likeness-preservation
Skill2 starsChanged 49 days agoMITView on GitHub
Preserve the creator's exact facial identity when generating or editing images. Triggered whenever an image is meant to include a real person.
In this repository23 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- analyse-channel-packagingSkill
- analyse-thumbnailsSkill
- channel-analyticsSkill
- channel-identitySkill
- channel-kickoffSkill
- competitor-boardSkill
- competitor-ideationSkill
- competitor-mappingSkill
- competitor-scanSkill
- image-generation-coreSkill
- image-refinementSkill
- keywords-seoSkill
- memory-reviewSkill
- monetisationSkill
- packagingSkill
- script-writingSkill
- thumbnail-best-practicesSkill
- thumbnail-inspirationSkill
- transparencySkill
- youtube-banner-specSkill
- youtube-profile-specSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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
- Distinctive: line 14
If a face was not explicitly asked for, do not put one in: When in doubt: objects, text, graphics or abstract.
- Distinctive: line 32
Do not proceed without a confirmed reference: If there is none, say so and ask for a photo.
- Distinctive: line 55
If it is not recognisably the same person, redo it with a better reference.
- Distinctive: line 56
Do not deliver it saying "it came out close".
- Very specific: line 60
When generate_image.py detects a reference with the likeness role, it prepends the exact-identity clause and the prohibition on cropping at …
- Distinctive: line 74
If the face is not recognisably the creator: say so plainly and ask for a better reference instead of delivering it.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Facial identity preservation
WHEN
Any image that should include the creator, or any real person. Load it before generating, not after seeing the face come out wrong: a lost identity is not recovered by iterating the prompt.
If a face was not explicitly asked for, do not put one in. When in doubt: objects, text, graphics or abstract. An invented person in the thumbnail of a channel with a recognisable face breaks the brand.
EXECUTION ORDER
- Get a sharp facial reference. In order of quality:
- A photo the creator provides in this conversation.
- An image generated earlier in this conversation where the face came out well.
- One of their own thumbnails with the face clear and large:
And open it to confirm the face is visible. A blurred, profile or obscured face guarantees a bad result.python3 tools/yt_recent_videos.py --limit 15 --stats python3 tools/yt_thumbnails.py --video ID
- Do not proceed without a confirmed reference. If there is none, say so and ask for a photo. Generating "something similar" is worse than not generating.
- Label it with the
likenessrole
The role does two things: it places the reference first and it activates the exact-identity clause in the prompt. Without the role, neither happens.python3 tools/generate_image.py --prompt "..." --type thumbnail \ --ref path_to_the_face.jpg:likeness - When refining, the image to edit goes in
--imageand the face in--ref face.jpg:likeness. Never the other way round. Verify by opening the result. The criterion:
Acceptable Not acceptable Different pose, different angle Different facial features Different expression Someone who "looks like them" Different light, different clothes A clearly generated face If it is not recognisably the same person, redo it with a better reference. Do not deliver it saying "it came out close".
WHAT THE TOOL ALREADY DOES
When generate_image.py detects a reference with the likeness role, it
prepends the exact-identity clause and the prohibition on cropping at the neck.
There is no need to repeat it in --prompt; verify it with --dry-run.
SOURCES
source: generated. A well-preserved face is still an artefact, not a
photograph: if it is used publicly, say so.
OUTPUT
- The generated image, after opening it and checking the identity against the table above.
- Which reference was used as
likeness. - If the face is not recognisably the creator: say so plainly and ask for a better reference instead of delivering it.
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.

