concept-art
Skill1 starsChanged 4 days agoMITView on GitHub
Generate concept art for a saved character-forge character on fal.ai — a front/back A-pose model sheet posed by a figure built on the character's own proportions, or the character in the pose of any picture the user gives. Checks every result against the card's look and iterates. Use when the user asks for a concept, model sheet, turnaround or character pose image.
- Reads credentials
1 other project uses a version of this.
Adopted by
Most recently taken up by
- edhahn/agent-skillstheir own version, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- edhahn/agent-skills★ 2same name
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 repository9 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- contributeSkill
- intentSkill
- security-checkSkill
- character-promptsSkill
- design-lookSkill
- forge-characterSkill
- meetSkill
- translate-characterSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Show the prompt: Call character_concept with dry_run: true and skim it.
- Very specific: line 18
If the details are wrong, add a short extra note, e.g.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Concept art via fal (A-pose model sheet)
Requires the character-forge MCP server and FAL_KEY (in the environment or in a .env in the working directory).
The tool draws an A-pose figure from the card's body (the DNA frame, as life events changed it, plus look.body posture) and gives it to the image model as the pose reference, with the card's full look. It costs about $0.02 per sheet, and each retry costs the same.
- Prepare. Find the id (
character_list). The card needs alooksection; if it's weak or missing, suggest thedesign-lookskill first. - Show the prompt. Call
character_conceptwithdry_run: trueand skim it. Fix anything in the card's look, not by hand in the prompt. - Generate.
- A-pose sheet (default): call
character_conceptwithviews: "front-back"(or"front"). The result becomesconcept.pngin the card. - Custom pose: the user supplies a picture (path or URL) whose pose to copy. Call
character_conceptwithpose_image. The pose is extracted from it, and the result is saved asconcept-pose.png, next to the A-pose sheet rather than replacing it.
- A-pose sheet (default): call
- Check the result by reading the PNG. Compare it with the card's
look: left/right asymmetry, marks on the correct side, signature item beside the figure, palette, silhouette, and an A-pose with the arms clear of the body. - Iterate, at most 2 retries unless the user asks for more.
- If the details are wrong, add a short
extranote, e.g. "scar behind the LEFT ear, hair covering it". - To vary the design, use a new
seed. To keep the design and only tweak the prompt, reuse the returnedseed.
- If the details are wrong, add a short
- Report to the user in their language: the image path, the seed, what matches the look, what doesn't, and the total spend so far.
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.

