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.
sandraschiReads credentialsllms.txtsandraschi/aiwatcher-mcp/llms.txt
Optional integrations: `ROBOFANG_ENABLED`, `EMAIL_ENABLED`, `CALIBRE_ENABLED`, `GMAIL_ENABLED`. ## Ports Backend: 10946 | Frontend: 10947 | MCP: http://localhost:10946/mcp ## Start ``` .\start.bat
sandraschiReads credentialsllms.txtsandraschi/discord-mcp/llms-full.txt
with RAG, and run agentic workflows from Cursor or Claude Desktop. **Ports:** Backend 10756, Frontend 10757 ## Tools All Discord operations are consolidated into a single portmanteau tool: ### discord(operation=...) | Operation
sandraschillms.txtsandraschi/gitee-mcp/llms-full.txt
REPOS | curated list | Radar seeds, comma-separated | | GITEE_BACKEND_PORT | 11161 | Backend port | | GITEE_FRONTEND_PORT | 11162 | Webapp port | Default seeds: openharmony/openharmony, RuoYi-Vue/RuoYi-Vue, dromara/hutool, dromara/sa-token, dromara/RuoYi-Vue-Plus, apache/dubbo, seata/seata
sandraschillms.txtsandraschi/handbrakemcp/llms-full.txt
presets. - `handbrake_shutdown`: Orderly self-termination (MCP tool) + `POST /api/shutdown` (HTTP). ## 🖥️ Industrial Dashboard The frontend (`web_sota/`) is a React/TypeScript/Vite app configured for: - Port (Frontend): `10874` - API Base (Backend
sandraschiReads credentialsllms.txtsandraschi/handbrakemcp/llms.txt
progress via SSE/FastAPI - **Custom params** — pass arbitrary HandBrakeCLI arguments ## Ports | Port | Service | |------|---------| | 10874 | Dashboard frontend (Vite) | | 10875 | Dashboard API (FastAPI) / MCP HTTP | ## Quick Start ```bash uv sync && uv run handbrake
sandraschillms.txtsandraschi/midasheng-gen-mcp/llms-full.txt
index (scenes, jobs) + generated WAV files (gitignored) - Ports: backend 11159 (REST /api + MCP /mcp), frontend 11160 Data flow: 1. Caption views composed into a tagged prompt (<|caption|> <|asr|> <|speech
sandraschiReads credentialsllms.txtsandraschi/plexmcp/llms-full.txt
Webapp ```text cd webapp powershell -ExecutionPolicy Bypass -File .\start.ps1 ``` Backend: http://127.0.0.1:10740 — Frontend: http://127.0.0.1:10741 FastMCP ASGI may be mounted at `/mcp` on the backend when `plex_mcp.app` loads
sandraschillms.txtsandraschi/plexmcp/llms.txt
plex_mcp` with `PLEX_TOKEN` and `PLEX_URL` 3. **Webapp / Tauri:** backend **10740**, frontend **10741** — [docs/WEBAPP.md](docs/WEBAPP.md) ## Docs (curated) | Doc | Purpose | |-----|---------| | [README.md](README.md) | Overview, doc map | | [docs/README.md](docs/README.md) | Documentation
sandraschillms.txtsandraschi/xkcd-mcp/llms-full.txt
serve`. 2. **404 on comic number** — Number may not exist; verify on xkcd.com. 3. **Frontend can’t reach API** — Ensure Vite proxy targets `127.0.0.1:10778` (see `web_sota/vite.config.ts`). 4. **Port
san-npmReads credentialsllms.txtsan-npm/skills-ws/public/llms-full.txt
# skills.ws — Full Skill Index > 87 agent skills for AI coding assistants. ## ab-testing Category
simongonzalezdcllms.txtsimongonzalezdc/GameStory-Lab/llms.txt
versioned concept history - export GDD, pitch, and technical documentation as markdown - run a React frontend, Node/Express backend, Prisma/PostgreSQL database, and optional local Ollama models ## Install / use Install with npm workspaces
sohaibdevvllms.txtsohaibdevv/claude-skills/docs/llms-full.txt
Fullstack, AI/ML, DevOps, security, data, and QA skills. Includes senior-role skills (architect, backend, frontend, fullstack, DevOps, data engineer/scientist, ML, computer vision, prompt, QA, security, SecOps), cloud architects (AWS/Azure/GCP
taylorbanksllms.txttaylorbanks/page-foundry/docs/llms.txt
invokes best-of-breed design skills to make the page beautiful (taste-skill, impeccable, frontend-design, grounded in a real reference captured with designlang), then refuses to ship until
techhorizonlabsPipes a download into a shellllms.txttechhorizonlabs/gearlist/llms-full.txt
Gearlist Updated: 2026-11-08 Documentation reviewed, not independently tested. No ranking or safety
vaah-aiPipes a download into a shellllms.txtvaah-ai/GenicUI/llms-full.txt
# GenicUI — `llms-full.txt` (full corpus for AI agent ingestion) # # Snapshot of the canonical https://genicui.vaah.ai
Adarshukumarllms.txtAdarshukumar/skills/docs/llms-full.txt
Fullstack, AI/ML, DevOps, security, data, and QA skills. Includes senior-role skills (architect, backend, frontend, fullstack, DevOps, data engineer/scientist, ML, computer vision, prompt, QA, security, SecOps), cloud architects (AWS/Azure/GCP
agentapplicationPipes a download into a shellllms.txtagentapplication/agentapplication/docs/llms-full.txt
# Agent Applications > A vendor-neutral reference architecture for building and operating AI agent systems
ArcQian-bitllms.txtArcQian-bit/codex-real-engineer-skills/docs/llms.txt
repo mapping, issue triage, PR review, security review, performance work, release prep, docs sync, frontend polish, migrations, and the general `real-engineer` workflow router. The pack is inspired by public
ArcQian-bitPipes a download into a shellllms.txtArcQian-bit/codex-real-engineer-skills/llms.txt
repo-cartographer`, `issue-sherpa`, `pr-reviewer`, `security-scout`, `perf-lab`, `release-captain`, `docs-keeper`, `frontend-polisher`, and `migration-pilot`. The collection adapts common engineering-agent patterns from the public Claude
baiyuan-techllms.txtbaiyuan-tech/pif-whitepaper/llms.txt
layer architecture — module boundaries, data flow, deployment topology, and design trade-offs - [Chapter 5: Frontend Stack](https://baiyuan-tech.github.io/pif-whitepaper/en/ch05-frontend-stack.html): Next.js 15 App Router, React Server Components, shadcn/ui, react-hook-form
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.
