agentleFS
witnesstodarkwitnesstodark/mr-mak-workspace/.agents/skills/character-sheet-pipeline/SKILL.md

character-sheet-pipeline

Skill800 starsChanged 23 days agoMITView on GitHub

Prepare strict-front character sheets, isolated parts and optional multiview references for 3D modeling from an approved image.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a consistent reference pack from the user's supplied character.

    line 8
  2. Distinctive:

    Use the supplied design as authority.

    line 12
  3. Distinctive:

    Do not turn isolated props into hero shots or add new equipment.

    line 26
  4. Distinctive:

    If requested, add side/back views for selected parts.

    line 32
  5. Distinctive:

    If requested and budgeted, add turntables, with a locked camera and rotating subject.

    line 33
  6. Distinctive:

    Verify current endpoint IDs and schemas via the selected provider.

    line 41

≈ “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.

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

Character sheets and isolated parts

Create a consistent reference pack from the user's supplied character. This is an agent-guided workflow with prompts and visual inspection; it does not bundle a standalone classifier or an automatic mesh-generation service.

Use the supplied design as authority. Establish the relevant parts, symmetry, pose and downstream use. Preserve already approved scope; do not ask again for an approval the user has given. Optional views and videos are separate scope.

  1. Inspect the reference and propose the useful body/accessory inventory.
  2. Prepare a strict-front A-pose sheet using 01a. Match the character's anatomy; keep feet and hands visible, lighting flat and the background neutral. Check identity and pose before extracting parts.
  3. A supplementary multiview sheet can help communicate the whole design: 01b. It does not replace the approved front source for extraction.
  4. Extract approved parts from the same source: body, paired items, accessories and hair. Keep the front camera and original pose. Do not turn isolated props into hero shots or add new equipment.
  5. Inspect every image with the host's image tools or an explicitly configured vision service. 08 supplies the front-view rubric. Record pass, soft failure or hard failure with reasons. Retry a failed criterion within the task budget; repeated failure is a decision to surface, not a reason for an unlimited paid loop.
  6. If requested, add side/back views for selected parts. If requested and budgeted, add turntables, with a locked camera and rotating subject. Do not create optional video by default.
  7. Deliver an inventory with prompt, provider/model, source hash, local files and review verdicts. Label which source is approved and which outputs still need a decision. Keep texture, rigging and mesh generation as later tasks.

Nano Banana Pro front/part edits and GPT Image supplementary sheets are useful routes from the source workflow, not restrictions on a user's explicit choice. Verify current endpoint IDs and schemas via the selected provider. The included fal module handles fal execution and job recovery.

Example: a robot with three feet and one telescope. Extract the body, telescope and foot set from the approved front reference. Acceptance means matching shape, pose and lighting, with no missing foot and no new perspective drift.

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.