Supercmo Setup

Organization

SupercmoHQ

supercmo-setup

Diagnoses which capabilities are ready or blocked, sets up the keys, then sets up the brand from its website. Use when the user asks to "set me up," "setup," "help me get set up," "get started," "help me get started," "get me started," "what can you do," or to configure or finish setting up SuperCMO, or on a no_provider_configured error.

Overview

Publisher	SupercmoHQ
Repository	`superCMO-skills`
Skill name	`supercmo-setup`
Stars	260
Forks	31
Bundled files	1
License	Apache-2.0
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by SupercmoHQ on GitHub. Read the source before you install it.

Installation

Install the Supercmo Setup AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/SupercmoHQ/superCMO-skills/tree/main/skills/supercmo-setup
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/SupercmoHQ/superCMO-skills.git /tmp/superCMO-skills
mkdir -p .claude/skills
cp -r /tmp/superCMO-skills/skills/supercmo-setup .claude/skills/supercmo-setup

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Supercmo Setup in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Supercmo Setup on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Supercmo Setup is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Setup

Get the API keys working so SuperCMO can generate, then set up the brand from the user's website.

Workflow

Step 1: Check what's set up

Call setup_status with check: true to see which capabilities already work. It validates any keys that are set and never generates.

Where setup_status isn't there at all — the tool doesn't exist yet — the install just ran and the agent hasn't loaded the SuperCMO tools. Ask the user to restart the agent, then try again; only if it's still missing after a restart is it a broken install.

First time through, nothing is set up: go straight to Step 2. Where a working setup is already there, skip to Step 4.

Step 2: Set up the key

The managed key is the default — one command, one key covering every capability, pay per use. Set it up unless the user has specifically asked to bring their own keys; don't raise the bring-your-own route yourself.

bash
npx --yes @supercmo/skills@0.1.27 login

It opens SuperCMO in your browser to sign in and authorize this device; the key is written to ~/.supercmo/.env automatically. Buy credits in the web app (no card needed to sign in). Run it for the user once they're ready — it needs their sign-in.

Only when the user asks to bring their own keys, set those up instead — free, straight to the vendors. Not all five are needed: an image + video key (WAVESPEED_API_KEY) is enough to start generating, and voiceover, analysis and website reading can be added when a task calls for them. Ask only for the capabilities they actually want.

Key	Enables	Get it at
`WAVESPEED_API_KEY`	generate images + video (recommended)	https://wavespeed.ai/dashboard
`FAL_KEY`	generate images + video (also supported)	https://fal.ai/dashboard/keys
`ELEVENLABS_API_KEY`	generate voiceover + narration	https://elevenlabs.io/app/settings/api-keys
`GEMINI_API_KEY`	analyze a photo or video	https://aistudio.google.com/app/apikey
`FIRECRAWL_API_KEY`	extract data from URLs	https://www.firecrawl.dev/app/api-keys

Keys go in ~/.supercmo/.env, one per line (WAVESPEED_API_KEY=their-key). Every host reads that file live — no restart. A shell export, or the host's own MCP env block, also works and takes precedence over the file. With both image keys set WaveSpeed is used; SUPERCMO_MEDIA_PROVIDER=fal picks the other.

Step 3: Verify

Re-run setup_status with check: true and say what changed — which capabilities went from blocked to ready. Don't declare success from the fact that a file was written.

Where a key still doesn't register, the causes in order of likelihood: the variable name is misspelled in ~/.supercmo/.env, the key was pasted with surrounding quotes or a trailing space, or an old export in the shell is shadowing the file.

Step 4: Set up the brand

Offer it — "keys work; want me to set up your brand from your website?" — and on yes, trigger the onboarding-user skill.

Step 5: Suggest what to do next

Skip this step where onboarding-user ran in Step 4: it already closed with the same list.

Close with this list:

Create a UGC video — a creator-style video for your product.
Create a product ad video — a produced ad or commercial for your product.
Generate product photos — packshots and lifestyle shots from one product photo.
Research competitor ads — what's working in your category, and what nobody runs.

Edge cases

setup_status isn't available and nothing generates → the skills were installed without the MCP server. Reinstall with npx --yes @supercmo/skills@0.1.27 --claude (or --cursor, --codex, --all), which wires both.
A probe fails on a key that is set → the vendor rejected it: expired, revoked, or from the wrong product. Name the vendor and have them re-issue it; don't retry.
The user asks which lane is better → managed is fastest to working and pay-per-use; their own keys go straight to the vendor, but they would need to manage multiple keys with different vendors and ensure each has sufficient balance. Both are fully supported. It is their call.
The user only wants one capability — just voiceover, just images → set up that key alone and say plainly which capabilities stay blocked.
The user asks about credits, billing or top-ups → that lives in the web app; point them there rather than guessing balances.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

evals/eval_cases.json2 KB

Frequently asked questions

What does the Supercmo Setup AI skill do?

Why use Supercmo Setup on TypingMind?

Because you install it once and use it with any model. Supercmo Setup is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Supercmo Setup in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/SupercmoHQ/superCMO-skills/tree/main/skills/supercmo-setup. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Supercmo Setup?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Supercmo Setup?

As many as you like. As long as a model supports skills, you can use Supercmo Setup with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Supercmo Setup AI skill free?

Yes. It is published on GitHub by SupercmoHQ under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Kanban Video Orchestrator

NousResearch

OrganizationPopular

Plan and run multi-agent video production pipelines.

Pixel Art

Pixel art w/ era palettes (NES, Game Boy, PICO-8).

Inference Sh Cli

Run 150+ AI apps (image, video, LLM) via inference.sh CLI.

Weights And Biases

W&B: log ML experiments, sweeps, model registry, dashboards.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Setup

Workflow

Step 1: Check what's set up

Step 2: Set up the key

Step 3: Verify

Step 4: Set up the brand

Step 5: Suggest what to do next

Edge cases

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now