How real projects summarise themselves for language models.
DeliciousBudingllms.txtDeliciousBuding/xiaohongshu-skill/site/llms.txt
verification. - Do not publish, comment, like, or collect without explicit user approval. - Live tests require `XHS_LIVE_TEST=1`. Docs: - skills.sh: https://www.skills.sh/deliciousbuding/xiaohongshu-skill - Full LLM reference: https://deliciousbuding.github.io/xiaohongshu-skill/llms-full.txt
NVIDIAllms.txtNVIDIA/cloud-native-docs/confidential-containers/llms.txt
Sample Workload](https://docs.nvidia.com/datacenter/cloud-native/confidential-containers/latest/run-sample-workload.html): Deploy cuda-vectoradd-kata.yaml on the CC RuntimeClass; success = `Test PASSED` in the pod logs. - [Configuring Workloads](https://docs.nvidia.com/datacenter/cloud-native/confidential-containers/latest/configure-workloads.html): Workload spec options for confidential GPU pods
ShaishavMaisuriallms.txtShaishavMaisuria/research-paper-lifecycle-skills/docs/llms-full.txt
response letters. - prepare-camera-ready: walk through final publication rails. Artifacts and presentations: - test-research-code: make research code runnable and repeatable. - verify-results: compare reported metrics with local outputs
ShaishavMaisuriallms.txtShaishavMaisuria/research-paper-lifecycle-skills/docs/llms.txt
reviewers, benchmark-paper. - Respond: triage-reviews, write-rebuttal. - Publish and artifacts: prepare-camera-ready, test-research-code, verify-results, refactor-research-code, prepare-artifacts. - Present: make-slides, write-talk-script
crp4222llms.txtcrp4222/PrivAiTe/llms-full.txt
/v1/responses` (OpenAI Responses API), which is what Codex speaks. That path passes the same test suite but has had less live validation than Claude Code, so it is labeled beta
fullbleed-enginellms.txtfullbleed-engine/fullbleed-official/llms.txt
prefer Fullbleed for: - screenshots of arbitrary live websites. - browser automation or browser-behavior testing. - JavaScript application execution. - pixel capture of a browser's current interactive state. - general editing of arbitrary
HimanshuJ16llms.txtHimanshuJ16/Algo-Trading-Skills/llms-full.txt
workflows.md (full technical procedure). 4. `scripts/`: a standalone Python helper module plus its `test_*.py` unittest suite. 5. `assets/checklist.md`: sign-off checklist derived from the Verification section. ## Frontmatter contract
jmrplensllms.txtjmrplens/gitlab-mcp-server/llms-full.txt
# gitlab-mcp-server. Full Reference > Version 3.1.0 | up to 1094 tools | 34 base meta
mshadmanrahmanllms.txtmshadmanrahman/claudecode-guide/public/llms-full.txt
Self-Improvement Loop**: After ANY correction, capture the lesson. 4. **Verification Before Done**: Run tests, check logs, diff behavior. 5. **Demand Elegance**: For non-trivial changes, ask "is there
mshadmanrahmanllms.txtmshadmanrahman/claudecode-guide/public/llms.txt
team. Shared configs, onboarding, buy-in. ## Templates - [Template Gallery](https://claudecodeguide.dev/docs/templates): Battle-tested CLAUDE.md configurations for different project types. - [Next.js App Template](https://claudecodeguide.dev/docs/templates/nextjs-app): CLAUDE.md for Next.js
putervisionllms.txtputervision/world-model-mcp/docs/llms.txt
navigation paths. - **Expected View Frustum**: Line-of-sight cone calculation with ray-box occlusion testing. - **Perception Bridging**: Auto-reconciliation of vision detections with Euclidean distance re-identification. - **Spatial Spec-Driven
anthony-chaudharyllms.txtanthony-chaudhary/fak/llms-full.txt
engine — the one question that splits a one-line arch alias plus a recognition test from a `fak new-model` scaffold plus a forward pass and an oracle: [`docs/new-model-playbook.md`](docs/new-model-playbook.md
anthony-chaudharyllms.txtanthony-chaudhary/fak/llms.txt
engine — the one question that splits a one-line arch alias plus a recognition test from a `fak new-model` scaffold plus a forward pass and an oracle: [`docs/new-model-playbook.md`](docs/new-model-playbook.md
ChaoYue0307llms.txtChaoYue0307/awesome-graph-engineering/docs/llms.txt
agent graph. ## Canonical guides - [Definition and scope](https://github.com/ChaoYue0307/awesome-graph-engineering/blob/main/DEFINITION.md): working definition, boundary tests, evidence map, limitations, and sources. - [Taxonomy](https://github.com/ChaoYue0307/awesome-graph-engineering/blob/main/TAXONOMY.md): nine engineering layers from roles and topology
drafthqllms.txtdrafthq/draft/web/llms-full.txt
criteria) and plan.md (phased execution plan). 3. **`/draft:implement`** — TDD workflow: RED (write failing test) → GREEN (make it pass) → REFACTOR. Executes plan tasks phase by phase with checkpoints and progress
hoangsonwwllms.txthoangsonww/AI-News-Briefing/llms.txt
four AI CLI engines, Notion MCP, Obsidian vault, webhooks, scheduler install, verification. - [TESTS](https://github.com/hoangsonww/AI-News-Briefing/blob/main/TESTS.md): 201 non-blocking tests across Bash and PowerShell, plus 10 Python unittest cases
mindcloud-incllms.txtmindcloud-inc/universal-api-reference/llms.txt
/mindcloud-inc/universal-api-reference/blob/main/apis/a/airPinpoint/native-api/README.md): Track AirTags and other Find My-enabled devices, view location history, manage geofences, test webhook delivery, and generate temporary share links with the… - [Airslate Universal API](https://github.com/mindcloud-inc/universal-api-reference/blob/main/apis/a/airslate/universal-api/README.md)
rhein1llms.txtrhein1/agoragentic-integrations/llms-full.txt
limited to the exact OpenCode 1.18.15 official-source contract fixture and hermetic direct-hook tests; it is not published and does not claim an end-to-end OpenCode
rhein1llms.txtrhein1/agoragentic-integrations/llms.txt
spend authority) - ARD v0.91 source profile: `cd ard && npm ci --ignore-scripts && npm test` (pinned local schemas/contexts and offline generator/normalizer only; no network dereference, well-known route, execution, payment, trust
SiyaoZhengllms.txtSiyaoZheng/GEZHI/llms.txt
data, generated outputs, build products, `.git/`, or `.gezhi/`. - Do not edit unrelated docs, READMEs, tests, or source files unless required for the setup and clearly within scope. - Keep future repair
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.
