ai-video-editing
$
npx mdskill add arcasilesgroup/ai-engineering/ai-video-editing``` /ai-video-editing plan recording.mp4 # plan structure from raw footage /ai-video-editing organize raw.mp4 # transcribe + edit decision list /ai-video-editing cut --edl cuts.txt # deterministic FFmpeg cuts /ai-video-editing compose --source demo.mp4 --aspect 9:16 ```
SKILL.md
.github/skills/ai-video-editingView on GitHub ↗
--- name: ai-video-editing description: "Edits real video footage: cuts recordings into highlights, transcribes and structures raw footage, runs FFmpeg operations (trim, concat, reframe, normalize audio), creates Remotion overlays, prepares social-platform cuts. Trigger for 'cut this video', 'edit the recording', 'make a highlight reel', 'reframe for TikTok', 'transcribe this footage'. Not for generating videos from prompts; use /ai-media instead. Not for animation specs; use /ai-animation instead." effort: mid argument-hint: "plan|organize|cut|compose [source]" mode: agent tags: [video, editing, ffmpeg] requires: anyBins: - npx bins: - ffmpeg model_tier: sonnet mirror_family: copilot-skills generated_by: ai-eng sync canonical_source: .claude/skills/ai-video-editing/SKILL.md edit_policy: generated-do-not-edit --- # Video Editing ## Quick start ``` /ai-video-editing plan recording.mp4 # plan structure from raw footage /ai-video-editing organize raw.mp4 # transcribe + edit decision list /ai-video-editing cut --edl cuts.txt # deterministic FFmpeg cuts /ai-video-editing compose --source demo.mp4 --aspect 9:16 ``` ## Workflow AI-assisted editing for real footage. Not generation from prompts. Core thesis: **the value is not generation. The value is compression.** 1. **Gate check** — verify `ffmpeg` is available (`ffmpeg -version`); install via `brew install ffmpeg` / `apt install ffmpeg` / `choco install ffmpeg`. 2. **Pick mode** — `plan` (structure), `organize` (transcribe + EDL), `cut` (FFmpeg deterministic), `compose` (Remotion overlays, optional). 3. **Run the 6-layer pipeline** — Capture → Organization → Deterministic Cuts → Programmable Composition → Generated Assets → Final Polish (human). 4. **Cross-reference** `ai-media` for Layer 5 generated assets (voiceover, music/SFX, b-roll). > Detail: see [the 6-layer pipeline + tool table](references/six-layer-pipeline.md), [FFmpeg recipes (extract / batch-cut / concat / proxy / silence detect)](references/ffmpeg-recipes.md), [social-platform reframing presets](references/social-presets.md). ## When to Use - `plan`: designing the overall edit structure from raw footage or transcript - `organize`: transcribing, labeling, identifying segments, generating edit decision lists - `cut`: deterministic FFmpeg operations (trim, split, concatenate, reframe, normalize) - `compose`: programmable overlays and compositions via Remotion (optional) Step 0 (load contexts): read `.ai-engineering/manifest.yml` `providers.stacks`; load `.ai-engineering/overrides/<stack>/conventions.md` for each stack and `.ai-engineering/overrides/_shared/conventions.md`; load `.ai-engineering/team/*.md` for team conventions. ## Common Mistakes - Trying to generate the whole video instead of compressing real footage. - Skipping organization or final polish. - Forcing one tool to span every layer. - Ignoring proxy / audio-normalization hygiene. - Replacing usable footage with generated assets. ## Examples ### Example 1 — highlight reel from a recording User: "cut this 60-minute talk into a 90-second highlight reel" ``` /ai-video-editing plan recording.mp4 ``` Plans cuts, transcribes, identifies highlight beats, runs FFmpeg trim+concat, normalizes audio, outputs the reel. ### Example 2 — reframe for TikTok User: "reframe this 16:9 demo for TikTok 9:16" ``` /ai-video-editing compose --source demo.mp4 --aspect 9:16 ``` Center-crop reframe with subject tracking via Remotion overlay, audio normalization, social-platform-ready output. ## Integration Called by: user directly, `/ai-build`. Calls: `ffmpeg` (deterministic cuts), Remotion (compositions), `/ai-media` (Layer 5 generated assets). See also: `/ai-media` (asset generation), `/ai-slides` (deck embeds), `/ai-visual` (cover art). $ARGUMENTS
More from arcasilesgroup/ai-engineering
- ai-adviseProactive governance advisor — checks standards, decisions, and quality trends during development. Always advisory, NEVER blocks. Three modes: `advise` (post-edit), `gate` (pre-dispatch), `drift` (on-demand decision audit). Trigger for 'governance check', 'advise on this change', 'check for drift', 'is this aligned with active decisions', 'shift-left advisory'. Not for blocking gates — use /ai-verify. Not for narrative code review — use /ai-review.
