How real projects summarise themselves for language models.
danicatllms.txtdanicat/skills/llms.txt
integrity, guards against regressions with compiler rollback gates, eliminates blind spots via Selene mutation testing, and enables fast test and coverage analytics with TestQuery SQLite queries. Activate when writing
dshakesllms.txtdshakes/distil/docs/llms.txt
checks itself: it certifies that the agent's decisions are statistically unchanged (non-inferiority test) rather than assuming it. Zero runtime dependencies. Four ways to use it, and they
heuremallms.txtheurema/signum/llms.txt
scoring (7 dimensions, /115), prose checks, optional multi-model spec validation, and Clover reconstruction test. EXECUTE: Engineer agent implements code against the contract. Repair loop retries up to 3 times
Kevin-Liu-01llms.txtKevin-Liu-01/Loop/public/llms.txt
more). - **Sandbox**: An isolated agent chat environment with Vercel Sandbox sessions for testing skills interactively. ## Key Pages - / — Skill catalog home (browse, search, filter by category) - /skills/{slug}/{version} — Skill detail
las-teamllms.txtlas-team/lastest/public/llms.txt
Lastest > Visual regression testing platform with AI-powered test generation, self-healing selectors, and MCP server for agent integration. ## Overview Lastest records browser interactions, runs Playwright tests, diffs screenshots against
matank001llms.txtmatank001/clodfarm/site/llms.txt
session and merges their branches. - An optional check (e.g. the project's tests) runs before work lands; a failing check sends the agent back to fix it. - A budget governor
Microsoftllms.txtmicrosoft/azure-sql-database-container/docs/llms.txt
container > The Azure SQL Database engine, running locally for development and CI. Build and test against the same engine, defaults, and T-SQL you run in the Microsoft Azure cloud
NSPG13llms.txtNSPG13/agent-bounties/site/llms.txt
skill for local or direct-chain fallback. - CLI for repository development and deterministic smoke tests. Do not treat the advanced HTTP tool catalog as the MCP catalog. Use only tools
paladinillms.txtpaladini/mcp-me/llms-full.txt
modelcontextprotocol/sdk - Validation: Zod - YAML: yaml (npm) - CLI: Commander.js - Build: tsup (ESM + DTS) - Tests: Vitest (2205 tests) - Lint: ESLint 9 + Prettier ## Author Fernando Paladini — https://github.com/paladini
paladinillms.txtpaladini/mcp-me/llms.txt
modelcontextprotocol/sdk - Schema validation: Zod - YAML parsing: yaml (npm) - CLI: Commander.js - Build: tsup (ESM + DTS) - Test: Vitest (2205 tests
ssdeanxllms.txtssdeanx/secure-rag-multi-agent/llms.txt
line interface for document indexing and management - [scripts/](scripts/): Utility scripts and automation tools ## Testing - [tests/](tests/): Test suites and testing utilities - [vitest.config.ts](vitest.config.ts): Testing framework configuration - [globalSetup.ts](globalSetup.ts): Global
xi-karillms.txtxi-kari/crossframe-skill/llms.txt
plain-language CrossFrame concept lessons with boundaries, signals, and exercises. - [Debate skill](skills/crossframe-debate/SKILL.md): proposition testing through both sides, premises, evidence, rebuttals, and withdrawal conditions. - [Notebook skill](skills/crossframe-notebook/SKILL.md): bidirectional reading notes
zxpmailllms.txtzxpmail/ReqForge/llms.txt
greenkeeper - **10 Sub-Agents** — implementer, planner, code-reviewer + 4 specialists, feedback-observer, evolution-runner, test-writer - **10 default hooks** — hallucination-gate, pre-commit-check, phase-exit-guard, stop-gate, retry
akustikrauschllms.txtakustikrausch/gonzales/llms.txt
Home Assistant and standalone use. ## What is Gonzales? Gonzales automatically runs internet speed tests at configurable intervals, stores results locally, and provides analytics through a modern web interface. It integrates
alexfrmnllms.txtalexfrmn/murmur/site/llms-full.txt
clients configure --client ` connect the AI client; reload the client afterwards. 7. Send a test message with murmur_request and require a reply. Importing keys confirms only one side
buildkitellms.txtbuildkite/skills/llms.txt
buildkite-preflight Path: skills/buildkite-preflight/SKILL.md Topics: bk preflight, local changes, CI validation, failed jobs, failed tests ### buildkite-agent-runtime Path: skills/buildkite-agent-runtime/SKILL.md Topics: buildkite-agent annotate, artifact upload/download, meta-data set/get, pipeline
cameronryellms.txtcameronrye/activitypub-mcp/public/llms-full.txt
cross-origin gating, `upload-media` content-type validation, audit logging on every write tool - **Testing**: 830+ unit tests plus a daily integration workflow against the live Fediverse ### Architecture The server
cfircoollms.txtcfircoo/claude-code-toolkit/docs/llms.txt
Core Components - [15 Skills](https://github.com/cfircoo/claude-code-toolkit/tree/main/skills): Domain expertise on demand (git, database, security, testing, planning, debugging) - [8 Agents](https://github.com/cfircoo/claude-code-toolkit/tree/main/agents): Autonomous specialists (git-ops, db-expert, pytest-writer
cis2042llms.txtcis2042/product-design-harness/llms-full.txt
agents can move from an idea to working software before a team has tested the product direction. Faster execution increases the cost of weak framing, unsupported claims, and invisible trade
cis2042llms.txtcis2042/product-design-harness/llms.txt
venv .venv - .venv/bin/python -m pip install -r requirements-dev.txt - .venv/bin/python -m unittest discover -s tests - .venv/bin/python scripts/validate.py - .venv/bin/python scripts/check_review.py examples/quick-gate-review.json - .venv/bin/python scripts/check_review.py examples/live-coding-review.json Operating rules: - review User Flow, Evidence Flow
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.
