How real projects summarise themselves for language models.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
drafthqllms.txtdrafthq/draft/web/llms.txt
specialist commands) 3. `/draft:implement` — TDD execution with checkpoints 4. `/draft:review` — Three-stage code review, now with graph-backed structural checks ## Key Concepts - **Context-Driven Development (CDD):** Structured documents
Nagarjuna2997llms.txtNagarjuna2997/ios-agent-skill/site/llms-full.txt
result in your app.Read the guide → AI clientsWhich Muse Code MCP settings actually work with a local Swift review server?A reproducible Muse 1.3.0 connection check, with the exact configuration
Nagarjuna2997llms.txtNagarjuna2997/ios-agent-skill/site/llms.txt
settings actually work with a local…](https://nagarjuna2997.github.io/ios-agent-skill/blog/muse-connection.html) - [Muse Code: what our integration actually verifies](https://nagarjuna2997.github.io/ios-agent-skill/blog/muse-verification.html) - [Review AI-generated Swift before you trust it](https://nagarjuna2997.github.io/ios-agent-skill/blog/review-swift-with-ai.html)
SiyaoZhengReads credentialsllms.txtSiyaoZheng/GEZHI/llms.txt
when Codex can review a local artifact file; - `claude_code_file` when Claude Code can review a local artifact file; - `api` only when OpenAI-compatible file upload is intended
agentskillexchangeReads credentialsllms.txtagentskillexchange/skills/llms.txt
Trace MCP slug: serve-codebase-impact-context-to-agents-with-trace-mcp category: Code Quality & Review framework: MCP verification: Security Reviewed description: Use Trace MCP to index a repository once
anzy-renlab-aillms.txtanzy-renlab-ai/pronounce/docs/llms-full.txt
# Pronounce — full dictionary Format: | | | | | kubectl | /ˈkuːb kənˌtroʊl/ | koob control | cli-tool | contested | (no source
bluebear-iollms.txtbluebear-io/baloo-bear/docs/llms.txt
Baloo > Baloo is a self-hosted AI code review GitHub App for pull requests. It reviews diffs and repository context, posts GitHub-native review feedback, and supports Anthropic, Amazon Bedrock
bsmi021Pipes a download into a shellllms.txtbsmi021/mcp-file-context-server/docs/llms-full.txt
# Example Clients Source: https://modelcontextprotocol.io/clients A list of applications that support MCP integrations
dfrostarllms.txtdfrostar/neuralmind/docs/llms.txt
guards that keep an agent's changes consistent with the code (pattern drift before commit, stale decisions, blast radius, review, index freshness) - [Security](https://neuralmind.uk/security/): verifying a release (cosign
littlebearappsllms.txtlittlebearapps/outlook-assistant/llms.txt
untrusted. Confirmation level `outward` (default), `all-writes` or `off`: a plugin setting in Claude Code, the `OUTLOOK_CONFIRM_LEVEL` environment variable elsewhere. How the hook prompts and fails differs
mikusnuzllms.txtmikusnuz/app-publish-mcp/llms.txt
apple_list_reviews — List customer reviews - apple_respond_to_review — Respond to a customer review - apple_list_certificates — List signing certificates - apple_create_certificate — Create a signing certificate - apple_revoke
ServosityReads credentialsllms.txtServosity/msp-skills/docs/llms-full.txt
# MSP Skills - full corpus > Free MCP servers and Skills connecting MSP tools to the
trekhlebllms.txttrekhleb/yesbrainer/public/llms.txt
password-reset style recovery, and browsers can evict site storage. Defenses in the code include a strict Content-Security-Policy whose `connect-src` allowlist names only the provider endpoints
AgentsKit-iollms.txtAgentsKit-io/agentskit/llms.txt
interfaces. - [Doc Bridge](https://doc-bridge.agentskit.io/): Turn repository documentation into executable agent handoffs. - [AgentsKit Code Review](https://code-review.agentskit.io): Run deep, low-noise review with the model already in use. - [AgentsKit
booklib-aiReads credentialsllms.txtbooklib-ai/booklib/llms-full.txt
reduced-motion", "storyboard", "parallax", "loading animation", "hover effect", "micro-interaction". **Directory**: `skills/animation-at-work/` --- ## Skill: clean-code-reviewer **Description**: Reviews code against Robert C. Martin's Clean Code principles. Use when users
booklib-aillms.txtbooklib-ai/booklib/llms.txt
Tools (5) - lookup — search for post-training docs, team decisions, expert knowledge - review — deep code review against a named skill - remember — capture a team decision or insight - verify — check
curie-engllms.txtcurie-eng/curie/llms.txt
reviewed pull request or merge request or a clear failure reason. Bring supported existing skills and tools onto the same platform. The CLI can be driven by a coding agent
ferdinandobonsllms.txtferdinandobons/AWSBestPracticesSkill/docs/llms.txt
review AWS services. The corpus intentionally contains only best practices, with official AWS source links. It does not contain pricing tables, service introductions, tutorials, or extended code walkthroughs. Answer behavior
kenqiallms.txtkenqia/bilibili-drum-score-to-pdf/llms.txt
Skill in skills/bilibili-drum-score-to-pdf/ for vision agents such as Codex, with page-by-page agent review and optional redraw. - [README (Chinese)](README.md) - [CLI and website installation](docs/install.md) - [Conversion contract](docs/script-product/conversion.md) - [Website
keployllms.txtkeploy/blog-website/public/llms-full.txt
testing type, community health, CI/CD integration, and team skill level. - https://keploy.io/blog/community/ai-for-coding Reviews 19 AI coding tools tested hands-on in 2026 — Cursor, Keploy, GitHub Copilot, Bolt, Gemini
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.
