How real projects summarise themselves for language models.
sanhuang520-ship-itllms.txtsanhuang520-ship-it/awesome-chinese-ai-tools/llms.txt
Chinese Agent Skills / Chinese AI Skills guide](https://sanhuang520-ship-it.github.io/awesome-chinese-ai-tools/chinese-agent-skills/): English path to browse, install, review, reproduce and contribute with explicit evidence boundaries - [Codex 兼容性实测](https://sanhuang520-ship-it.github.io/awesome-chinese-ai-tools/compatibility/): 13 个原创 Skill
ankit373llms.txtankit373/hydra/docs/llms.txt
task JSON file - `hyctl edit`: scoped, validated, rollback-safe single-file edit - `hyctl review`: code review - `hyctl init`: first-run wizard: discover heads, choose your cortex - `hyctl upgrade`: re-runs
confused-aillms.txtconfused-ai/personaforge/docs/llms-full.txt
# personaforge — Full Documentation > This file is the complete, machine-readable documentation for personaforge (1.1.0
khaskyllms.txtkhasky/awesome-agent-skills/llms.txt
Awesome Agent Skills > Skills for AI coding agents in the Agent Skills (agentskills.io) format: code review, debugging, security audits, refactoring, and cleaning up AI-written code and text. Each skill
zhurong2020llms.txtzhurong2020/pyobfus/docs/llms.txt
runtime anti-debug cannot switch it off. Informational only, does not change the exit code - `pyobfus --init src/` — auto-detect framework and generate `pyobfus.yaml` - `pyobfus --unmap --trace error.log --mapping mapping.json
zhurong2020llms.txtzhurong2020/pyobfus/llms-full.txt
deterrent, not cryptographic. - `eval()` / `exec()` with obfuscated code may need manual exclusions. - Debugging obfuscated code without a mapping.json is intentionally harder; keep mapping files for any build you might need
AbdumajidRashidovllms.txtAbdumajidRashidov/mycop/docs/llms.txt
started via `mycop mcp` - Enables Claude Code, Cursor, Windsurf, Codex CLI, Gemini CLI, and other agentic tools to call mycop's scanning and review capabilities directly - 5 tools: scan, list
abhinavg6llms.txtabhinavg6/yutha/docs/llms.txt
yutha.ai/examples/customer-support/): classifier + L1 + L2 escalation, supervisor-required for refunds above a threshold. - [Code review crew with security boundaries](https://yutha.ai/examples/code-review/): reviewer + auto-fix agents with capability gates around
aiapplications001-artllms.txtaiapplications001-art/seo-page-creator-agent/llms.txt
product category pages. It is designed for agentic coding tools and AI-assisted content operations that need source-backed, editorially reviewable SEO assets rather than generic AI drafts. Core outputs
AliOsmllms.txtAliOsm/pastehtml.dev/public/llms.txt
OAuth in the user's browser -- there is no pht_ key to handle. # Claude Code claude mcp add --transport http pastehtml https://pastehtml.dev/mcp # Codex codex mcp add pastehtml
answerLoopsllms.txtanswerLoops/answerLoops/public/llms.txt
content, and Notion pages; promote reviewed ticket resolutions. Notion content is initially unpublished. - **Answer review:** a separate AI assessment and configurable automatic-reply settings. Confidence scores do not guarantee correctness
ArcticFox2029llms.txtArcticFox2029/chamnan/llms.txt
anything unrecognised still works and `--window` takes an exact number. - **Agents**: 22 adapters. Claude Code and Gemini CLI receive a real session hook; every other agent receives a file
babarmuhammadllms.txtbabarmuhammad/archeus/docs/llms.txt
/getting-started/): what archeus is, the three surfaces it offers (terminal UI, desktop app, Claude Code plugin), and where to go next. - [Installation](https://docs.claudectl.space/installation/): requirements, pipx/pip, running from
berkayturancillms.txtberkayturanci/voicebridge/site/llms.txt
agent: works with Claude Code, Codex, Antigravity, Ollama, Aider, and Gemini CLI - Full-duplex WebSocket live sync: multi-device synchronization over `/ws` - Interactive tool approvals: review shell commands and tool
D4umakllms.txtD4umak/linkedin-outreach-mcp/llms-full.txt
Cursor (manual) Settings > MCP > "Add new MCP server" > Name: `heylead`, Command: `uvx heylead` ### Claude Code ``` claude mcp add heylead -- uvx heylead ``` ### Any MCP client (manual) ```json { "heylead": { "command": "uvx", "args
dgeniollms.txtdgenio/contextweaver/llms-full.txt
Clone the repository and install that checkout so the maintained example fixtures and the code under evaluation are guaranteed to match: Commands below use `python3`, matching the repository's documented
dgeniollms.txtdgenio/contextweaver/llms.txt
building a complete agent loop - [Error Reference](docs/errors.md): Exception hierarchy with stable error codes, causes, and fixes ## Agent Context - [Agent Architecture](docs/agent-context/architecture.md): Non-obvious architectural guidance, design tradeoffs, and async/sync
gauravs19llms.txtgauravs19/enterprise-architecture-skill/llms.txt
evals. - Related project by the same author: **spring-boot-microservices** (a Claude Code skill for building and reviewing Spring Boot microservices
hermes-labs-aillms.txthermes-labs-ai/hermeneutic/llms.txt
Python 3.10+ toolkit for three distinct jobs: 1. mine correction triples from supported Claude Code, Codex, and OpenAI-style chat logs; 2. optionally retrieve similar prior corrections with a local
hermes-labs-aillms.txthermes-labs-ai/hermes-blind/llms.txt
user text and should be reviewed before sharing. ## Find a supported session log Blind reads an explicit local JSONL path and currently supports Claude Code and Codex session logs
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.
