mcpField
B
blitzreels-clipping

blitzreels-clipping

github.com/blitzreelsCreative & media4115 installsUpdated 7w ago
Repository

About blitzreels-clipping

A skill for operating BlitzReels' managed clip state machine, from source selection through quality checks and export. It is for workflows that need controlled clip creation, with explicit state transitions and user approval before paid exports.

Key features

  1. 01Resolve video URLs or workspace asset IDs
  2. 02Create clips with idempotency keys
  3. 03Track state transitions and next actions
  4. 04Choose selections and apply layouts
  5. 05Review QA and repair offered issues
  6. 06Export after approval and verify output

Use cases

  1. 01Create clips from public videos or workspace assets
  2. 02Review alternate clip selections before committing
  3. 03Repair a clip flagged by quality checks
  4. 04Export an approved, ready clip

MCP support

The skill can use the bundled MCP `clips_create` tool to create clips. It follows batch polling with `clips_get`.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/blitzreels/agent-skills --skill blitzreels-clipping

After installing, type/blitzreels-clippingin Claude Code to confirm it loaded.

Details

From the project README

BlitzReels Clipping

Use the managed clip state machine. It owns ingest, transcription, selection, layout, captions, QA, repair, and export sequencing.

Steps

  1. Resolve the source as a supported public video URL or workspace asset ID and resolve selection intent. Use a provided time range or suggestion; use automatic best selection only when choice is delegated. Complete when source and selection mode are explicit.
  2. Choose the available surface. Prefer the bundled MCP clips_create tool; otherwise discover the current contract with blitzreels agent-context --command "clips create" --json or the OpenAPI /clips operations. Complete when required inputs, mutation effects, and state fields are known.
  3. Create with a caller-generated idempotency key. Complete when the response contains a clip ID, project ID, state, and next_action.
  4. For MCP batches, follow batch.polling with clips_get. For managed API clips, follow next_action: poll, reselect, repair, export, or stop. Complete each transition only when the next response advances or reaches a terminal state.
  5. When the user retained selection choice, present available alternatives with title, hook, range, duration, and score; reselect the approved ID or range. Complete when the chosen selection is persisted.
  6. Validate layout intent. Tutorial layout is for flattened screen-share plus facecam footage. Interview and podcast footage use automatic, split, or focus layouts. Complete when applied layout and content type agree.
  7. Review QA previews and warnings; run only the repair action offered by current state. Complete when QA passes or the state reports a specific unresolved block.
  8. Start a paid export only after user approval and an export-ready state. Poll to terminal and verify output duration, aspect ratio, captions, framing, and download location.

Manual branch

Use low-level project media, transcript, timeline, caption, and preview operations only when managed state reports a specific block requiring manual control.

Return to the managed clip after the repair instead of rebuilding its state machine with low-level calls.

Completion

Return clip and project IDs, selected range, applied layout, QA result, warnings, export status, and download location.

If blocked, return next_action, the exact blocking state, and the user choice or system state required. Completion requires a verified terminal output or an explicit managed-state blocker.

Comments

Markdown supported