setup
Skill2 starsChanged 27 days agoMITView on GitHub
Set up tubecrew for this creator - detect which production tools are already installed (Remotion, HyperFrames, Wan, CosyVoice, Codex, ffmpeg, a GPU), ask about subscriptions (ElevenLabs, ChatGPT/Codex), suggest a tool for every station of the production line, install the free pieces with permission, and save the choices. Use on first run, for "set up tubecrew", "what tools can I use", "I have ElevenLabs / a GPU / Codex", or before the first video.
- Reads credentials
- Installs packages
191 other projects use a version of this.
Adopted by
Most recently taken up by
- hydra-db/hydradb-claude-codetheir own version, first seen Nov 8, 2026
- WALKERKILLER/Look-Tongji-Notestheir own version, first seen Nov 8, 2026
- steerlabs/opensteertheir own version, first seen Nov 8, 2026
- ansvisor/ansvisortheir own version, first seen Nov 8, 2026
- dsifry/metaswarmtheir own version, first seen Nov 8, 2026
- anombyte93/prd-taskmastertheir own version, first seen Nov 8, 2026
Used with
Projects with it also use add-voice-transcription, add-discord and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
juancruzmunozalbeloSkilladd-voice-transcription
Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.
Also in 5 projects that use this
MicrosoftSkilladd-discord
Add Discord bot channel integration via Chat SDK.
Also in 11 projects that use this
- MicrosoftSkill
add-slack
Add Slack channel integration via Chat SDK.
Also in 11 projects that use this
- juancruzmunozalbeloSkill
add-telegram-swarm
Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".
Also in 7 projects that use this
- +8 more from microsoft
Other versions191 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 191
- anthropics/knowledge-work-plugins★ 35ksame name
- garrytan/gbrain★ 32ksame name
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- qwibitai/nanoclaw★ 31ksame name
- Q00/ouroboros★ 6.3ksame name
- pytorch/executorch★ 5.2ksame name
- agenticnotetaking/arscontexta★ 3.5ksame name
- aws/agent-toolkit-for-aws★ 3.4ksame name
- spotify/portal-ai-plugins★ 2.8ksame name
181 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- channel-pulseSkill
- check-renderSkill
- check-thumbnailSkill
- check-voiceoverSkill
- find-topicSkill
- localizeSkill
- make-shortsSkill
- morph-clipsSkill
- produce-videoSkill
- research-factsSkill
- retention-by-sceneSkill
- upload-privateSkill
- write-scriptSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 171 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
Ask in one round, skipping anything already known:
- Distinctive: line 57
If the creator lets the agent run uploads, offer the opt-in publish guard: a Claude Code hook that asks the creator before any upload or …
“Common” is measured: kept by at least 6 in 10 of the 171 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Set up the crew
tubecrew does not force a toolset. It checks what the creator already has and pays for, then fits the production line around it. Run this once, and again whenever the creator's tools change.
$SKILL below is this skill's folder.
1. Detect
python $SKILL/scripts/detect_stack.pyIt reports what is installed (Python, FFmpeg, yt-dlp, Node.js, Codex CLI, the GPU and its memory, faster-whisper,
Remotion and HyperFrames skills, a running ComfyUI, CosyVoice, whether ELEVENLABS_API_KEY is set) and suggests a
tool for each station. It never prints secrets and never installs anything.
2. Ask what code cannot see
Ask in one round, skipping anything already known:
- Subscriptions: ElevenLabs (voice cloning, narration, music), a ChatGPT plan for Codex, vidIQ.
- Whether they narrate with their own recorded voice.
- For Remotion: is the work for a for-profit company with more than 3 employees? Then Remotion needs a company license; HyperFrames (Apache-2.0) has no such condition.
- Which they prefer to read and edit: React (Remotion) or HTML/CSS (HyperFrames). Both pass the same render gate.
3. Recommend, then install with permission
Present one line per station: the suggested tool, why, and the alternative. The full catalog with costs and
licenses is $SKILL/references/tools.md.
Offer to install the free pieces that are missing, and run each command only after the creator says yes (they change the creator's machine or agent setup):
| Piece | Command |
| Remotion agent skills | npx skills add remotion-dev/skills (new project: npx create-video@latest) |
| HyperFrames (Claude Code) | claude plugin marketplace add heygen-com/hyperframes then claude plugin install hyperframes@hyperframes |
| HyperFrames (other agents) | npx skills add heygen-com/hyperframes |
| yt-dlp, faster-whisper | pip install yt-dlp faster-whisper |
| YouTube API libraries | pip install google-auth google-auth-oauthlib requests |
| OCR for the text-dose check (optional) | pip install rapidocr-onnxruntime |
Remotion and HyperFrames are installed by default when the creator agrees, because the Make station relies on
code-based motion design. Paid tools (ElevenLabs, Codex) are only suggested, never signed up for. Wan and CosyVoice
need a GPU and a manual install; point to their guides in references/tools.md. A plugin installed now is
available after the agent restarts.
4. Offer the publish guard
If the creator lets the agent run uploads, offer the opt-in publish guard: a Claude Code hook that asks the
creator before any upload or publish command and refuses it when nobody is there to answer. Install it only on a
yes, with python $SKILL/scripts/publish_guard.py --install-copy, and follow $SKILL/references/publish-guard.md
to add the printed block to the creator's settings.
5. Save
Record the creator's decisions, so every later station uses the same tools:
python $SKILL/scripts/detect_stack.py --set voice=elevenlabs --set motion=remotion --set verifier=codexStations and values: research (yt-dlp, vidiq, manual), verifier (codex, claude-agent), voice (elevenlabs,
cosyvoice, recording, other-tts), transcription (faster-whisper, editor), motion (remotion, hyperframes,
morph-clips, editor), clips (wan, none), dubbing (cosyvoice, elevenlabs, none), upload (youtube-api, studio).
The file is ~/.tubecrew/stack.json; --show prints it.
Report back
The stack as a short table (station, tool, cost), what was installed in this run (and whether the publish guard is on), and the one next step, usually "start a video with produce-video".
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.