How real projects summarise themselves for language models.
sno-aillms.txtsno-ai/mda/llms.txt
implementation spec](apps/cli/IMPL-SPEC.md): Scope, CLI surface, module layout, conformance levels, release model, dependencies, compatibility tests, and out-of-scope items. - [CLI source](apps/cli/src/): TypeScript source for the reference
youichi-udallms.txtyouichi-uda/godot-mcp-pro/llms.txt
buses, effects (reverb, delay, compressor), 2D/3D players - **Navigation** — regions, mesh baking, pathfinding agents - **Automated testing** — test scenarios, assertions, stress testing, UI verification - **Code analysis** — unused resources, signal flow mapping, circular
logicrwllms.txtlogicrw/awesome-jev-projects/public/llms-full.txt
separate Jev scripts were inspected; desktop behavior and end-to-end latency were not tested here. - License: Apache-2.0 - Details: https://logicrw.github.io/awesome-jev-projects/en/projects/jev-desktop/ - Source evidence: https://github.com/lahfir/agent-desktop/blob/7a8e4a10281c7319733aa200fd79501f34529716/README.md - Source evidence
decionisllms.txtdecionis/agent-safe-pipeline/llms-full.txt
github.com/decionis/agent-safe-pipeline/blob/master/spec/intent/v1/README.md, https://github.com/decionis/agent-safe-pipeline/blob/master/spec/intent/v1/schema.json, https://github.com/decionis/agent-safe-pipeline/blob/master/spec/intent/v1/CHANGELOG.md, https://github.com/decionis/agent-safe-pipeline/blob/master/spec/intent/v1/frameworks.md - The Compromised Principal Test (valid identity + valid access ≠ authorized execution: the test, three ways to run it in under
decionisllms.txtdecionis/agent-safe-pipeline/llms.txt
github.com/decionis/agent-safe-pipeline/blob/master/spec/intent/v1/README.md, https://github.com/decionis/agent-safe-pipeline/blob/master/spec/intent/v1/schema.json, https://github.com/decionis/agent-safe-pipeline/blob/master/spec/intent/v1/CHANGELOG.md, https://github.com/decionis/agent-safe-pipeline/blob/master/spec/intent/v1/frameworks.md - The Compromised Principal Test (valid identity + valid access ≠ authorized execution: the test, three ways to run it in under
kydlikebtcllms.txtkydlikebtc/awesome-jev/llms.txt
dates vary by row. These counts do not describe runtime tests or current availability. Jev (https://docs.typesafe.ai/) returns typed decisions rather than text: a `choice` among
minhnv0807llms.txtminhnv0807/ai-business-skills/llms.txt
plan - [Performance Loop (ads cycle)](https://github.com/minhnv0807/ai-business-skills/blob/master/workflows/vi/performance-loop.md): Audience and media plan through tracking, testing, audit, scaling, and next ads plan - [Design Pipeline (T-14 to D+1)](https://github.com
agnt-ggllms.txtagnt-gg/agnt/docs/llms-full.txt
custom provider by ID - **Response**: ```json { "success": true, "message": "Custom provider deleted successfully" } ``` ### Test Custom Provider Connection **POST** `/test` - **Authentication**: Required - **Body**: ```json { "base_url": "https://api.example.com", "api_key": "your
agnt-ggllms.txtagnt-gg/agnt/docs/llms.txt
Firecrawl, GitHub, OpenAI, Google Sheets, and Slack integrations with AuthManager patterns, error handling, and testing. - [Authentication Usage Guide](https://agnt.gg/docs/api/authentication-usage-guide): Practical implementation guide for authentication in plugins and tools
danielrosehillllms.txtdanielrosehill/Claude-Code-Projects-Index/docs/llms.txt
Analyst](https://github.com/danielrosehill/Claude-Data-Analyst-plugin): First-pass data analysis toolkit: correlations, PII flagging, anomalies, hypothesis tests, data dictionaries, and trend analysis on a dataset in a folder. - [Claude Data Wrangler
