agentleFS
Sign inStart free
mehbylabsmehbylabs/creator-skills/skills/creator-character/SKILL.md

creator-character

Skill7 starsChanged 16 days agoMITView on GitHub

Keep a person, mascot, or character consistent across many images and videos with whatever providers the user has. Builds a reusable character pack (reference sheet, anchor description, approved reference images) and reuses it in every generation; uses a Higgsfield Soul ID when available. Use when the user wants the same face or character in multiple images, a recurring mascot, a consistent AI influencer or presenter, "use my face", a character sheet, or a story with recurring characters. Not for one-off images (creator-image).

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    After each output, compare face/outfit against refs/.

    line 56
  2. Distinctive:

    Never create packs of real people without consent, and never for impersonation, deception, or sexual content.

    line 61

≈ “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

Creator Character

A character pack lives in characters/<name>/:

characters/<name>/
  character.json     # anchor sentence, provider used, soul_id (optional), consent note
  refs/              # 3–6 approved reference images (the source of truth)
  sheet.png          # turnaround / expression sheet

Create

  1. Source
    • Real person: 5–15 clear photos (front, 3/4, profile; varied light; no sunglasses or heavy filters). Only the user themself, or someone who has consented. Record this in character.json → "consent": "self" | "<who confirmed>".
    • Invented character: a short description; first generate 3–4 candidates with creator.py image and let the user choose one.
  2. Anchor sentence — 25–40 words fixing what must not drift: age range, face shape, eye color, hair style/color, skin tone, distinguishing marks, signature outfit/colors.
  3. Higgsfield available? (creator.py detect) → offer to train a Soul ID (higgsfield soul-id create …, see their CLI help) and store the returned id as soul_id. Otherwise the reference-image method below works everywhere refs are supported.
  4. Reference sheet — generate with the best ref-capable provider:
    python3 scripts/creator.py image --prompt "Character reference sheet of <anchor>: front, 3/4, profile, back views and 4 expressions, neutral grey background, consistent lighting, no text" --ref refs/01.jpg --ratio 16:9 --size 2k --out characters/<name>/sheet.png
  5. Approve 3–6 best images into refs/. Save the pinned provider in character.json.

Use

For every image/video with the character:

  • Prompt = Same person as the reference images: <anchor sentence>. + the scene.
  • Pass 2–3 refs (--ref repeatable; most-similar angle first) and pin the pack's provider.
  • Video: make the first frame as an image with the character, then creator.py video --start.
  • After each output, compare face/outfit against refs/; regenerate on drift. Add new approved outputs to refs/ only if they're clearly on-model.

Rules

  • Never create packs of real people without consent, and never for impersonation, deception, or sexual content.
  • agy can't take references; it's unsuitable for consistency work (the router skips it when --ref is passed).

References

  • references/image-prompting.md — reference usage
  • references/video-prompting.md — start frames
  • references/providers.md — which providers accept references

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