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.
openqodexllms.txtopenqodex/openqodex/docs/llms.txt
OpenQodex for AI agents](for-agents.md) - [Agents](agents.md) - [Benchmark results](benchmark-results.md) - [The review benchmark](benchmark.md) - [Code review in Claude Code](claude-code-review.md) - [Commands](cli.md) - [Configuration](config.md) - [Custom scanners](custom-scanners.md) - [FAQ](faq.md) - [GitHub
sno-aillms.txtsno-ai/sno-station/llms.txt
Station > Open-source software that turns the agents a developer already uses (Claude Code, > Codex, Cursor, Hermes Agent, OpenClaw) into one squad on their own machine (Sno Station
hanzohanzhellms.txthanzohanzhe/Grandet/llms.txt
raw.githubusercontent.com/hanzohanzhe/Grandet/main/data/RELEASE-v3.json : schema, SHA-256, observation policy and release status - https://raw.githubusercontent.com/hanzohanzhe/Grandet/main/data/free-tokens-v3.json : complete reviewed v3 records and conditions - https://raw.githubusercontent.com/hanzohanzhe/Grandet/main/CATALOGUE-v3.md : full bilingual records - https://raw.githubusercontent.com/hanzohanzhe/Grandet/main/METHODOLOGY.md : how the data
agentic-communityPipes a download into a shellllms.txtagentic-community/mcp-gateway-registry/docs/llms.txt
Agent State Management **Agent State File (registry/agents/agent_state.json):** ```json { "agents": { "/code-reviewer": { "path": "/code-reviewer", "name": "Code Reviewer Agent", "enabled": true, "registered_at": "2024-11-09T14:45:00Z", "last_modified
borgheiReads credentialsllms.txtborghei/Claude-Skills/site/llms.txt
posture security across AWS, Azure, and GCP — IAM least privilege, public exposure, encryption, logging... - [Code Reviewer](https://borghei.github.io/Claude-Skills/skills/engineering/code-reviewer.html): Code review automation for TypeScript, JavaScript, Python, Go, Swift, and Kotlin
Jarvis322Deletes or force-pushesllms.txtJarvis322/macos-sysdata/docs/llms-full.txt
downloads; the AI coding tools (Claude Code, Codex, Grok, Copilot, Kilo, Gemini); Claude's local VM bundles and Chrome's on-device model | Review / Manual | | Logs & diagnostics | unified log store
umputunllms.txtumputun/revdiff/site/llms.txt
diffs, files, and documents with inline annotations revdiff is a terminal-based UI for code review and document annotation. It displays diffs from Git, Mercurial, and Jujutsu repositories with syntax
JuliusBrusseellms.txtJuliusBrussee/caveman-code/llms.txt
format-per-model ## Cookbook & API - [Cookbook](docs/cookbook.md): GitHub Actions, multi-agent review, daemon pair programming - [Comparison](docs/comparison.md): Caveman Code vs Claude Code / Codex / Aider / Crush / opencode - [Troubleshooting](docs/troubleshooting.md): install, auth
MartinDelophyllms.txtMartinDelophy/ai-video-editor/public/llms.txt
multi-track timeline editing, visual keyframes and MP4/WebM export. Canonical site: https://video-editor.ai-creator.top/ Source code: https://github.com/MartinDelophy/ai-video-editor License: MIT ## Primary pages - [Open the editor](https://video-editor.ai-creator.top/): The live
basellms.txtbase/base/llms-full.txt
CLAUDE.md](CLAUDE.md): Repo coding conventions for agents: crate naming, lib.rs and module layout, Cargo manifest rules, doc and lint policy, tracing style, testing and mocking rules, review expectations. - [CONTRIBUTING.md](CONTRIBUTING.md
basellms.txtbase/base/llms.txt
CLAUDE.md](CLAUDE.md): Repo coding conventions for agents: crate naming, lib.rs and module layout, Cargo manifest rules, doc and lint policy, tracing style, testing and mocking rules, review expectations. - [CONTRIBUTING.md](CONTRIBUTING.md
openflowkitllms.txtopenflowkit/openflowkit/public/llms.txt
repo's architecture `discover_architecture` with `{ path }` proposes a C4 workspace (`dsl`) from the code. Review its names, `create_diagram` with it, and write the text to `architecture.ofk
GarethManningllms.txtGarethManning/education-agent-skills/llms.txt
science/](https://github.com/GarethManning/education-agent-skills/tree/main/skills/memory-learning-science): 8 skills — retrieval practice, spaced practice, interleaving, cognitive load, dual coding, elaborative interrogation, feedback - [self-regulated-learning/](https://github.com/GarethManning/education-agent-skills/tree/main/skills/self-regulated-learning): 5 skills — metacognition, self-regulation scaffolds
laolaoshirenllms.txtlaolaoshiren/claude-code-skills-zh/docs/llms.txt
全局）或项目内 `.claude/skills/`（项目级） 当前精选数量与最近更新日期以 README 顶部徽章为准（由自动维护任务同步），此处不再重复硬编码，避免与实际数据脱节。 ## 值得先装的 5 个原创技能 - zh-code-reviewer：中文代码审查，输出中文审查报告 — https://github.com/laolaoshiren/claude-code-skills-zh/tree/main/skills/zh-code-reviewer - zh-readme：先分析项目，再生成中文 README — https://github.com/laolaoshiren/claude-code-skills-zh/tree/main/skills/zh-readme
promptise-comReads credentialsllms.txtpromptise-com/Foundry/llms-full.txt
Data Analysis Agent](guides/lab-data-analysis.md): SQL queries, cross-table analysis, specialized reasoning pattern - [Lab: Code Review Agent](guides/lab-code-review.md): Adversarial critique, per-node models, security scanning - [Lab: MCPcast Your SaaS API](guides/lab-mcpcast-storefront.md
promptise-comReads credentialsllms.txtpromptise-com/Foundry/llms.txt
docs.promptise.com/core/engine-skills/): Pre-configured node factories for agent tasks such as web research, code review, data analysis, fact checking, planning and summarizing, all overridable. - [Path-Scoped Skills for Reasoning Graphs
AVIDS2Reads credentialsllms.txtAVIDS2/memorix/llms-full.txt
evidence can be requalified when code moves. - **Claim Ledger** keeps provenance, confidence, conflicts, and lifecycle state separate from prose. - **Knowledge Workspace** compiles claims into reviewable Markdown proposals; it does
AVIDS2Reads credentialsllms.txtAVIDS2/memorix/llms.txt
provenance - **Code State**: versioned local file/symbol/import facts and freshness links that keep memory tied to the current checkout - **Claim Ledger and Knowledge Workspace**: source-backed claims compiled into reviewable Markdown
ningbainbllms.txtningbainb/deepseek-harness-desktop/website/llms.txt
read acknowledgements bound normal streaming by count and serialized bytes, preserving complete ordered text, code, history and tool output through pause/resume and cancellation. Oversized-history/lookahead exceptions mean this
kinopio-clubllms.txtkinopio-club/kinopio-client/public/llms.txt
features - real-time collaboration with privacy settings - backlinked [[Tags]] - add images, websites, and PDFs - code blocks - trackable todos - groups for shared spaces - quick capture browser extensions - save as pdf - mobile
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.
