review-cut-images
Skill1 starsChanged 3 months agoApache-2.0View on GitHub
Reviews and improves cut images; stops before video generation. Use only when the user asks for an image review.
In this repository30 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- autoproduceSkill
- brandingSkill
- channelSkill
- compose-blenderSkill
- datagoSkill
- edit-speechSkill
- generate-cut-imagesSkill
- generate-cut-videosSkill
- grow-instagramSkill
- grow-threadsSkill
- grow-youtubeSkill
- ingestSkill
- inspect-contentSkill
- introSkill
- platform-guideSkill
- produceSkill
- project-initSkill
- publishSkill
- review-cameraSkill
- review-contextSkill
- review-cut-videosSkill
- review-recentSkill
- setup-instagramSkill
- setup-threadsSkill
- setup-youtubeSkill
- storyboardSkill
- topic-scoutSkill
- upscale-videoSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Follow the production order.
≈ “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.
Files
Review Cut Images
Runs only when the user asks for it (user directive 2026-10-31); no other step waits on it. Follow the production order.
Read image inspection and visual grounding.
An independent reviewer opens every actual image in cut order, compares with the camera plan (and Blender compositions when the user asked for them), then tests audience comprehension against the text. Check visible evidence, opening state, prop hands/ownership, actor placement, identity, readable text and style. Seeing an expressive face is not evidence of the narrated event. Future motion cannot excuse an incorrect first frame. Cover every cut ID in the review JSON.
The author repairs the earliest affected layer: story with the story tools, camera with
shot_icons, image pixels with shot_image (a new versioned file). Preserve old media and
failed reports, and reuse unaffected files. Never spend beyond existing authorization to
chase a pass. Stop after the review.
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.

