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.
yschimkePipes a download into a shellllms.txtyschimke/compose-ai-tools/site/llms.txt
Optional review and CI skills (`compose-preview-review`, `compose-preview-ci`; Claude Code: `/plugin install compose-review@compose-agent-plugins`) and the `apply` GitHub Action that posts before/after renders
VKirillllms.txtVKirill/claude-lane-stack/llms.txt
database or cloud service — plain files + plain git. MIT license. Key facts: - Only Claude Code is required; workers optional and auto-detected by `agents-doctor` (profiles: full → claude-only). - Task
Bande-a-BonnotPipes a download into a shellllms.txtBande-a-Bonnot/Boucle-framework/docs/llms.txt
same tier from the documented project root. - Temporary hook trials still edit Claude Code settings while active. Snapshot, verify install, uninstall, then verify cleanup. - A clean native Windows `install.ps1 verify
sandbaseaillms.txtsandbaseai/deepseek-harness-handbook/site/llms.txt
public dsh-plugin topic repositories + 471 manual additions); this handbook intentionally exposes a reviewed subset: https://github.com/0xsline/awesome-deepseek-harness/blob/07278233cba25e6f2d011018751187b7a4d8ed52/CATALOG.md SandBase Harness MCP bridge guide: https://sandbaseai.github.io/deepseek-harness-handbook/sandbase-harness-bridge.html English README and Star
OraclesTechReads credentialsllms.txtOraclesTech/guardian-sdk/llms.txt
default) or JSON — for a SIEM or a vendor security review. Team and Enterprise plans only. Defaults to the last 30 days; max 366 days, 100,000 rows. --- ## Agent Self
X-isdoingreatllms.txtX-isdoingreat/canvas-pilot/site/llms.txt
open source" -> Canvas Pilot automates recurring assignment workflows while keeping review and submission under student control. - "Canvas LMS Claude Code Codex agent" -> Canvas Pilot supports the local-agent workflow shape
0xzrllms.txt0xzr/freellmpool/docs/llms.txt
speaks the OpenAI API and has an experimental Anthropic-compatible path, > so Codex, Claude Code, and aider run on pooled free models unchanged. MIT licensed. > Capacity tools (`freellmpool capacity status
Houseofmvpsllms.txtHouseofmvps/ultraship/llms.txt
spec approval, step-by-step implementation plans, test-driven development, systematic debugging, AI-powered code review, and a pre-deploy quality gate that scans SEO, security, performance, code quality
marcimastro98llms.txtmarcimastro98/Xenon/docs/llms.txt
page under `/catalog/ /` - [Xenon Maker](https://xenon-app.com/maker/): make widgets, themes and more without code, in the browser - [Live demo](https://xenon-app.com/demo/): the dashboard in the browser, with sample
ScraperNodellms.txtScraperNode/awesome-n8n-templates/public/llms-full.txt
# Awesome n8n Templates — Full Listing > https://scrapernode.github.io/awesome-n8n-templates > 13,593+ n8n workflow templates > Built
agents-uillms.txtagents-ui/agents-kit/llms-full.txt
local notes, and switch voice mode on when useful | `example-chat-app` | | Coding workspace | Select files, review a proposed patch, accept or reject changes, and run checks against the accepted
agents-uillms.txtagents-ui/agents-kit/llms.txt
then switch to voice without losing your draft. - [example-coding-app](https://agents-ui.github.io/agents-kit/c/example-coding-app.json): An agent proposes a patch, you review it, and the checks explain the result. - [example-voice
jangtrinhllms.txtjangtrinh/design-os-3d-blender/docs/llms.txt
graded reviews in interactive Three.js 3D viewers. ## Model Context Protocol (MCP) Server `design-os-3d-blender` exposes a certified First-Party Model Context Protocol server for AI coding agents (Claude
jangtrinhllms.txtjangtrinh/design-os-3d-blender/llms.txt
graded reviews in interactive Three.js 3D viewers. ## Model Context Protocol (MCP) Server `design-os-3d-blender` exposes a certified First-Party Model Context Protocol server for AI coding agents (Claude
KilbexReads credentialsllms.txtKilbex/Vigla/llms-full.txt
Read the architecture · Take an open task --- Five coding agents should not mean five terminals, five diff reviews, and five unread merges. Vigla gives the work one operations
Kilbexllms.txtKilbex/Vigla/llms.txt
Revert the whole mission when the result is wrong. --- Five coding agents should not mean five terminals, five diff reviews, and five unread merges. Vigla gives the work one operations
JSv4llms.txtJSv4/Docxodus/docs/llms.txt
revisions`, `docx_diff_get_edit_script`, `docx_diff_get_semantic_changes`. - Merge several reviewers' copies into one multi-author redline: .NET `DocxDiff.Consolidate`; npm `docxDiffConsolidate`; Python `docx_diff_consolidate`; MCP `docxodus
EliasOulkadillms.txtEliasOulkadi/shokunin/llms.txt
Mobile**: flutter, react-native - **Quality**: test-commander, performance-profiler, code-review - **Content**: content-marketing, translate-craft, communication, documentation - **Productivity**: git-workflow, windows-powershell, strategy, finance - **Documents**: kami, kagen, portfolio-auto
EliasOulkadillms.txtEliasOulkadi/shokunin/.pack/llms.txt
Mobile**: flutter, react-native - **Quality**: test-commander, performance-profiler, code-review - **Content**: content-marketing, translate-craft, communication, documentation - **Productivity**: git-workflow, windows-powershell, strategy, finance - **Documents**: kami, kagen, portfolio-auto
tecnologicachilePipes a download into a shellllms.txttecnologicachile/mail-mcp/site/llms-full.txt
Apple Silicon), Windows (x86_64), Docker ## What it does Connect mail-mcp to Claude Code, Claude Desktop, Cursor or any MCP client and the agent can work with an inbox
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.
