clip
Skill40 starsChanged 4 months agoMITView on GitHub
Cut a video into short-form clips (highlights/shorts) — cut given timecodes directly, or pick the best moments from a Perso AI STT project. Reframes 16:9→9:16. Subtitles are added separately by the srt skill.
- Reads credentials
13 other projects use a version of this.
Adopted by
Most recently taken up by
- Ivan-propio/claude-skillstheir own version, first seen Nov 16, 2026
- DeepExtrema/Tesseracttheir own version, first seen Nov 16, 2026
- OpenLAIR/dr-clawtheir own version, first seen Nov 8, 2026
- ashleysbrain/skillstheir own version, first seen Nov 8, 2026
- TakeOff-Team/claude-shortform-video-editortheir own version, first seen Oct 25, 2026
- jinhuang712/claude-code-cliptheir own version, first seen Oct 20, 2026
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
- OpenLAIR/dr-claw★ 1.2ksame name
- TakeOff-Team/claude-shortform-video-editor★ 11same name
- DeepExtrema/Tesseract★ 4same name
- ashleysbrain/skills★ 1same name
- Clay-HHK/claude-skills★ 1same name
- gitsang/skills★ 1same name
- kwiggen/claude-code-plugin★ 1same name
- mhiskall282/Securing-the-Digital-Mine-UNESCO-Project★ 1same name
- bloxy-studios/shorts-studio★ 0same name
- Ivan-propio/claude-skills★ 0same name
3 more not listed
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.
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 0 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 32
Phase 2 — pick, then cut: Read the transcript and choose clips, each { "title": "...", "start_order": N, "end_order": M }.
- Very specific: line 43
Run: node scripts/clip.mjs --project <seq> --clips '<json>' [--out folder] (--clips also accepts @path).
- Very specific: line 49
Write the sidecars: node scripts/clip.mjs --sidecars "<out>/clips.json" — add --karaoke only for a karaoke preset (it also writes …
- Very specific: line 52
Add --host <runtime> for telemetry (silent), same as the other workers.
“Common” is measured: kept by at least 6 in 10 of the 10 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
/clip
Cut a video into short clips + reframe. Subtitles are not this skill's job — after cutting, the srt skill styles them (see the handoff below).
Entry points
- Explicit timecodes ("cut 2:00–3:00 of this video") → cut the local file directly:
--video "<file>" --ranges "2:00-3:00,...". No STT, no key, no credits. - AI highlight selection on an STT project →
--planthen--clips(the flow below). Needs the project's transcript + word timestamps. Raw video, "find the good moments" (no timecodes given) → you can't pick highlights without a transcript, so ask the user which they want:
- STT (proper selection, uses credits): run the
srtskill's STT first to create the project, then clip it with--plan/--clips. - Free (no STT): the user gives the timecodes and you cut them with
--video --ranges.
Proceed with their choice — don't run STT (which bills credits) without asking.
- STT (proper selection, uses credits): run the
Core rules
- Only the worker sees the raw key — never open, echo, or pass it as an argument.
- The key gate applies only to
--project/--plan/--clips.--video --rangesand--sidecarsare fully offline — never run a key check/registration for them. - Run in the background — encoding takes time.
- This skill shares the dubbing skill's libraries: the
dubbingfolder must be installed next toclip.
Flow
Phase 1 — plan. node scripts/clip.mjs --project <seq> --plan prints the summary's section map (topic guide) plus the full sentence transcript, each line as order [start-end] text.
Phase 2 — pick, then cut. Read the transcript and choose clips, each { "title": "...", "start_order": N, "end_order": M }. Rubric:
- Hook first — start on a sentence that grabs attention (question, bold claim, funny/surprising line).
- End where the moment resolves, not at the first complete sentence. Ride the beat to its end — the whole reaction, follow-through, and any secondary punchline. Read a few sentences past the apparent ending; keep them if still the same reaction.
- Cut at the transition — end just before the energy drops or the tone shifts (excited reaction → calm narration).
- Peak — favour funny / surprising / emotional / quotable moments; the high point often sits a sentence or two after the literal reveal.
- Length 30–90s — the worker warns when outside; prefer the full arc over a premature cut.
- Title — describes the moment; becomes the file name (
01_<title>.mp4).
Sections are chapter-length — use the section map only as a guide, then tighten to a hook.
Run: node scripts/clip.mjs --project <seq> --clips '<json>' [--out folder] (--clips also accepts @path). Landscape (16:9) sources are reframed to 9:16 (drama-shorts letterbox); portrait sources are kept. The worker writes the clips plus a clips.json manifest (records each clip + the transcript slice needed for subtitles later). Relay [progress]; deliver the files from [clips-output].
Subtitles → hand off to the srt skill
Subtitles are off by default. After cutting, tell the user clips are ready and ask whether to add subtitles. If they want subtitles, show the presets first — never jump straight to one, exactly as the srt skill's styling flow does: the interactive gallery (select + Apply) in the Claude app, or the static ../srt/assets/style_presets.png + node ../srt/scripts/style.mjs --list-presets menu elsewhere. Let the user pick a preset or describe a style (short-form presets like karaoke/bold-punch suit clips). Only after they pick:
- Write the sidecars:
node scripts/clip.mjs --sidecars "<out>/clips.json"— add--karaokeonly for a karaoke preset (it also writes<clip>.timestamps.jsonfor measured word timing; a plain preset needs just the.srt). - Style each clip with the srt skill:
node ../srt/scripts/style.mjs "<clip>.mp4" "<clip>.srt" --preset <id>(append--word-timestamps "<clip>.timestamps.json"for karaoke). See the srt skill's "Style & burn subtitles" section.
Add --host <runtime> for telemetry (silent), same as the other workers.
Config (env)
Same as /dubbing / /srt (PERSO_API_BASE/PERSO_MEDIA_BASE — https perso.ai hosts only, PERSO_SPACE_SEQ, XP_API_KEY, PERSO_NO_TELEMETRY, …).
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.

