Update to Creative Claw

{
  "name": "creativeclaw",
  "description": "Route mixed, ambiguous, cross-modal, or workspace-management requests through Creative Claw. Use when the user asks to use Creative Claw generally, needs several media types, or needs account balances, generation charges, purchases/subscriptions, assets, themes, onboarding, or existing-media editing; prefer a focused skill for one clear outcome.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 526
    },
    {
      "relative_path": "assets/platform-dimensions.json",
      "size_in_bytes": 2003
    },
    {
      "relative_path": "references/async-jobs.md",
      "size_in_bytes": 1891
    },
    {
      "relative_path": "references/avatars/identity.md",
      "size_in_bytes": 4236
    },
    {
      "relative_path": "references/images/gpt-image-2.md",
      "size_in_bytes": 10996
    },
    {
      "relative_path": "references/images/index.md",
      "size_in_bytes": 456
    },
    {
      "relative_path": "references/images/nano-banana-2.md",
      "size_in_bytes": 8817
    },
    {
      "relative_path": "references/images/nano-banana-pro.md",
      "size_in_bytes": 8779
    },
    {
      "relative_path": "references/images/seedream-5-pro.md",
      "size_in_bytes": 9556
    },
    {
      "relative_path": "references/job-recovery.md",
      "size_in_bytes": 3786
    },
    {
      "relative_path": "references/media-assembly.md",
      "size_in_bytes": 3876
    },
    {
      "relative_path": "references/platform-client.md",
      "size_in_bytes": 1287
    },
    {
      "relative_path": "references/platform-dimensions.md",
      "size_in_bytes": 1359
    },
    {
      "relative_path": "references/platform-upload.md",
      "size_in_bytes": 1477
    },
    {
      "relative_path": "references/tool-catalog.md",
      "size_in_bytes": 12058
    },
    {
      "relative_path": "references/video/gemini-omni.md",
      "size_in_bytes": 9538
    },
    {
      "relative_path": "references/video/index.md",
      "size_in_bytes": 1823
    },
    {
      "relative_path": "references/video/minimax-h3-max.md",
      "size_in_bytes": 9097
    },
    {
      "relative_path": "references/video/other-models.md",
      "size_in_bytes": 4257
    },
    {
      "relative_path": "references/video/recipe-character-scene.md",
      "size_in_bytes": 2966
    },
    {
      "relative_path": "references/video/recipe-product-ad.md",
      "size_in_bytes": 2998
    },
    {
      "relative_path": "references/video/recipe-source-edit.md",
      "size_in_bytes": 2620
    },
    {
      "relative_path": "references/video/reference-production.md",
      "size_in_bytes": 7381
    },
    {
      "relative_path": "references/video/review.md",
      "size_in_bytes": 1909
    },
    {
      "relative_path": "references/video/seedance-2-5.md",
      "size_in_bytes": 12711
    },
    {
      "relative_path": "references/video/seedance-mini.md",
      "size_in_bytes": 1480
    },
    {
      "relative_path": "references/video/ugc-paths.md",
      "size_in_bytes": 2923
    },
    {
      "relative_path": "references/video/wan-3.md",
      "size_in_bytes": 8665
    },
    {
      "relative_path": "references/voices/alternatives.md",
      "size_in_bytes": 1799
    },
    {
      "relative_path": "references/voices/cartesia-sonic-guide.md",
      "size_in_bytes": 4950
    },
    {
      "relative_path": "references/voices/cartesia.md",
      "size_in_bytes": 2200
    },
    {
      "relative_path": "references/voices/chatterbox-guide.md",
      "size_in_bytes": 3410
    },
    {
      "relative_path": "references/voices/cloning.md",
      "size_in_bytes": 4020
    },
    {
      "relative_path": "references/voices/elevenlabs-v2-guide.md",
      "size_in_bytes": 7975
    },
    {
      "relative_path": "references/voices/elevenlabs-v2.md",
      "size_in_bytes": 1784
    },
    {
      "relative_path": "references/voices/elevenlabs-v3-guide.md",
      "size_in_bytes": 9349
    },
    {
      "relative_path": "references/voices/elevenlabs-v3.md",
      "size_in_bytes": 1795
    },
    {
      "relative_path": "references/voices/languages.md",
      "size_in_bytes": 2776
    },
    {
