agentleFS
Sign inStart free
joebenscoter86joebenscoter86/higgsfield-ugc-workflow/skills/ugc-base-character/SKILL.md

ugc-base-character

Skill4 starsChanged 5 months agoMITView on GitHub

Step 2 of the ugc-ad pipeline. Generate one consistent, photorealistic base portrait of a UGC creator/actor — person only, neutral professional environment, NO product. Registers the face to cast.md so a winner can be reused. Use standalone to mint a reusable creator face, or as step 2 of a UGC ad. Brand-agnostic.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 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.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Confirm the image model + reference roles: Default soul_2 (best for photoreal UGC/portrait).

    line 16
  2. Very specific:

    Generate the portrait: Call generate_image:

    line 18
  3. Very specific:

    If a brands/<brand>/cast.md exists for the target brand, also append the same entry there.

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

ugc-base-character

Generates the master portrait that locks the actor's identity across every cut of the ad.

Inputs

  • CREATOR_BRIEF (text) — age range, gender presentation, ethnicity if specified, hair, attire, vibe.
  • DEST (path).

Steps

  1. Confirm the image model + reference roles. Default soul_2 (best for photoreal UGC/portrait). Call models_explore(action="get", model_id="soul_2") if unsure of aspect_ratio / params.
  2. Generate the portrait. Call generate_image:
    • model: "soul_2"
    • prompt: describe ONLY the person — physical features, attire, expression, and a neutral professional environment (soft studio or clean indoor light). Do not mention the product, props, or any branding.
    • aspect_ratio: "9:16", count: 1
    • Poll job_status until terminal; capture job_id and the result URL.
  3. Download the result: curl -fsSL <url> -o "$DEST/character.png".

  4. Register to cast. Append to DEST/cast.md (create if missing):

    ## <slug> — generated <date>
- source: ugc-base-character
- job_id: <job_id>
- brief: <one-line CREATOR_BRIEF summary>
- status: candidate   # promote to "keeper" after a winning ad

    If a brands/<brand>/cast.md exists for the target brand, also append the same entry there.

Output

DEST/character.png + the character job_id (report it — downstream steps pass it as a media reference).

Constraints

  • PERSON ONLY. No product. (Hard rule — product in the base portrait causes compositing drift in the storyboard + video steps.)
  • One face per run. Identity variety comes from generating fresh per ad, not from multiple faces in one image.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free