agentleFS
skulitomskulitom/Cutbolt/skills/deliver-and-review/SKILL.md

deliver-and-review

Skill1 starsChanged 22 days agoMITView on GitHub

Export a saved Cutbolt edit, inspect the delivered file and optionally create an OTIO handoff with explicit loss acknowledgement.

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use $PROJECT_ID at its intended saved head.

    line 8
  2. Very specific:

    If the saved project does not exist yet, load the cutbolt setup skill first and use its source inspection and initial linked snapshot.

    line 13
  3. Very specific:

    Use its ticket as $JOB_ID.

    line 24
  4. Distinctive:

    Start review only after job.wait reports the export completed.

    line 34
  5. Distinctive:

    If the project has changed since export, use the exact exported revision in the project reference rather than comparing the file with an …

    line 38
  6. Very specific:

    Use its new ticket as $JOB_ID.

    line 46
  7. Distinctive:

    Run this section only when the user requests project interchange.

    line 59
  8. Very specific:

    Read losses and required_acknowledgements.

    line 66

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Deliver a saved edit

Use $PROJECT_ID at its intended saved head. Choose a new $OUTPUT (for example delivery.mp4) and an $INPUT_TRANSFER matching the project's working RGB declaration. Do not guess a different transfer to make an export pass. Use listed cutbolt_* tools or cutbolt_run. Examples are engine requests with placeholders replaced by actual values.

If the saved project does not exist yet, load the cutbolt setup skill first and use its source inspection and initial linked snapshot. Do not guess setup operations from delivery examples. Return here with the created project ID and revision.

Export and wait

<!-- example: export -->
{"command":"job.start","request_id":"delivery-export","run":"export.run","arguments":{"project":{"project_id":"$PROJECT_ID"},"output":"$OUTPUT","profile":"h264_aac","streams":"audio_video","input_transfer":"$INPUT_TRANSFER"}}

Use its ticket as $JOB_ID. A running job needs another bounded wait; failed, interrupted or cancelled is not a successful delivery.

<!-- example: wait-export -->
{"command":"job.wait","job_id":"$JOB_ID","timeout_seconds":120}

Review the actual delivered file

Start review only after job.wait reports the export completed. Queuing export and review together does not create a dependency; a review can run before the file exists. The export receipt verifies the encoded file. Review adds contact sheets, timing checks and audio measurements. Set $REVIEW_OUTPUT to a new directory name, such as review. If the project has changed since export, use the exact exported revision in the project reference rather than comparing the file with an unrelated new head.

<!-- example: review -->
{"command":"job.start","request_id":"delivery-review","run":"export.review","arguments":{"path":"$OUTPUT","output":"$REVIEW_OUTPUT","project":{"project_id":"$PROJECT_ID"},"frames":4,"rendition_height":0}}

Use its new ticket as $JOB_ID.

<!-- example: wait-review -->
{"command":"job.wait","job_id":"$JOB_ID","timeout_seconds":120}

Inside result, check timing.video.ok and timing.audio.ok, the review summary, image sheet and relevant audio/playback. A passing duration check alone does not establish editorial quality. The full measurements remain in review.json inside the review folder.

Optional OTIO handoff

Run this section only when the user requests project interchange.

<!-- example: inspect-handoff -->
{"command":"interchange.export.inspect","project":{"project_id":"$PROJECT_ID"}}

Read losses and required_acknowledgements. Only acknowledge losses acceptable for the requested handoff; editing_links omits Cutbolt link groups, and declared_transfer omits the RGB transfer declaration. Keep that declaration in delivery notes if accepting its loss. Blocking losses need another representation or explicit editing changes. $ACKNOWLEDGEMENTS is the accepted list from that result, and $HANDOFF_OUTPUT is a new .otio filename.

<!-- example: handoff -->
{"command":"interchange.export","project":{"project_id":"$PROJECT_ID"},"output":"$HANDOFF_OUTPUT","acknowledged_losses":"$ACKNOWLEDGEMENTS"}

Return the actual output paths and material limitations. Do not claim portable behavior for another editor/build without a tested transfer. Preserve the source assets required by a handoff. For OUTPUT_EXISTS choose a new path. For source changes, revalidate/rebind the intended media; never bypass a content-identity mismatch. For job failure, follow retry/path/hint before retrying.

This workflow runs on Windows and Linux with external FFmpeg/ffprobe. Speech recognition, when needed, requires a separately configured local runtime and model. Recording and hardware decode have no Linux backend. The plugin bundles no engine, fonts, models or media tools.

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.