midasheng-gen-mcp
Copilot instructions2 starsChanged 3 months agoApache-2.0View on GitHub
- Python: use uv run python, ruff for lint/format, FastMCP 3.4.4+ - The heavy inference stack (torch, transformers) is an optional extra - tools must return declared failure states when it is missing, never simulated success - MCP tools register at import time on the shared instance in server.py - Webapp: React + Vite + Tailwind (dark), Zustand stores in src/store/, API client in src/lib/api.ts - Ports: backend 11159, frontend 11160 - Tests: uv run pytest (light, no torch); webapp:…
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms-full.txtllms.txt
- llms.txtllms.txt
The file
Files
MiDashengLM-Gen MCP - coding guidance
- Python: use
uv run python, ruff for lint/format, FastMCP 3.4.4+ - The heavy inference stack (torch, transformers) is an optional extra - tools must return declared failure states when it is missing, never simulated success
- MCP tools register at import time on the shared instance in
server.py - Webapp: React + Vite + Tailwind (dark), Zustand stores in
src/store/, API client insrc/lib/api.ts - Ports: backend 11159, frontend 11160
- Tests:
uv run pytest(light, no torch); webapp:bun run check - ASCII only in all files (no em dashes)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
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.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.