- ai-analyze-permissionsUse when Claude Code keeps asking to approve commands you have already approved, when settings.local.json has grown large, or when you want to consolidate permission grants into wildcard patterns. Trigger for 'too many permission prompts', 'clean up permissions', 'audit my settings', 'consolidate allow rules'. Claude Code only — not available in GitHub Copilot, Antigravity, or Codex.
- ai-animationDesigns motion, transitions, and micro-interactions for UI components: spring animations, gestures, easing, staggers — taste-driven detail compounding. Trigger for 'animate this', 'add transitions', 'micro-interactions for', 'gesture design', 'swipe to dismiss', 'easing for this', 'stagger the'. Not for design systems; use /ai-design instead. Not for visual art; use /ai-visual instead. Not for testing animation code; use /ai-test instead.
- ai-autopilotDelivers large multi-concern specs and backlog runs autonomously: decomposes specs into sub-specs (or normalizes work items into a backlog DAG), deep-plans with parallel agents, builds a dependency DAG, implements in waves, runs a single final quality loop with one bounded quality-remediation pass (verify+guard+review on full changeset), delivers via PR. Trigger for 'implement spec-NNN end to end', 'autopilot this', 'autonomous delivery', 'decompose and ship', 'run the backlog', 'execute these GitHub issues', 'process the sprint backlog'. Invocation is the approval gate. Not for small or single-concern tasks; use /ai-build instead. Not for ambiguous requirements; use /ai-brainstorm first.
- ai-boardOperates the project board (GitHub Projects v2 or Azure DevOps): discovers configuration after install (fields, state mappings, process templates) and syncs work-item state at lifecycle transitions. Trigger for 'set up the board', 'configure our ADO board', 'discover board fields', 'move this issue to in-review', 'update the board', 'mark as in progress', 'sync the work item state'. Two subcommands: `discover` (post-install configuration write) and `sync` (lifecycle state transitions). Auto-invoked via `sync` by /ai-brainstorm, /ai-build, and /ai-pr; fail-open. Not for backlog execution; use /ai-autopilot --backlog instead.
- ai-brainstormForces rigorous design interrogation BEFORE any code: explores approaches, surfaces ambiguity, gathers evidence, produces an approved spec that becomes the contract for /ai-plan. Trigger for 'lets add X', 'how should we handle Y', 'whats the best approach', 'I am thinking about', 'what should we build for'. Not for existing approved specs; use /ai-plan instead. Not for execution; use /ai-build instead.
- ai-branch-cleanupCleans branches safely: switches to the default branch, prunes merged and squash-merged branches, syncs to remote, sweeps stale specs, rotates `.ai-engineering/runtime/` per retention policy. Trigger for 'tidy up', 'tidy branches', 'sync to main', 'delete old branches', 'start fresh', 'rotate runtime'. Auto-invoked by /ai-pr after merge. Not for committing changes; use /ai-commit instead. Not for code-level dead-code removal; use /ai-simplify instead.
- ai-buildCanonical implementation gateway: reads approved plan.md, resolves stack from manifest, deterministic-routes each task to its adapter, dispatches the build agent in an isolated worktree, runs TDD self-validation per task, then a single final quality loop with one bounded quality-remediation pass on the full changeset before /ai-pr. Trigger for 'go', 'start building', 'execute the plan', 'implement it', 'lets do this', 'build the plan', 'resume', 'continue'. Not without an approved plan; run /ai-plan first. Not for multi-concern specs needing decomposition; use /ai-autopilot instead. Not for a single function or subcomponent; use /ai-code.
- ai-codeWrites production code that satisfies stack-context standards on the first pass: interface-first design, backward-compatibility checks, lightweight self-review. Trigger for 'implement this', 'write the code for', 'add X to Y', 'build this function', 'make this work'. Not for tests; use /ai-test instead. Not for debugging; use /ai-debug instead. Not for refactoring; use /ai-simplify instead. Not for executing an approved plan end-to-end; use /ai-build (the gateway).
- ai-commitRuns the governed commit pipeline: auto-branches from protected, stages selectively, formats and lints, scans for secrets, gates docs, composes a conventional message, pushes. Trigger for 'commit my changes', 'save my work', 'push this to remote', 'stage these files', 'ship it'. Not for opening a PR; use /ai-pr instead. Not for branch hygiene; use /ai-branch-cleanup instead.