      "relative_path": "references/voices/minimax-speech-guide.md",
      "size_in_bytes": 3453
    },
    {
      "relative_path": "references/voices/xai-tts-guide.md",
      "size_in_bytes": 11625
    },
    {
      "relative_path": "references/workflow-basics.md",
      "size_in_bytes": 7159
    },
    {
      "relative_path": "references/workflows/account.md",
      "size_in_bytes": 3506
    },
    {
      "relative_path": "references/workflows/asset-library.md",
      "size_in_bytes": 2757
    },
    {
      "relative_path": "references/workflows/audio.md",
      "size_in_bytes": 6928
    },
    {
      "relative_path": "references/workflows/brand-theme.md",
      "size_in_bytes": 5123
    },
    {
      "relative_path": "references/workflows/characters-and-film.md",
      "size_in_bytes": 5562
    },
    {
      "relative_path": "references/workflows/edit-video.md",
      "size_in_bytes": 5562
    },
    {
      "relative_path": "references/workflows/feedback.md",
      "size_in_bytes": 3555
    },
    {
      "relative_path": "references/workflows/image-gen.md",
      "size_in_bytes": 5755
    },
    {
      "relative_path": "references/workflows/onboard.md",
      "size_in_bytes": 2400
    },
    {
      "relative_path": "references/workflows/storyboard-to-video.md",
      "size_in_bytes": 4929
    },
    {
      "relative_path": "references/workflows/video-gen.md",
      "size_in_bytes": 6396
    }
  ],
  "skill_md_contents": "---\nname: creativeclaw\ndescription: \"Route mixed, ambiguous, cross-modal, or workspace-management requests through Creative Claw. Use when the user asks to use Creative Claw generally, needs several media types, or needs account balances, generation charges, purchases/subscriptions, assets, themes, onboarding, or existing-media editing; prefer a focused skill for one clear outcome.\"\n---\n\n# Creative Claw\n\nRead [shared execution guidance](references/workflow-basics.md) once per task before using tools. It covers existing authorization, model discovery, optional cost checks, imports, and recovery.\n\nUse the Creative Claw MCP server as a media workspace: source durable assets, apply a brand theme, choose a model by capability, generate or process media, and save results for reuse.\n\n## Account and billing questions\n\nUse `manage_account` for current balance, recent generations and their recorded charges/refunds. For purchase and subscription management, open its account view and use the returned account-page controls; the tool itself is read-only. Read [account and cost guidance](references/workflows/account.md) before interpreting charges. Use `estimate_generation` for future quotes, not the cost of a past generation. Do not submit feedback automatically for an account question.\n\n## Operating rules\n\n1. **Inspect before generating.** Use `search_assets` for likely reusable media and `get_theme` for branded work.\n2. **Discover only what is missing.** Use `list_models({ category })` when choosing or checking availability; use `get_model_params` for a known selected model. Reuse current-task schemas until a model/operation changes or an error indicates they need refreshing.\n3. **Use durable references.** Read `references/platform-upload.md` before importing attached or local media. Pass Creative Claw URLs to generation and processing tools.\n4. **Keep exact control syntax intact.** Preserve approved references, dialogue, timecodes, and layout instructions. Speech receives the exact performed script in `text`.\n5. **Respect the user’s requested scope and budget.** Use `estimate_generation` only when the user asks about cost, balance, affordability, or supplies a budget constraint. An estimate does not add an approval gate: proceed with requested work that fits the constraints. Do not ask routine cost or permission questions. Clarify only material scope changes, missing essential choices, or explicit tool confirmation requirements.\n6. **Treat queued work as unfinished.** The inline viewer may monitor a generation for the user. Call `check_job` when another tool needs the completed URL, or when no viewer is monitoring the job. Never claim completion from a job ID alone.\n7. **Organize outputs.