reframe
Skill0 starsChanged 42 days agoMITView on GitHub
Vertical reframing that follows who is speaking: face tracks, mouth-activity speaker turns with hysteresis and minimum holds, two-shots or stacks for rapid exchanges, off-camera voices, reaction shots, screen-aware layouts, jump-cut punch-ins where the preset allows — and static held crops for presets (Luxury Tech) that forbid footage motion.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- Belweave/hstacktheir own version, first seen Nov 8, 2026
- callumflack/skillstheir own version, first seen Nov 1, 2026
- sreejithraman/SreeStacktheir own version, first seen Nov 1, 2026
- killi1812/man-mcptheir own version, first seen Oct 8, 2026
- Kshitijpalsinghtomar/depth-skillstheir own version, first seen Oct 1, 2026
- Lengros/bennutheir own version, first seen Jul 8, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- ramboz/jig★ 7same name
- rohunvora/my-claude-skills★ 6same name
- Kshitijpalsinghtomar/depth-skills★ 5same name
- Lengros/bennu★ 2same name
- Belweave/hstack★ 1same name
- callumflack/skills★ 1same name
- killi1812/man-mcp★ 1same name
- sreejithraman/SreeStack★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository19 other files it gives its agents.
- analyzeSkill
- audioSkill
- captionsSkill
- clipSkill
- creator-editSkill
- designSkill
- directorSkill
- doctorSkill
- editSkill
- exportSkill
- graphicsSkill
- ingestSkill
- luxury-techSkill
- previewSkill
- quality-checkSkill
- reviseSkill
- studioSkill
- style-learningSkill
- transcribeSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
0
Distinctive
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
- Very specific: line 33
Look first: read qa/cuts.jpg/qa/contact.jpg of the latest render and the analysis sheets for the range.
“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Reframe
Rules: ${CLAUDE_PLUGIN_ROOT}/references/rules.md · CLI: ${CLAUDE_PLUGIN_ROOT}/references/cli.md.
ss = "${CLAUDE_PLUGIN_ROOT}/bin/shorts-studio". Input: $ARGUMENTS
0. Engine check
The commands below run the Shorts Studio engine. Installed as the Claude Code plugin it is already
present and shorts-studio is on the Bash PATH. If shorts-studio doctor is not found (for example,
this skill was added with npx skills add), ask the user before installing anything, then:
- Claude Code:
/plugin marketplace add bloxy-studios/shorts-studio→/plugin install shorts-studio@shorts-studio. - Other agents:
git clone --depth 1 https://github.com/bloxy-studios/shorts-studio ~/.shorts-studio/engineand read every${CLAUDE_PLUGIN_ROOT}path below as~/.shorts-studio/engine.
Then run shorts-studio doctor --setup once (project-local runtime; never sudo or global installs).
Steps
- Look first: read
qa/cuts.jpg/qa/contact.jpgof the latest render and the analysis sheets for the range. Speaker detection is mouth activity normalized per face (evidence, not certainty); a laughing listener can be mistaken for the speaker — check frames. - Record what you see:
ss analyze note <project> --kind reaction --at 0:12.4 --detail "host laughs, guest speaking". - Fix with targeted ops (other runs untouched):
keep-both-visible(two-shot/stack over a range),switch-speaker(at a time, optionaltrackId),reduce-motion(holds instead of follows). Thenss render. - Luxury Tech: footage never moves — layouts change instead (
luxury-techskill).
Limits
Face tracking samples 5 fps (denser around turns); profile faces and heavy occlusion reduce confidence; off-camera voices keep the previous framing or a wide/stack layout and are logged.
Completion check
On rendered frames the active speaker is framed in every run you changed, no unrequested reframes
appear elsewhere, and captions.face-collision passes.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

