudolife-MCP/llms-full.txt
stdio shim, LAN sharing, data layout, backups, schema history | | [Providers](docs/guide/providers.md) | Capability matrix per coding agent, memory instruction layers, AGENTS.md standard, Codex hook setup and verification, writer ids | | [Retrieval](docs/guide/retrieval.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.
