agentleFS
Sign inStart free
sandraschisandraschi/midasheng-gen-mcp/CLAUDE.md

midasheng-gen-mcp

CLAUDE.md2 starsChanged 3 months agoApache-2.0View on GitHub

You can generate and manage mixed audio scenes (speech + music + SFX + ambience) with a local LLM-driven flow matching model. Before starting work: 1. Check model state: audio_scene(operation="status") 2. Check recent scenes: audio_scene(operation="list", limit=5) At end of work: - Keep generated scenes indexed (they persist automatically in SQLite) - The model loads lazily on first generate - no preload needed - Use uv run python (never naked python) - Run just lint + just test before committing; just…

The file

We split this CLAUDE.md into the rules it gives an agent

7 rules. About 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Check model state: audio_scene(operation="status")

    line 9
  2. Very specific:

    Check recent scenes: audio_scene(operation="list", limit=5)

    line 10
  3. Distinctive:

    Keep generated scenes indexed (they persist automatically in SQLite)

    line 13
  4. Very specific:

    Use uv run python (never naked python)

    line 18
  5. Very specific:

    Run just lint + just test before committing.

    line 19
  6. Very specific:

    Do not edit mcpb/src/ - it is a staging copy.

    line 23
  7. Distinctive:

    No em dashes in any file

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

CLAUDE.md - midasheng-gen-mcp

Session Context (MiDashengLM-Gen Audio)

You can generate and manage mixed audio scenes (speech + music + SFX + ambience) with a local LLM-driven flow matching model.

Before starting work:

  1. Check model state: audio_scene(operation="status")
  2. Check recent scenes: audio_scene(operation="list", limit=5)

At end of work:

  • Keep generated scenes indexed (they persist automatically in SQLite)
  • The model loads lazily on first generate - no preload needed

Development rules

  • Use uv run python (never naked python)
  • Run just lint + just test before committing; just web-check after webapp changes
  • The heavy inference stack is optional (uv sync --extra model) - tools must never fake success when it is missing (declared state machine)
  • Do not edit mcpb/src/ - it is a staging copy; fix src/ and re-pack
  • No em dashes in any file

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

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.

Check your setup, free