setup-mulmoclaude
Skill388 starsChanged 7 months agoMITView on GitHub
Interactively guide MulmoClaude setup following README instructions. Checks port conflicts, host dependencies (Docker / ffmpeg / claude CLI), and common pitfalls. Respond in the user's language.
- Reads credentials
- Deletes or force-pushes
In this repository13 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- archive-shipped-plansSkill
- e2e-live-dockerSkill
- e2e-live-mediaSkill
- e2e-liveSkill
- e2e-live-wikiSkill
- make-e2e-liveSkill
- publish-mulmoclaudeSkill
- release-appSkill
- setup-mulmobridge-lineSkill
- setup-ollama-localSkill
- setup-relaySkill
- setup-wizardSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 0 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 13
Read README.md Installation section and walk the user through it (yarn install → .env).
- Very specific: line 26
Check each dependency below.
- Very specific: line 36
If which docker is not found, point to README's Prerequisites + Installing Docker Desktop.
- Very specific: line 37
If Docker is installed but not running, open -a Docker (macOS) and wait until the whale icon is steady
- Very specific: line 41
Ask the user to run yarn dev in a separate terminal (not as a background process — so they can Ctrl+C to stop).
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill 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.
Files
Setup MulmoClaude
Guide the user through MulmoClaude setup following README.md (Installation / Running the App sections). Claude handles checks and pitfall guidance.
Step 1: Follow README setup
Read README.md Installation section and walk the user through it (yarn install → .env).
Step 2: Port 5173 availability
lsof -i :5173 -sTCP:LISTEN- Available: proceed
- In use: show PID and command. Suggest that MulmoClaude may already be running — skip to Step 4 browser open, or stop the process with
Ctrl+C
Step 3: Dependency check
Check each dependency below. Install commands are NOT duplicated in this skill — README's ### Prerequisites section is the single source of truth. If something is missing, tell the user which dependency + which feature is affected, then point them to README's Prerequisites section.
| Dependency | Detect | Required for | Skippable? |
claude CLI auth | claude --version succeeds AND ~/.claude/.credentials.json (or equivalent) exists | Agent loop | No |
| Docker running | which docker && docker info | Sandbox mode | Yes — if .env has DISABLE_SANDBOX=1 |
ffmpeg on PATH | which ffmpeg | Movie generation | Yes — if user doesn't generate videos |
Docker-specific notes:
- If
which dockeris not found, point to README's Prerequisites + Installing Docker Desktop. Localized READMEs (README.ja.md/README.zh.md/README.ko.md/README.es.md/README.pt-BR.md/README.fr.md/README.de.md) have an equivalent section with a language-specific anchor — link to the one that matches the user's language - If Docker is installed but not running,
open -a Docker(macOS) and wait until the whale icon is steady
Step 4: Start dev server
Ask the user to run yarn dev in a separate terminal (not as a background process — so they can Ctrl+C to stop).
[server] ... INFO [server] listening port=3001means ready.[client] ➜ Local: http://localhost:5173/alone means only the frontend is ready, backend is still starting.
Once ready, open http://localhost:5173 and verify the General role is displayed.
Common pitfalls
| Symptom | Cause | Fix |
ERR_MODULE_NOT_FOUND: @mulmobridge/... | yarn install not run or incomplete | Re-run yarn install |
[sandbox] ... not found. | Host claude not authenticated or expired | Run claude once to authenticate |
| Movie generation hangs / silently fails | ffmpeg not on PATH | Install ffmpeg (see README Prerequisites) |
| Startup hangs silently | macOS TCC dialog hidden in background | Check for Docker folder access permission dialog |
EADDRINUSE :5173 | Port conflict | Stop the conflicting process |
| Vite stuck pending | Dependency re-optimization after lockfile change | rm -rf node_modules/.vite && yarn dev |
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.

