How real projects summarise themselves for language models.
sin4chllms.txtsin4ch/nigerian-fintech-llms-txt/opay/llms.txt
minor units (100 kobos = 1 NGN, 100 cents = 1 USD) - Sandbox environment available for testing before production - Webhooks provide real-time transaction status updates ## Docs - [OPay Documentation Home](https://documentation.opaycheckout.com
sin4chllms.txtsin4ch/nigerian-fintech-llms-txt/paystack/llms.txt
KES/ZAR/USD) - API requests require authentication: secret keys (server-side) or public keys (client-side) - Test mode uses test API keys (`sk_test_*`, `pk_test_*`); live mode uses live keys
sunholo-datallms.txtsunholo-data/ailang/docs/llms.txt
/docs/reference/no-loops) | [Go Interop](https://ailang.sunholo.com/docs/guides/go-interop) --- ## Development ```bash make install # Build and install make test # Run all tests make repl # Start REPL make lint # Run linter ``` **Guides:** - [Development Guide
xu-xiangllms.txtxu-xiang/awesome-top-skills/llms.txt
facebook/react;verify;A skill for validating changes before committing or checking React contribution requirements. test;facebook/react;test;A skill for running tests on React core with support for multiple channels
axelfreemanllms.txtaxelfreeman/marketing-mindset/docs/llms.txt
some SaaS) - Five principles: no stale sources, 3-month horizon, the user moves first, test fast, marketing runs ahead of the product - Sources of truth: competitors first; stop-list = Product
axelfreemanllms.txtaxelfreeman/marketing-mindset/llms.txt
some SaaS) - Five principles: no stale sources, 3-month horizon, the user moves first, test fast, marketing runs ahead of the product - Sources of truth: competitors first; stop-list = Product
elon-choollms.txtelon-choo/fablever/llms.txt
fablever 43% (26/60); 10 tasks × 6 reps = 180 runs, better on 10/10 tasks, sign test p=0.002 — `cat eval/codex-native-ab/RESULTS-confirmatory.md` - Scope violations, deterministic no judge: fablever 0% vs plain Claude
fishzjpllms.txtfishzjp/qa-skills/llms.txt
host — Claude Code, Cursor, Codex, OpenCode and 70+ more — work like a senior software testing engineer. Full lifecycle: requirement analysis with clarification checkpoints, risk-based test strategy with
Koukyosyumeillms.txtKoukyosyumei/h5i-db/docs/llms-full.txt
semantics deliberately, so bucketed rollups port as-is. - **ASOF joins**: supported, and semantically differential-tested against DuckDB as the oracle (ties, NULLs, strict/non-strict). The syntax differs slightly, using `ASOF JOIN
Koukyosyumeillms.txtKoukyosyumei/h5i-db/docs/llms.txt
cointegration pair strategy on real prices. We scan candidate pairs with an Engle-Granger test, build a rolling hedge ratio, compute the spread z-score… - [EWMA volatility and vol-targeted
oomkapwnllms.txtoomkapwn/enquire-mcp/llms.txt
remove them, so inspect/recover and purge them manually as documented in `SECURITY.md` - 2272 unit tests declared; required PR CI runs the general Linux suite plus 8 Windows-only path contracts
thought2codellms.txtthought2code/mcp-annotated-java-sdk/llms-full.txt
with the official MCP Java SDK. - Make plain Java MCP servers faster to write, test, and ship. - Improve compile-time validation, generated bindings, schema support, and examples. - Avoid competing with
thought2codellms.txtthought2code/mcp-annotated-java-sdk/llms.txt
with the official MCP Java SDK. - Make plain Java MCP servers faster to write, test, and ship. - Improve compile-time validation, generated bindings, schema support, and examples. - Avoid competing with
Aboudjemllms.txtAboudjem/solidity-style-guide/llms.txt
namespaced storage, transient storage, custom errors in `require`, named imports, NatSpec, and Foundry testing conventions. The canonical source is `README.md`. This file is a machine-friendly index for LLMs. ## Docs
borgheillms.txtborghei/AI-Skills-German-Law/site/llms.txt
DORA, wesentliche... - [Dora Resilienztests](https://borghei.github.io/AI-Skills-German-Law/SKILLS/dora/dora-resilienztests.html): Aufbau eines DORA-Programms für Tests der digitalen operationalen Resilienz – allgemeine Testanforderungen Art. 24 DORA, Testmethoden... - [Dora Vorfallsmeldung](https://borghei.github.io/AI-Skills-German-Law/SKILLS/dora/dora-vorfallsmeldung.html): Klassifizierung
jdpolaskyllms.txtjdpolasky/chief-of-staff-2/llms.txt
rather than Notion. - [docs/notion-vs-obsidian-deep.md](https://raw.githubusercontent.com/jdpolasky/chief-of-staff-2/main/docs/notion-vs-obsidian-deep.md): The full analysis, with pricing and live tests. - [docs/laws.md](https://raw.githubusercontent.com/jdpolasky/chief-of-staff-2/main/docs/laws.md): Thirteen laws governing the system, each with the mistake that produced
paramount-engineeringllms.txtparamount-engineering/roku-dev-studio/docs/llms.txt
traffic, attach a real socket debugger (breakpoints, step execution, variables), automate end-to-end test flows with Action Scripts, and let AI agents (Claude, Cursor, VS Code) drive a real
odds-apillms.txtodds-api/odds-api/llms.txt
discovery - arbitrage detection - positive EV detection - line movement tracking - mock odds data for local testing ## Primary files - `openapi.yaml` - `openapi.json` - `AGENTS.md` - `sdks/typescript` - `sdks/python` - `mcp-server` - `examples/minimal-rest` - `examples/javascript` - `examples/python` - `postman/odds-api.postman_collection.json` ## Integration options
racciolyllms.txtraccioly/docguard/llms-full.txt
opposite controls, reduces them under an explicit predicate, derives duplicate identities, and emits test-only contributions | `cli/feedback-fixture.mjs`, `cli/commands/feedback.mjs`, `schemas/docguard-feedback-fixture.schema.json` | Publication remains user-controlled; contribution generation requires reviewed redaction, scope
racciolyllms.txtraccioly/docguard/llms.txt
/REQUIREMENTS.md): REQUIREMENTS documentation - [SECURITY](docs-canonical/SECURITY.md): Authentication, authorization, secrets management, and security policies - [TEST-SPEC](docs-canonical/TEST-SPEC.md): Test coverage requirements, testing strategy, and quality rules ## Optional - [DRIFT
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.
