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.
LoserLabllms.txtLoserLab/gridlock/llms.txt
grids (page + nested), breakpoints, spacing scale, and density profiles. Ready for design systems and frontend tooling. ## Part of a suite Hexed (colors) + Specimen (typography) + Gridlock (layout) + Eyes Peeled (accessibility) + Devourer
lpalboullms.txtlpalbou/AbstractSkill/llms-full.txt
# AbstractSkill — full documentation > The Agent Skills (`SKILL.md`) contract library for AbstractFramework: parse > and validate
markoblogollms.txtmarkoblogo/ABVXsite/public/llms.txt
save you hours of work. Meet F*cking Good Libraries, a curated collection of frontend li - Jekyll and Hyde in Toki Pona | A Classic in a New Voice
millhqReads credentialsllms.txtmillhq/mill/userdocs/llms-full.txt
# Mill — full documentation --- # What is Mill A script writes new shapes into a `.drawio
minjikim89llms.txtminjikim89/make-me-unicorn/llms.txt
products. It checks a codebase against a 670-item launch checklist across 15 categories — frontend, auth, billing, security, SEO, legal, observability, deployment, monitoring, growth, and more — organized into 6 named
MustaphaStephllms.txtMustaphaSteph/agent-bus/llms.txt
project. Errors: `INVALID_INPUT`, `NAME_TAKEN`. Example: ``` register({ name: "worker-a", team: "frontend", capabilities: ["tests","review"] }) ``` ### send Fire-and-forget message to another agent. Input: - `from: string` — your registered name
myk-orgDeletes or force-pushesllms.txtmyk-org/claude-code-config/docs/llms-full.txt
agents/` | Specialist personas for Python, Git, GitHub, docs, tests, Bash, Docker, Kubernetes, Java, Go, frontend, and more | | `plugins/` | Slash commands for GitHub workflows, local review workflows, and `acpx` multi-agent
noahzjw888-debugReads credentialsllms.txtnoahzjw888-debug/superh3-api-examples/llms-full.txt
trusted client's secret settings. Keep it out of public chats, source control, browser frontend code and logs. Download this repository or the [agent kit](https://superh3.com/agents/superh3-agent-kit.zip). Python uses
padhy-debugDeletes or force-pushesllms.txtpadhy-debug/saas-master-builder/llms-full.txt
current_tenant_id()`). 2. **Law 2 (Cryptographic Server-Side Tenant Extraction)**: Never rely on frontend client headers (`X-Tenant-Id`) alone. Tenant identity must be extracted from a cryptographically verified
patalbansishashankllms.txtpatalbansishashank/hyponoia/docs/llms.txt
native executable with an authenticated integration asset; the UI variant adds one content-addressed frontend pack. All processing is local — the embeddings run on-device; there is no embedded
Pentagonal-aillms.txtPentagonal-ai/pentagonal/public/llms-full.txt
audits. (3) Full lifecycle — generate, audit, fix, and deploy from one platform. --- ## Technical Stack - **Frontend:** Next.js 15, React 19, TypeScript - **Styling:** Vanilla CSS with design tokens - **Auth:** Supabase Auth (OAuth
pixel-educacaollms.txtpixel-educacao/pixel-aihub-skills-public/llms-full.txt
reduzir erros de LLM: don't assume, minimize code, surgical changes, verifiable success. 03 | frontend-design | foundation-security | essential | intermediate | medium | ready | auto | UI production-grade. Evita "estética IA genérica
proveo-callms.txtproveo-ca/orrery/llms-full.txt
human approval. - **@architect** — designs before code. Must be consulted for non-trivial work. - **@backend / @frontend / @devops** — domain specialists. - **@adversarial-reviewer** — finds every problem in a diff. No fixes on first
rdhawladarllms.txtrdhawladar/claude-code-fullstack-starter/llms.txt
GitHub template that bootstraps a Claude Code project with five specialist AI subagents (architect, frontend, backend, QA, code reviewer), pre-configured workflows, coding standards, and architecture documentation — built specifically
rlakamrajullms.txtrlakamraju/accessible-ai/llms.txt
site: Crawl and audit all pages - analyze_codebase: AST-level static analysis of a frontend project - import_audit_results: Import Chrome Extension findings - map_violations_to_source: Map runtime violations
Roughn3ckllms.txtRoughn3ck/ExecutiveMind/llms.txt
compliance. - Aria (Site-Shaper) — Web dev, SEO, brand guardian. - Dash (UI/UX) — Dashboard and frontend. - Vault (Treasury Guardian) — Privacy sentinel, deny by default. - Scout (Market Intelligence) — Speed is signal, alpha from
sandraschiDeletes or force-pushesllms.txtsandraschi/avatar-mcp/llms-full.txt
# avatar-mcp > This guide explains how to set up and run the AvatarMCP server
sandraschillms.txtsandraschi/butterchurn-mcp/llms-full.txt
/sandraschi/butterchurn-mcp cd butterchurn-mcp uv sync cd webapp; bun install; cd .. .\start.ps1 # backend :10878 + frontend :10879, opens browser ``` Or run separately: `uv run butterchurn-mcp --serve` (backend) and `cd webapp
sandraschiReads credentialsllms.txtsandraschi/immich-mcp/llms-full.txt
endpoints** - All 15+ MCP tools available via HTTP - **Immich++ integration** - Seamless integration with web frontend - **CORS support** - Web client access enabled - **Comprehensive API documentation** - All endpoints documented - **Automatic fallback support
sandraschiReads credentialsllms.txtsandraschi/immich-mcp/llms.txt
export and backup photos - **Storage info** — server storage health ## Ports | Port | Service | |------|---------| | 10838 | Dashboard frontend (Vite) | | 10839 | Backend (FastAPI + MCP HTTP) | ## Quick Start ```bash uv sync && uv run immich
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.
