editing-montage
Provider-independent editing and montage direction for AI agents producing generated videos, ads, trailers, social clips, explainers, product videos, documentary-style pieces, and music- or beat-driven cuts. Use when planning, revising, QAing, or handing off an edit: story structure, shot selection, continuity, montage theory, rhythm and pacing, J/L cuts, match cuts, cutaways, transitions, beat sync, platform timing, source/generated asset management, revision workflow, and composition handoff.
Profile →npx skills add calesthio/generative-media-skills --skill editing-montage --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Directs an AI agent to make decisions about sequence, duration, shot function, rhythm, continuity, audio/visual relationships, platform fit, and revision logic for edits involving generated and mixed media.
How it works
The skill instructs the agent to treat editing as controlling what the viewer notices, understands, feels, and remembers, not merely placing clips in order. It emphasizes provider-independent work across diverse source media, and it highlights considerations for provenance, continuity, and QA when media are generated. It provides guidance on evidence and theory, including montage types, rhythm, shot selection by function, and continuity methods. It demands building an edit promise and locking decisions about delivery context, viewer action, emotional curve, timing, source regime, and revision authority. It introduces a narrative and decision framework (edit decision ladder) prioritizing viewer effect, story function, attention path, rhythm, continuity, and technical cleanliness.
It defines shot-function taxonomy (establishing, insert, reaction, cutaway, proof, bridge, reset, button) and continuity rules (screen direction, eyeline, match on action, object permanence, temporal logic, light/color, spatial scale, audio space) with remediation options if continuity fails. It covers montage theory with patterns (graphic, rhythmic, spatial, temporal, associative, emotional, evidentiary) and lists patterns to pursue or avoid. It prescribes rhythm and pacing considerations, including how to shape with shot duration, motion, narration density, music, captions, and sound design, plus review passes (silent, audio-only, caption-only, full).
It instructs on using split edits (J-cuts and L-cuts) to bridge visuals, including example usage like hearing crowd noise before a cut to a launch event.
When to use it
Use when the edit itself determines whether a video works, especially in contexts requiring planning, revising, QA, or handoff for various formats such as explainers, ads, product videos, trailers, social clips, and documentary-style pieces. It is intended for productions where generated media, stock, UI, captions, and mixed media are involved and where continuity and provenance are critical.
What it can touch
- Tools: claude-code, codex, copilot, cursor
- Focus areas: shot metadata, duration, frame rate, resolution, aspect ratio, audio status, shot type, content, motion, continuity risks, and editorial value
- It references and leverages templates and patterns for montage and rhythm but does not specify external scripts beyond the listed tools.
Caveats
- License: MIT
- It discusses platform-specific timing considerations (e.g., Netflix subtitling guidance, YouTube Shorts timing, TikTok ad formats) as empirical observations and guidelines, not guarantees.
- It warns that generated media may require stricter provenance, continuity, and QA due to identity/geometry/text/physics drift.
- It emphasizes decision-making authority and revision boundaries to be client/brand/legal/music/platform-locked when applicable.
# Editing and montage direction Use this skill when the edit itself determines whether a video works. Your job is to make decisions about sequence, duration, shot function, rhythm, continuity, audio/visual relationship, platform fit, and revision logic. Do not treat editing as "put the clips in order." Treat it as the craft of controlling what the viewer notices, understands, feels, and remembers.
What does the editing-montage skill do?
Provider-independent editing and montage direction for AI agents producing generated videos, ads, trailers, social clips, explainers, product videos, documentary-style pieces, and music- or beat-driven cuts. Use when planning, revising, QAing, or handing off an edit: story structure, shot selection, continuity, montage theory, rhythm and pacing, J/L cuts, match cuts, cutaways, transitions, beat sync, platform timing, source/generated asset management, revision workflow, and composition handoff.
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill editing-montage --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.