How real projects summarise themselves for language models.
ratel-aillms.txtratel-ai/ratel/llms.txt
ratel-local repo `ratel-ai/ratel-mcp`. ## Optional - [Contributing](https://github.com/ratel-ai/ratel/blob/main/CONTRIBUTING.md): Build & test, branching, TDD policy, ADR workflow, commit messages. - [AGENTS.md](https://github.com/ratel-ai/ratel/blob/main/AGENTS.md): In-repo operating manual
SponsioLabsllms.txtSponsioLabs/Sponsio/llms-full.txt
install --pre "sponsio[all]" ``` --- ## Python support Python 3.10 and newer. Older versions are not tested. ## TypeScript The TypeScript deterministic engine ships separately: ```bash npm install @sponsio/sdk@alpha ``` See [TypeScript integrations
Kevin-Liu-01llms.txtKevin-Liu-01/Claude-of-Tanks/public/llms-full.txt
Geometry/profile changes are verified through combat-anatomy generation, articulation checks, asset checks, focused profile tests, and targeted release gates. The Tank Gallery at https://cot.kevinliu.studio/gallery exposes the production fleet
Kevin-Liu-01llms.txtKevin-Liu-01/Claude-of-Tanks/public/llms.txt
deterministic perception, route planning, weapon-aware fire control, friendly-fire safety, survival, and authority tests. - [Multiplayer authority](https://cot.kevinliu.studio/docs/multiplayer): Rooms, authoritative state, input intent, filtered snapshots, prediction, spotting, bots
pranshuchittorallms.txtpranshuchittora/simvyn/llms.txt
overview. - [Agent setup](https://github.com/pranshuchittora/simvyn/blob/main/docs/agents.md): Pi and portable skill installation, local checkout testing, output handling, and known limitations. - [simvyn Agent Skill](https://github.com/pranshuchittora/simvyn/blob/main/skills/simvyn/SKILL.md): Entry point for agents using
Keesan12llms.txtKeesan12/martin-loop/llms-full.txt
replace Git, GitHub, CI/CD, dedicated security scanners, observability platforms, human code review, or all testing infrastructure. It can connect work that uses those systems into one surrounding run and handoff
jamditisllms.txtjamditis/claude-skills-journalism/docs/llms.txt
email newsletters and subscriber workflows ### Development - vibe-coding, AI-assisted development for non-engineers - test-first-bugs, test-driven bug fixing - one-way-door, flag irreversible architectural decisions - electron
carloslfullms.txtcarloslfu/slotstream/llms-full.txt
Sevra on Slotstream: private, personal AI optimized for your computer.** > Sevra will choose a tested model for your hardware, keep that choice current > as models improve, and let you control
carloslfullms.txtcarloslfu/slotstream/llms.txt
with different settings. The README gives rough planning ranges; the hardware guide lists the tested configurations with installed RAM, release and process memory target. The upper High/Ultra estimates assume
mcpwarellms.txtmcpware/cross-code-organizer/llms.txt
scopes. ## Docs - [AI Index](https://github.com/mcpware/cross-code-organizer/blob/main/AI_INDEX.md): Canonical AI-oriented map of architecture, behavior, tests, drift, and file responsibilities - [README](https://github.com/mcpware/cross-code-organizer/blob/main/README.md): Full documentation, features, comparison, quick start
openaccountantsllms.txtopenaccountants/openaccountants/llms-full.txt
# OpenAccountants — GitHub Skills Repository > Open-source Tax Guides ("skills") for AI agents. 1,998
oxbshwllms.txtoxbshw/watch-skill/llms.txt
variables - [Agent matrix](https://github.com/oxbshw/watch-skill/blob/main/docs/agents/README.md): per-client setup and what has been machine-tested - [Architecture](https://github.com/oxbshw/watch-skill/blob/main/docs/architecture.md): data model, provider boundaries, extension points - [THE LOOP](https://github.com/oxbshw/watch-skill/blob/main/docs/guides/the-loop.md):
timwuhaotianllms.txttimwuhaotian/the-pair/llms.txt
Pair separates planning, implementation, and review so another agent can catch hallucinations, missing tests, unsafe edits, or incomplete work before changes reach the codebase. ## Canonical URLs - Repository: https://github.com/timwuhaotian/the-pair
cheapestinferencellms.txtcheapestinference/claude-auto-retry/llms.txt
with safe fallbacks for invalid values. - No runtime dependencies; Node >= 18; MIT license; 200+ tests. ## Docs - [README](https://github.com/cheapestinference/claude-auto-retry/blob/master/README.md): features, configuration, every error render detected - [DESIGN-NOTES](https://github.com
LangChainllms.txtlangchain-ai/langchain-aws/llms-full.txt
response = secure_llm.secure_invoke("Tell me about data privacy laws") ``` ## Testing and Monitoring ### Integration Testing ```python import pytest from unittest.mock import patch, MagicMock from langchain_aws import ChatBedrock, BedrockEmbeddings class TestLangChainAWS
griddynamicsllms.txtgriddynamics/rosetta/llms-full.txt
questions, never stop once coding. Rosetta: approval gates after specs/plans, before risky actions, before tests continue; batch 5–10 questions, prioritized by impact, 1 decision/question; stop+ask vs guess
Sentryllms.txtgetsentry/vitest-evals/packages/docs/public/llms.txt
vitest-evals > Harness-backed AI evaluation tests on top of Vitest. `vitest-evals` lets teams write evals as ordinary Vitest tests while still capturing the AI-specific data needed
raysonmengllms.txtraysonmeng/agent-bridge/site/llms.txt
Linux (Windows not officially supported yet) - Runtime: Bun (required — Node.js alone is not sufficient) - Tests: 1,700+ - Runs 100% locally; no accounts, API keys, or servers needed for AgentBridge itself
claude-did-thisllms.txtclaude-did-this/MCPControl/docs/llms-full.txt
Diagnostics** * Implement health checks * Monitor connection state * Track resource usage * Profile performance 3. **Testing** * Test different transports * Verify error handling * Check edge cases * Load test servers # Prompts Source: https://modelcontextprotocol.io
88linllms.txt88lin/computer-repair-skill/docs/llms.txt
company data — for offboarding or device reassignment - `backup-verify-restore` — Backup Verify & Restore Test / 备份验证与抽样恢复 [Cross-platform]: Verify backup integrity by checking status, timestamps, and testing a real file restore
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.