** Give assets meaningful metadata when the tool supports it; otherwise use `update_asset` after completion. Use stable tags across a project.\n8. **Do not invent tools or parameters.** If a tool is absent on the current client, follow `references/platform-client.md`. Use the exposed tool schema for top-level fields and `get_model_params` for model-specific settings.\n9. **Capture actionable feedback.** Use `submit_feedback` for bugs, missing features or models, confusing flows, generation-quality problems and praise only when the user asks or approves sending it. A complaint alone is not permission to contact the team. Read `references/workflows/feedback.md` before reporting.\n10. **Match the user's language.** Conduct the workflow in the user's language, preserve supplied scripts and visible copy exactly, and verify the selected model supports the requested spoken or rendered language.\n11. **Use examples deliberately.** For speech voice selection, use `get_model_params` and the voiceover workflow. For other media, route requests for examples, inspiration, styles, or a close starting point to `creativeclaw-find-examples`. Do not search the catalog before every generation.\n12. **Keep HTML rendering explicit.** Use `creativeclaw-render-html-image` or `creativeclaw-render-html-video` only when the user explicitly requests HTML/CSS, HyperFrames, code-driven rendering, or accepts that proposed method. Ordinary image or video requests stay with the generative skills.\n\n## HTML-video example discovery\n\nFor explicit HTML-video/HyperFrames work, look for relevant `search_examples` matches (use `render_type: \"html_video\"` when exposed) and load selected results with `get_example`. Returned `sourceType` distinguishes a complete HTML document from a downloadable ZIP project plus description. Inspect the source and decide what to adapt. Use single HTML for basic short videos; use ZIP only when adapting a selected full-project example or the user already has a full HyperFrames project. The `creativeclaw-render-html-video` skill covers both; shared timing, shader and design references apply to both. This does not route ordinary generative video requests into HTML rendering.\n\n## Route the request\n\n| User wants | Primary route |\n| --- | --- |\n| Understand balance, past generation costs, charges/refunds, or manage purchases/subscriptions | `manage_account`, following [account guidance](references/workflows/account.md) |\n| Generate or edit one general image | `creativeclaw-generate-image` |\n| Create a consistent product image set | `creativeclaw-product-photoshoot` |\n| Generate, extend, reframe, or transform one video clip | `creativeclaw-generate-video` |\n| Plan a script, shot list, or storyboard | `creativeclaw-plan-video` |\n| Produce a complete multi-shot film | `creativeclaw-build-film` |\n| Create a creator-style product ad | `creativeclaw-create-ugc-ad` |\n| Generate narration, dialogue, or speech | `creativeclaw-generate-voiceover` |\n| Generate a score, music bed, sting, jingle, theme, or song | `creativeclaw-generate-music` |\n| Generate sound effects, ambience, Foley, loops, impacts, or UI cues | `creativeclaw-generate-sound-effects` |\n| Clone a consented voice | `creativeclaw-clone-voice` |\n| Browse, filter, load, or adapt curated examples | `creativeclaw-find-examples` |\n| Explicitly render HTML/CSS as a PNG | `creativeclaw-render-html-image` |\n| Explicitly render HTML/HyperFrames motion as video | `creativeclaw-render-html-video` |\n| Add or create an intro/outro around existing video | `creativeclaw-add-video-intro-outro` |\n| Create a personal avatar from photos or a reusable identity sheet | `creativeclaw-create-avatar` |\n| Create or update a reusable Character | `creativeclaw-create-character` |\n| Report a bug, request, quality issue, or praise | `creativeclaw-submit-feedback` |\n| Find, import, name, tag, reuse, or delete media | `references/workflows/asset-library.md` |\n| Create, inspect, edit, or apply a brand theme | `references/workflows/brand-theme.md` |\n| Trim, resize, caption, transcribe, clean, or combine existing media | `creativeclaw-edit-media` |\n| Select highlights from long footage and create vertical Reels | `creativeclaw-create-reels` |\n| Cut, reorder, and reframe chosen video moments | `creativeclaw-cut-and-reframe-video` |\n| Learn what Creative Claw can do | `references/workflows/onboard.md` |\n\nUse an explicit outcome over a generic modality. If the user names a model, keep the outcome skill in control and use the matching packaged model reference for prompt and reference details. Use this root skill for requests that span outcomes or do not have one clear owner. Read the matching workflow before calling a mutating or paid tool.