Verify

Skill LuisHiluy/claude-code-pipeline-skills/verify

Run CLIP-based quality scoring on AI-generated image frames against configurable thresholds. Returns a GOOD / PASS / FAIL verdict with per-metric breakdown (prompt match, character similarity, palette match, composite). Use whenever the user generates an AI frame and needs objective quality feedback, says "verify", "check quality", "CLIP score", "does this pass", "score this frame", "is this good enough", or is iterating on an AI image pipeline. Trigger this skill as the quality gate between generation and the next step in any AI media loop.From its SKILL.md

Install

npx -y skills add LuisHiluy/claude-code-pipeline-skills --skill verify

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.1 KB, 654 tokens by cl100k_base, as published. Nobody here has run it

Verify — AI Frame Quality Gate

Runs CLIP analysis against configurable thresholds to verify generated frames meet quality standards.

Quick Reference

Verify a specific item

python3 "${CLAUDE_SKILL_DIR}/scripts/verify-scene.py" <ITEM_ID>

Verify an arbitrary image against a prompt

python3 "${CLAUDE_SKILL_DIR}/scripts/verify-scene.py" \
  --image /path/to/frame.png \
  --prompt "descriptive prompt" \
  --scene_id <ITEM_ID>

Batch verify all items

python3 "${CLAUDE_SKILL_DIR}/scripts/verify-scene.py" --batch

Get JSON output (for piping to other tools)

python3 "${CLAUDE_SKILL_DIR}/scripts/verify-scene.py" <ITEM_ID> --json

Workflow: Generate → Verify → Iterate

Generate a frame (via any generator — NB2, Flow, Seedance, etc.)
Run verification: python3 scripts/verify-scene.py <ITEM_ID>
Read the verdict:
- GOOD — all metrics above "good" thresholds → approve and move on
- PASS — above fail thresholds but not all good → acceptable, iterate if time permits
- FAIL — any metric below fail threshold → must iterate
If FAIL or iterating, check which metric failed, adjust prompt:
- Low character score → strengthen character descriptors, add reference images
- Low palette score → reinforce world palette keywords
- Low prompt match → simplify prompt, front-load key descriptors

Thresholds

Thresholds are configured in reference/thresholds.md. Default suggestions:

Metric	FAIL <	GOOD ≥
prompt_match	0.27	0.30
character	0.50	0.65
palette	0.55	0.70
composite	0.40	0.50

Derive your own thresholds by running a baseline pass on known-good frames, then setting FAIL at ~mean−1σ and GOOD at ~mean.

Dependencies

pip install transformers torch pillow

Expected directory layout (configurable):

Character refs in references/approved/characters/
Palette refs in references/approved/palettes/
Item prompts in runs/prompts.json

Gotchas

CLIP model loads ~500MB on first run. Subsequent calls in the same process are instant.
CLIP text tokenizer truncates at 77 tokens (~300 chars). Front-load important descriptors in prompts.
Scores are relative, not absolute. A 0.30 prompt match is genuinely good for this model. Don't expect 0.90+.
Grid images score lower than cropped single frames. Always verify on cropped hero frames, not raw grids.
Items with no expected character return N/A for the character metric — composite uses palette + prompt only.

What ships with it: 3 files

8.8 KB alongside SKILL.md, 1 of them executable

reference/

thresholds.md1.6 KB

scripts/

verify-scene.pyruns6.9 KB

README.md407 B