Skip to content
Agentmart
Submit a tool

gen

Generate an image with ComfyUI from a text prompt

Skill by hybridindie

IndexedMIT★ 3
Write a review

Chalk Labs

Need help deploying gen?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/hybridindie-gen

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Generate an image with ComfyUI from a text prompt

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/gen

What's inside

Skill name
gen
Description
Generate an image with ComfyUI from a text prompt
License
MIT
Instructions
31 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Generate Image

Generate an image using ComfyUI based on the user's prompt "$ARGUMENTS".

## Steps

1. **Parse the prompt.** Extract any explicit parameters (dimensions, steps, cfg, model name) from the user's request. Reject and ask for clarification only in these specific cases:
   - The prompt is empty or whitespace-only
   - The prompt is a question or meta-request rather than a scene description (e.g., "what can you do?", "how does this work?")
   - The user passed a parameter outside its valid range (steps < 1, cfg < 0, width/height not divisible by 8)

   Otherwise, apply these defaults for the listed parameters (and only these) when not specified:
   - width: 512, height: 512
   - steps: 20
   - cfg: 7.0
   - negative_prompt: "bad quality, blurry"

2. **Select a model.** If the user specified a model name, use it. Otherwise, call `comfyui_list_models` with folder `"checkpoints"`, pick one from the returned `items`, and ask the user to confirm before proceeding (offer to swap if they want a different one).

3. **Generate the image.** Call `comfyui_generate_image` with the parsed parameters and `wait=True` so we block until completion.

4. **Fetch the result.** The response is a dict envelope with keys `status` (expect `"completed"`), `prompt_id`, `outputs`, `elapsed_seconds`, and optionally `warnings`. `outputs` is a list of `{node_id, filename, subfolder}` entries — read the first entry's `filename` and `subfolder` and call `comfyui_get_image` with those. (Tip: pass `preview_format="webp"` and `preview_quality=80` to `comfyui_get_image` for a thumbnail instead of the full PNG — much cheaper context.)

5. **Present the result.** Show the image and a summary of the generation parameters used (prompt, model, dimensions, steps, cfg).

## Notes

- If generation fails, check `comfyui_get_queue` to see if ComfyUI is busy or stuck.
- For img2img, ControlNet, or other advanced workflows, use `/comfy:workflow` instead.

From hybridindie/comfyui_mcp, MIT.

Signals

Stars
3
Forks
0
Open issues
0
Last commit (this folder)
May 12, 2026 (5 months ago)
Last release
Oct 6, 2026 (24 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from hybridindie

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get gen running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying gen?

CallGet help
Cite this page

gen skill. Agent Mart. https://agentmart.dev/skills/hybridindie-gen (last updated 2026-10-24)