agentleFS
Galbaz1Galbaz1/video-research-mcp/skills/footage-edit/SKILL.md

footage-edit

Skill23 starsChanged 40 days agoMITView on GitHub

Prepare and assemble short edits from exact local source footage using measured frame lineage, scene revision approvals, contact previews and final technical gates.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    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
  1. Very specific:

    Use media_edit_footage for a bounded local linear edit.

    line 15

≈ “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

Local footage editing

Installed workflow resources

For a Claude installer layout, use the adjacent managed support directory ../video-research-resources/ and its ../video-research-resources/docs/integrations/FOOTAGE_EDIT.md. The ../video-research-resources/integrations/qwen/footage-edit.json records the selected component and requirements. The repository-relative references below apply when using a source checkout or unpacked npm package. Installing resources does not activate optional runtimes, providers or external source components.

Use media_edit_footage for a bounded local linear edit. Keep the existing external companion renderer separate. Read FOOTAGE_EDIT.md for the public fields, limits and evidence boundaries.

Prepare a chosen brief and one to eight unique scenes from at most two regular local sources. Bind each complete source SHA256, half-open source interval, declared FPS and explicit contiguous timeline start. Select only the required bounded crop, neutral-default grade and source-audio preservation/attenuation or explicit mute. This route supports hard cuts and compatible source grids/audio formats; do not claim unsupported compositing, music, transitions, fonts, SFX or external render engines.

Choose beats.mode: none when no music grid is asserted, declared with BPM/origin and an explicit cut tolerance, or offbeat to disclose an intentional mismatch. A declared grid is not detected musical timing.

Call action: prepare. Inspect the exact returned scene PNGs/contact evidence and the full original-PTS timeline ledger in the scope authorized by the caller. prepared means scene evidence exists; it does not mean a final was delivered. Preserve complete artifact and prepared-manifest hashes when communicating scene decisions.

For assembly, use the exact prepared manifest path/SHA and one approval per scene: scene_id, full scene_sha256, prepared_manifest_sha256 equal to that prepared revision, and locked: true. Use approval assertions supported by the current caller's intent and inspection; label their actual source. These integrity commitments do not authenticate the caller or establish human visual acceptance. Changes to the brief, source, treatment, timing or prepared evidence require approval of the new revision.

Call action: assemble only with the complete assertions. Report delivery only when the returned status is delivered; black spans, missing audio, failed full decode, clock/population mismatch, undefined measurements or failed hard loudness/peak bounds are terminal refusals. No automatic fallback or rerender retry is implied. Existing prepared/prior views survive final refusal or cancellation.

Finish with image_manifest_read using the exact returned manifest path/SHA. This rechecks original and actual artifact bytes after restart without rerendering. Native preview inclusion and text-only metadata refer to the same artifacts. Distinguish technical delivery, source integrity and the actual scope of visual/semantic/human review. Do not infer model/provider/native-isolation or standards qualification from ready/success status.

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.