Update to Wandeo

{
  "description": "Edit local media into an authored video with Wandeo, preview review, MP4 and subtitles. For science, mechanism and how-it-works explainers, use the bundled Anatomy authoring workflow before editing.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 190
    },
    {
      "relative_path": "references/director.md",
      "size_in_bytes": 8746
    },
    {
      "relative_path": "references/project-contract.md",
      "size_in_bytes": 5947
    },
    {
      "relative_path": "references/render-review.md",
      "size_in_bytes": 4729
    },
    {
      "relative_path": "references/spatial-3d.md",
      "size_in_bytes": 4749
    },
    {
      "relative_path": "references/spatial-anatomy.md",
      "size_in_bytes": 10643
    }
  ],
  "name": "auto-edit",
  "skill_md_contents": "---\nname: auto-edit\ndescription: Edit local media into an authored video with Wandeo, preview review, MP4 and subtitles. For science, mechanism and how-it-works explainers, use the bundled Anatomy authoring workflow before editing.\n---\n\nCLI file references are relative to the explicit `--project` directory. Resolve returned video, frame, screenshot, subtitle and workspace paths against that directory before reading files or passing them as `--input`; do not resolve them against the plugin directory. `[external file]` means the original input is outside the project; use the input path already supplied for that task. Normal results omit raw media tags, account/cache paths, process details and environment variables. Read only the source content and diagnostics needed for the user’s task.\n\nYou are the editor and director. Own the story, source selection, duration, copy, composition, motion and sound using the user's brief and real evidence. Use the plugin's `scripts/wandeo.sh` or `scripts/wandeo.ps1`; resolve the plugin root from this skill's location. Commands return JSON. The host supplies reasoning and file/image tools; no separate model API is required.\n\nFor science education, mechanisms, internal structures, physical processes and how-it-works videos, start with [Anatomy explainer](../anatomy-explainer/SKILL.md). Prefer its complete-object authoring workflow, then return here for narration, editing and export. Respect an explicit user choice of real footage, another visual style or an existing verified model. A simple equation or chart can remain 2D.\n\nRead [the project contract](references/project-contract.md) before authoring a timeline. Read [directing guidance](references/director.md) for open creative briefs, [spatial 3D guidance](references/spatial-3d.md) and [anatomy guidance](references/spatial-anatomy.md) when a shot may benefit from 3D, and [render review](references/render-review.md) when inspecting or revising a render. The plugin bundles the pinned anatomy kit, editable examples, authoring references and capture/audit tools under `third_party/anatomy/`; use those examples for dense parts, details, readouts, controls and WebGL layer composition. Generated example PDFs and HTML pages are omitted except for the turning-dial page used by the renderer. Use `project capabilities` and targeted `project recipes --query` to discover actual renderer features rather than guessing.\n\n1. Initialize or resume the requested `--project` directory. Inspect its manifest and director state before repeating work. Run setup when the render runtime is absent.\n2. Import selected user media with `media import`. Probe video/audio, then use `media frames --asset <id> --times <seconds>` to inspect actual images through the host's image tool. Sample relevant intervals densely enough to see actions and results. A frame filename or transcript is not an image observation. Use the capture skill when the task needs website or repository research.\n3. Transcribe speech locally with `media transcribe --asset <id>` when useful. Read its JSON cues and subtitle files. Preserve speech/visual causality and account for source trims and playback speed. Use user-provided narration/music or source audio; paid media-generation services are not bundled.\n4. Save the brief, evidence-backed claims, visual grammar and useful shot plans in `director-state.json` using [the directing contract](references/director.md). For a recorded demonstration, connect its claim to inspected actions and visible results, with source ranges and observable acceptance criteria. If the selected footage lacks the promised result, collect it or narrow the claim. Use `media focus --asset <id> --start <source-start> --end <source-end>` for editable camera candidates from interaction evidence. Inspect their source frames before choosing a candidate. Author `project.json` using registered assets and supported motion primitives. When a spatial shot is useful, state its target object, camera target, main action and observable result, then combine the spatial scene with 2D evidence where appropriate. For anatomy, complete the explainer Skill's research, object, model and visual checks before composing the film. Import its self-contained figure with `anatomy import`, reference it through `project.anatomyFigures` and reuse the same `figureId` across overview and detail shots. Use `anatomy.view` for model time, framing and emphasis. Author a subject-specific object using the upstream kit when no suitable figure exists; lack of a GLB is not a reason to substitute a few generic primitives or ask the user to source a model. Record unresolved scientific assumptions and simplify the claim honestly. Content and canvas follow the brief; no fixed film length, recipe quota or mandatory style applies.\n5. Run `project validate` and read `quality.findings` and `reviewPlan`. Fix invalid references and evidence gaps. Treat creative suggestions as prompts for judgment; record intentional choices rather than adding effects to satisfy a quota. Keep `presentation.showTimelineProgress` omitted or `false`; never add a horizontal playback progress bar to an authored export. Render a preview (optionally with `--start/--end`), then run `review`. Inspect its targeted frame images and `smallScreenFrames`, compare them with each shot's acceptance criteria, and investigate relevant static intervals, audio pauses and typography warnings. Listen to relevant audio ranges when supported. Technical success is not visual approval.\n6. For a requested visual/backend upgrade, save the prior render context as a `revisionRequest` baseline using [the render-review contract](references/render-review.md). Confirm the new `sourceUsage` and `spatialRuntime.observed` reflect the intended change; unchanged old source MP4s do not establish an upgrade. For each material issue, record the affected scene/range, observed problem, intended correction and expected visible difference. Re-render and inspect the affected range until the issue is resolved or its limitation is documented. Keep meaningful processing and reading holds. Render `final`, check final output, and deliver the MP4 plus applicable SRT/VTT and editable project directory. Review follows the saved render revision; frame timestamps and `--times` refer to the output file, while `timelineSeconds` refers to the full film.\n\nUse captions in the user's requested language, preserve names and technical terms, and verify actual Chinese glyphs. Never declare footage watched or a defect fixed without inspecting the resulting media. Do not impose an approval checkpoint for ordinary local editing; follow explicit user directions and the host's execution permissions.\n"
}