Skip to content
OpenAgentSkill
Browsing is open · Catalog captured 2026-11-21 · Automatic updates and account services are paused.
Video & audio

edit-video-with-valmera

Edit uploaded footage through Valmera's authenticated MCP connector, review a rendered preview, and deliver an MP4. Use for conversational cuts, captions, framing, sound and visual treatments on a chosen video project.

ABO3SKRALMASAOODI · Static checks on file

Installation

Read the source and dependencies before running a command. Copying does not install or execute anything.

npx skills add ABO3SKRALMASAOODI/valmera-mcp --skill edit-video-with-valmera

About this skill


name: edit-video-with-valmera description: Edit uploaded footage through Valmera's authenticated MCP connector, review a rendered preview, and deliver an MP4. Use for conversational cuts, captions, framing, sound and visual treatments on a chosen video project. license: MIT

Edit a video with Valmera

Valmera is a hosted AI video editor. The connected assistant calls editing tools directly; it does not delegate the edit to Valmera's in-house agent. Changes create versioned editing state and preserve the original upload.

Connection and cost

Connect to https://valmera.io/mcp/server and authenticate using the client setup guide. Discover the current tools and input schemas in the connected session; the names below describe a workflow, not a permanent catalog.

Account creation and uploads are free; editing requires a paid Valmera plan. Before billable work, explain the intended scope and use any cost estimate exposed by the account. If an exact quote is unavailable, say so and obtain approval for a bounded preview before proceeding. Reuse an existing explicit scope and budget approval; ask again if the work would exceed it. Do not buy credits or upgrade a plan without authorization. Review a preview before an approved final export.

Workflow

  1. Choose the project and result. Use list_projects and open_project to identify the intended recording. Reuse the user's brief; clarify only missing decisions that materially change the edit. State the destination, aspect ratio, target duration and delivery files. For new media, use Studio or the upload_start → file transfer → upload_finish protocol. A path mentioned in chat does not upload a file.
  2. Wait for source readiness. Follow index_status until analysis is ready. Read the transcript and available visual evidence before selecting cuts. get_transcript, get_words, get_shots, find_silences and look_at can inform the plan when available.
  3. Apply focused changes. Select tools from the current session for the requested treatment. For example, cut_silences or keep_segments shapes the cut; add_captions and set_caption_style handle caption appearance; auto_reframe changes framing; audio and visual tools add supporting material. Use each returned schema instead of guessing arguments. Check that cuts preserve the speaker's meaning.
  4. Review a representative preview. Call render_preview; follow its existing job with wait_for_job. Inspect the rendered result with look_at or watch_video as supported by the client. Check cut boundaries, readable text, framing and sound. Fix a small sample before repeating a treatment across a long recording.
  5. Report the version and clock. Identify the project and reviewed edit version. Distinguish source timestamps from output timestamps in revision notes; a time in a shortened or reordered preview may refer to a different source moment. Describe what was verified and any unresolved requirement.
  6. Deliver the approved version. When final export is authorized, call export_final with the intended project_id and reviewed edl_version, then wait_for_job, then download_url with kind="final". A job ID is a receipt, not a finished video. Return the actual final link and identify the version. Verify the downloaded file when the client can inspect it; otherwise state what still needs checking.

Requirements that change the plan

  • Identify approved source files and any supporting material to supply, source or create. Use the creative-media brief for new visual requirements.
  • Specify caption language, names, appearance and whether delivery needs burned-in text, a subtitle file or both. Confirm the required output against current project options and the caption guide.
  • Name the dialogue source, music treatment and passages needing attention. Compare a sound change with the source before extending it.
  • For multiple deliverables, review each aspect ratio and export version. Use the delivery guide for destination requirements.
  • Let an active Studio or MCP edit finish before editing the same project from another client. On a queued or running job, continue with its existing job ID; inspect a terminal failure before retrying.

For a worked result, see the original motion-graphic trim-and-reframe example. It documents an actual cuts-and-crop export; it does not demonstrate every treatment above. For multiple stories from one recording, use the turn-long-video-into-shorts skill when installed.