nirholasllms.txtnirholas/XActions/llms-full.txt
Prisma ORM (`prisma/schema.prisma`) - **Job Queue**: Bull + Redis - **Browser Automation**: Puppeteer + puppeteer-extra-plugin-stealth - **Testing**: Vitest 4.x (config: `vitest.config.js`); the suite is offline and runs in CI on Node
evolution-foundationllms.txtevolution-foundation/evo-nexus/docs/llms-full.txt
visualizations in Evolution theme | | `data-statistical-analysis` | Runs descriptive stats, trend analysis, and hypothesis testing | | `data-validate` | Pre-delivery QA for methodology, accuracy, and bias checks | | `int-stripe` | Accesses Stripe
Ikalus1988llms.txtIkalus1988/MisakaNet/docs/llms-full.txt
Lesson: mcp-context-mode-98-reduction](https://misakanet.org/lessons/mcp-context-mode-98-reduction/) - [Lesson: mcp-server-direct-handler-testing](https://misakanet.org/lessons/mcp-server-direct-handler-testing/) - [Lesson: misakanet-heal-engine-bootstrap-workflow](https://misakanet.org/lessons/misakanet-heal-engine-bootstrap-workflow/) - [Lesson: misakanet-heal
EliaAlbertillms.txtEliaAlberti/cpr-compress-preserve-resume/llms.txt
internal; the parser is defensive and the curated summary never depends on it. - Tests: `python3 -m unittest discover -s tests`. Manifest: `claude plugin validate .`. ## Links - README: https://github.com/EliaAlberti/cpr-compress-preserve-resume#readme - Token
mixpeekllms.txtmixpeek/amux/site/llms.txt
Copy-paste hook configs for Claude Code — block secret leaks, enforce formatting, auto-run tests, coordinate parallel agents, audit all tool calls, enforce conventional commits, and more. Each recipe includes
VikashLoomballms.txtVikashLoomba/copilot-mcp/llms.txt
/web/src/components/SearchRegistryServers.tsx) - [web/src/utils/registryInstall.ts](./web/src/utils/registryInstall.ts) - Installed server management: - [web/src/components/InstalledMCPServers.tsx](./web/src/components/InstalledMCPServers.tsx) - [src/panels/ExtensionPanel.ts](./src/panels/ExtensionPanel.ts) ## CI + Release (Canonical Files) - Test workflow: [.github/workflows/tests-on-main.yml](./.github/workflows/tests-on-main.yml) - Version workflow: [.github/workflows/update-version.yml](./.github/workflows/update-version.yml) - Build/release workflow: [.github/workflows/release.yml](./.github/workflows/release.yml) - Vendored provider sync workflow
codexstar69llms.txtcodexstar69/bug-hunter/llms-full.txt
repository containment, secret stripping, output redaction, timeouts, and total budgets. Supported plans can include tests, type checks, static checks, builds, reproductions, fuzzing, and security-static checks. Required check failure
HeiGeAillms.txtHeiGeAi/heige-codex-skin-studio/llms-full.txt
想提主题预设或改代码，先看[贡献指南](CONTRIBUTING.md)。一句话版本：基于最新 main 开发，主题预设必须登记素材来源，代码改动先开 issue 对齐范围，本地 `npm test` 全绿再提交。 ## 交流群 微信群「Codex 皮肤共创交流」已满 200 人上限，扫码加我微信，我手动拉你进群。加好友记得备注：codex。纯技术交流，非盈利，互相学习
juyterman1000llms.txtjuyterman1000/entroly/docs/llms-full.txt
semantic tiers, budget-aware recall, consolidation, forgetting, persistence, safety scanning, receipts, and deterministic stress testing. Internal/experimental layers are labelled separately. - **Hallucination reduction:** WITNESS evaluates evidence support. On the published faithful
juyterman1000llms.txtjuyterman1000/entroly/docs/llms.txt
repository with `entroly go`. Run `entroly verify-claims` for a bounded local installation smoke test and `entroly simulate` for a no-model context-reduction estimate. Indexing, repository intelligence, selection, compression
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.
