Edit video with Tesseract

For converting files to or from other editing tools, such as Premiere Pro or After Effects, read conversion. When opening shared or older .tsrct files, updating tools, or investigating load/render differences, read versions and compatibility.

The CLI may send basic usage telemetry for some commands. You can provide optional attribution via TESSERACT_SKILL=tesseract-video and the other attribution variables. Respect the CLI's telemetry opt-out setting; never enable telemetry on the user's behalf.

Make a deliberate edit from the user's material. Tesseract is the local editing and rendering engine; the agent supplies editorial judgment. The output is both a playable video and its editable project.

Start with the material

1. Resolve this skill's root from the directory containing this SKILL.md. Read CLI installation and check the required Tesseract version once per session. Use the resolved executable path throughout the task. Scripts and references are relative to the installed skill, not a guessed home directory or development checkout.
2. Read local operation. Probe the supplied media, sample frames at meaningful points, and listen to its audio using the host's available media tools. Metadata does not tell you what a shot depicts. If audio cannot be auditioned, disclose that limit rather than claiming a complete review.
3. Establish the deliverable, audience, aspect ratio, duration, must-keep moments, and supplied brand assets from the request. Ask only for missing information that materially changes the edit. For a small correction, preserve the existing edit's style and scope.
4. Read editorial decisions before planning a new edit. For each beat decide footage, footage with graphics, or full graphics and why. This is not a quota: do not add motion graphics just to demonstrate the engine.

For a new ad or a revision to its opening, read ad hooks. Build a visual hook in the opening seconds from the actual footage, proposition, and evidence. Consider distinct concepts, select the strongest, and map its reveal/motion and purposeful SFX to confirmed opening music cues when music is provided. Render and inspect the hook plus its handoff into the ad before polishing the rest. Preserve the scope of unrelated revisions.

Read waveform editing when music sets the pacing or when trimming talking footage. Generate and open the music waveform before planning picture timing; confirm beats, phrases, and major changes by listening and map visual arrivals to them. For speech, use overview and zoomed source waveforms to choose pause trims, protect quiet word boundaries, and retain natural breathing. Waveform markers are candidates, never automatic cut decisions.

For a substantial new video, share a concise edit plan with the source moments, their narrative purpose, graphic treatment, and audio intent. Routine authorized edits can proceed. Do not require a new approval for every local preview or revision.

Author the edit

• New edit: tsrct project create creates a portable .tsrct document; import local footage before placing its layers. Existing .tsrct: inspect and check out a copy of its editable JSON. Preserve the original and stable IDs. Save JSON through project commit, or apply supported action batches with project apply, before rendering.
• Read native authoring before changing project structure. Source time, edit time, and layer time are different clocks. In particular, moving a clip must not silently change which source moment it plays.
• Keep footage cuts, full scenes, and editable overlays as native layers in the document's single composition. Use groups for scenes. activeRange places a clip in its parent; sourceRange selects the source moment. Do not create base-video, caption, or audio tracks.
• For talking-head cuts, follow eyeline continuity: align the speaker’s eye height and screen position across cuts with appropriate framing, including punch-ins. Check the rendered outgoing/incoming frames and playback while preserving natural head movement and intentional camera changes.
• For motion work, read motion design, then only the relevant authoring reference. The examples demonstrate real schema; their visual style is not a required template.
• For every new edit or sound pass, read sound design. Consider dialogue, music, micro-SFX, structural cues, and foley/ambience; use the roles the piece needs. Add appropriate sounds from supplied/local assets or the procedural helper without per-cue approval. Import the selected files with project import-asset --kind audio, then keep them as editable Audio layers. Use audio and timing for placement, ducking, local preparation, and measurement. Preserve useful source audio and chosen music. Do not produce invented speech or captions.
• When footage needs color correction, a look, log conversion, or shot matching, or the user asks about color, read color grading. Follow its scene-aware workflow, including shot-local control when needed for a baked edit. Shot consistency is expected without a separate request, but intentional lighting differences should remain. Follow its source-relative neutral and skin checks: use median Lab regions from the original source and final output at matching timestamps, not your earlier graded preview. Keep corrections native and editable; protect skin under looks and check secondary selections against an exaggerated preview (the CLI has no matte-preview switch). Use only one spatial noiseReduction instance and check edge retention; see noise reduction. In a default document, HDR output does not make grades HDR-domain; for filmic highlights, light-like compositing, camera log without vendor LUTs, or one grade for SDR and HDR, use that reference's ACES section. See its Limitations before promising tracking or automatic matching.
• When talking audio needs cleanup, read speech cleanup. Diagnose room noise versus reverb/echo, use restrained EQ/dynamics or local noise reduction as appropriate, and compare at matched loudness. Preserve voice detail and timing; the plugin has no bundled dereverberation model.
• Keep typography, graphics, footage, and audio native and editable. Import supplied images as assets with project import-asset --kind image, not as a flattened replacement for text, vector graphics, or entire scenes. Use existing footage; this plugin provides no generative-video or avatar service.
• Respect the user's brand references. Mirage branding identifies this plugin, not every video created with it.

Look up capabilities only as needed

Use the installed CLI's schemas through local operation.

Read capabilities for the feature map and limits, FX authoring for native layers and footage, and motion for supported keyframe and script actions. Search for the specific definition needed rather than dumping the whole schema. The action schema includes supported standalone operations and their field restrictions; use local operation to choose actions versus JSON checkout/commit. The installed schema and actual render are authoritative.

Review and handoff

Use filmstrip review to inspect and correct visual changes. For dialogue cuts and music timing, follow waveform editing. Finish with review and delivery; report actual checks and any limitations. Follow final-export picture checks: inspect several exported timestamps away from cuts/fades, compare with the source, and block delivery on unexplained black picture. Use absolute local file links and show the video inline when supported. Cloud sync and publishing are not implemented.

If the host cannot execute local commands or access the local GPU/filesystem, explain that this package needs a local execution environment. Do not substitute a hosted service or silently switch rendering engines.