\n\n## Default model policy\n\n- **Images:** default to `image/nano-banana-2` for most generation and editing. It is the primary cost-efficient recommendation because it offers the best overall balance of quality, speed, and cost. Use `image/gpt-image-2.5-flare` for fast OpenAI image work, and escalate to `image/nano-banana-pro`, `image/gpt-image-2.5-sunburst`, or `image/seedream-5-pro` when their specialty materially improves the requested result. Do not proactively surface lower-tier or internal-route variants.\n- **Video:** default to `video/gemini-omni-flash`. Recommend `video/seedance-2.5` for premium long or reference-rich work, `video/seedance-2.0-mini` as Seedance Mini for inexpensive drafts, `video/minimax-h3-max` for fast cinematic native-audio work, or `video/minimax-h3-max-turbo` for the faster lightweight H3 Max route. For existing footage, route through `references/workflows/edit-video.md` instead of applying this generation ranking. Never recommend or proactively route to an LTX or DreamActor model.\n- **Speech:** use `speech/elevenlabs-v3` for stock voices and general speech. Use `speech/elevenlabs-v2` only with an existing cloned Character voice in supported languages. Recommend `speech/cartesia-sonic` for cloned speech too; it also supports explicitly selected stock voices. Use v3 with an existing clone when expressive tags or broader language support are needed. Never clone without consent or silently switch providers. Load `creativeclaw-generate-voiceover` for the selected model's reference and current settings.\n- **Audio:** use `generate_sound_effect` with `sfx/elevenlabs-sound-v2` for sound effects, Foley, ambience, and loops. Use `generate_music` with `music/elevenlabs-music-v2.5` for scores, music beds, stings, jingles, and songs. Do not pass non-speech model IDs to `generate_speech`.\n\nVerify missing capabilities with runtime discovery, then reuse the selected schema for unchanged operations within the task.\n\nFor image prompting, load [the selected image model reference](references/images/index.md). Video outcome skills package their selected video model references. For speech, load creativeclaw-generate-voiceover and only its selected model guide. There are no standalone model skills; the outcome workflow owns authorization, execution and delivery.\n\n## Shared production pattern\n\n1. Clarify the deliverable, audience, duration or dimensions, and required references.\n2. Search the asset library and import only what is missing. When the user wants inspiration or a starting point, search curated examples and load only the selected example.\n3. Fetch the selected theme for branded work.\n4. Inspect available models and the chosen model's parameters.\n5. State consequential settings briefly; honor existing authorization and user-requested review stages without asking again.\n6. Generate or process the media.\n7. Resolve any queued job needed by later steps.\n8. Inspect the result, revise deliberately, and preserve approved anchors.\n9. Name, tag, and describe the final assets.\n\n## References\n\n- `references/tool-catalog.md` — current tool routing by purpose.\n- `references/async-jobs.md` — queued-job handling.\n- `references/platform-upload.md` — attachment, local-file, picker, and URL ingestion.\n- `references/platform-client.md` — client capability and connection rules.\n- `references/platform-dimensions.md` — common image and video sizes.\n\n## ElevenLabs model routing\n\nUse `creativeclaw-generate-voiceover` for speech routing. V2 is only for existing clones, v3 is the stock-voice default, and Cartesia is recommended for clones too. Read the selected model reference; do not transfer tags or settings between providers.\n"
}