agentleFS
ttalkkaklabttalkkaklab/social-flow/skills/review-camera/SKILL.md

review-camera

Skill1 starsChanged 3 months agoApache-2.0View on GitHub

Reviews and improves cut direction; stops before images. Use only when the user asks for a camera review.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Follow the production order.

    line 12
  2. Very specific:

    Use shot boundary decisions and storyboard_read.boundaryReview to challenge every playback join against an uninterrupted scene.

    line 22
  3. Very specific:

    Use an independent reviewer with fresh context.

    line 32
  4. Distinctive:

    If a missing event changes the story, fix the story layer first.

    line 35

≈ “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

Review Camera

Runs only when the user asks for it (user directive 2026-10-31); no other step waits on it. Follow the production order.

Read action direction and shot continuity and dialogue coverage. Test its worked cases against each speaking shot: fixed OTS with two speakers, unreadable profile two-shots, valid one-speaker OTS and valid two-speaker two-shots. Inspect the whole reverse sequence for speech ownership, eyelines and preserved lines; these findings are guidance, not gates.

Use shot boundary decisions and storyboard_read.boundaryReview to challenge every playback join against an uninterrupted scene. Preserve justified cuts; fewer shots alone is not improvement.

Map every required audience-visible beat to one or more cuts. Export the camera plan separately from mutable scenes.js and give it to the reviewer. Inspect what the viewer first notices, angle/size, focus endpoints, motivated movement or hold, actor blocking, prop state, eyelines, action cue and final composition. Check consecutive cuts and missing coverage of causal events; do not equate a camera technique name with executable direction.

Use an independent reviewer with fresh context. The author fixes named defects — render route, size, angle, move, focus, depth and frame plan with shot_icons; endpoints, blocking and eyelines with storyboard_apply — and the reviewer rechecks the entire affected sequence. If a missing event changes the story, fix the story layer first. Stop before image generation.

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.