How real projects summarise themselves for language models.
garrytanllms.txtgarrytan/gstack/gstack/llms.txt
feedback, and iterate. - [/deslop-shared-libs](deslop-shared-libs/SKILL.md): Find worthwhile shared-code extractions in recent work. - [/devex-review](devex-review/SKILL.md): Live developer experience audit. - [/diagram](diagram/SKILL.md): Turn an English description
koala73llms.txtkoala73/worldmonitor/public/llms-full.txt
views - **Custom keyword monitors**: User-defined keyword alerts with word-boundary matching, auto color-coding, and multi-keyword support - **Entity extraction**: Auto-links countries, leaders, organizations across headlines - **Virtual scrolling
Microsoftllms.txtmicrosoft/ai-agents-for-beginners/15-browser-use/llms.txt
output` field containing the structured JSON from step 2. ### 5. `Code – Generate Slack message` A short JS snippet turns the JSON into a nicely-formatted Slack block with emojis
mem0aillms.txtmem0ai/mem0/docs/llms.txt
Code with Mem0](https://docs.mem0.ai/vibecoding) [Both]: Use when the user is in Claude Code, Cursor, or Windsurf and wants memory wired into their editor. - [Platform Overview](https://docs.mem0.ai/platform/overview)
alirezarezvanillms.txtalirezarezvani/claude-skills/docs/llms-full.txt
palette), and three converters: `md-document` (long-form → single-file HTML with TOC/search/code-copy/scrollspy), `md-review` (code-review markdown → 2-column diff + severity annotations), and `md-slides` (markdown deck → single-file
alirezarezvanillms.txtalirezarezvani/claude-skills/docs/llms.txt
/alirezarezvani/claude-skills - **Distribution:** Claude Code plugin marketplace + ClawHub registry. - **Design philosophy:** Algorithm over AI (deterministic code, not LLM calls in tools), documentation-driven, template-heavy, self-contained skills. - **Skill package shape
enescingozllms.txtenescingoz/awesome-n8n-templates/llms.txt
fair-code, source-available workflow automation platform that can be self-hosted. Each template is a JSON workflow example that should be reviewed, configured, and tested before use. ## Template Categories
NirDiamantllms.txtNirDiamant/GenAI_Agents/llms.txt
Self-Healing Code](https://github.com/NirDiamant/GenAI_Agents/blob/main/all_agents_tutorials/self_healing_code.ipynb): Detect a failure, diagnose it and repair the code. - [Trace-Based Agent Evaluation](https://github.com/NirDiamant/GenAI_Agents/blob/main/all_agents_tutorials/trace_based_agent_evaluation.ipynb): Evaluate an agent from its execution traces
tonhowtfllms.txttonhowtf/omniget/llms-full.txt
# OmniGet: full README as plain text > Flattened copy of https://github.com/tonhowtf/omniget/blob/main/README.md without images
lastmile-aillms.txtlastmile-ai/mcp-agent/LLMS.txt
requests, handle flight modifications, cancellations, and lost baggage cases. https://github.com/user-attachments/assets/b314d75d-7945-4de6-965b-7f21eb14a8bd **Link to code**: [examples/workflows/workflow_swarm](./examples/workflows/workflow_swarm/) ## Core Components The following are the building blocks of the mcp-agent framework
anbeimellms.txtanbeime/skill/public/llms-full.txt
postgres-best-practices - **Expo** (3个) - expo-app-design, expo-deployment, upgrading-expo - **Sentry** (7个) - code-review, commit, create-pr, find-bugs 等 - **Better Auth** (3个) - best-practices, commands, create-auth
tw93llms.txttw93/Waza/llms.txt
Code, Codex, Cursor, Antigravity, OpenCode, Pi, and compatible agents. - `think`: pressure-test a requirement and produce a decision-complete plan - `ui`: build or polish a distinctive frontend interface - `check`: review
HKUSTDialllms.txtHKUSTDial/Supervisor-Skills/llms.txt
research discovery, idea evaluation, paper planning, drafting, polishing, figure design and reconstruction, pre-submission review, and AI-assisted research workflow. Usable as a standalone Chinese curriculum at `handbook
Q00llms.txtQ00/ouroboros/llms.txt
that rewrites its own architecture -- a different project with a different design, no shared code. ## Core Concepts - Seed Spec: An immutable YAML specification auto-generated from a Socratic interview. Contains
FlorianBruniauxllms.txtFlorianBruniaux/claude-code-ultimate-guide/llms-full.txt
lets developers interact with Claude directly from the terminal to write, edit, debug, and review code. Unlike IDE plugins, it has full filesystem access, can run shell commands, and works
FlorianBruniauxllms.txtFlorianBruniaux/claude-code-ultimate-guide/llms.txt
privacy and retention, enterprise governance (guardrail tiers, MCP approval workflow, audit trails) - CI/CD and code review: GitHub Actions patterns, the Code Review feature (Teams/Enterprise), multi-provider review pipelines - Verification methods
kenn-iollms.txtkenn-io/agentsview/docs/llms.txt
example `/docs/quickstart/`). ## Product - [AgentsView](https://agentsview.io/index.md): The system of record for your AI coding agents. - [The session intelligence loop](https://agentsview.io/guide.md): A nine-stop tour from session capture
eugeniughelburllms.txteugeniughelbur/obsidian-second-brain/llms.txt
ships on Claude Code only; its agenda / meeting / schedule / reconcile modes consolidate the four former standalone calendar commands.) **Thinking (14)** - synthesis, decisions, learning, reviews, panels, discovery, brainstorming: obsidian-brainstorm, obsidian
dagucloudllms.txtdagucloud/dagu/llms.txt
committed path as `${steps. .outputs. }`. - Do not read attempt-only `${step_id.stdout}`, `${step_id.stderr}`, or `${step_id.exit_code}` from potentially reusable producers. This also applies to `${step_id.output. }` and `${step_id.outputs. }`, including their whole-value
flypythoncomllms.txtflypythoncom/python/llms.txt
Chinese. - `templates/TASK_CONTRACT.md`: Scoped specification template for coding agents. - `templates/IMPLEMENTATION_PLAN.md`: Implementation plan template. - `templates/CODE_REVIEW.md`: Code change review template. - `templates/VERIFICATION.md`: Evidence record for reproducible tests. ## Official Portal - Official Website: https://flypython.com - Website
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.
