Fantasy Transform Video Gen Seedance2.0

Transform any everyday scene, action, or subject into a fantastical, magical, ritual-rich vertical video using WeryAI Seedance 2.0 only. Use when you need fe...

Security Scan

The skill's code, runtime instructions, and required credential (WERYAI_API_KEY) are consistent with a video-generation integration for WeryAI Seedance 2.0.

Purpose & Capability

Name/description claim to produce fantasy-styled videos using WeryAI Seedance 2.0; required items (node and WERYAI_API_KEY) and the included CLI script target exactly that API and model. Nothing requested (binaries, env vars, or config paths) appears unrelated to the stated purpose.

Instruction Scope

SKILL.md confines runtime actions to expanding prompts, validating parameters, running the included node CLI, and returning URLs. It explicitly limits image inputs to public https URLs and instructs how to present results. It also documents that the script does not enforce the skill-level model constraint (caller must pass model:"SEEDANCE_2_0"). No instructions ask for unrelated system files or extra credentials.

Install Mechanism

No install spec is provided (instruction-only with a shipped JS script). The script uses only standard Node 18+ APIs and makes HTTPS calls to two WeryAI hosts. No third-party downloads, shorteners, or extract steps are present.

Credentials

Only WERYAI_API_KEY is required and declared as primaryEnv, which matches the skill's need to call WeryAI services. The SKILL.md and resources explicitly warn to treat the key as sensitive. No unrelated credentials or high-privilege paths are requested.

Persistence & Privilege

The skill does not request always:true and does not modify other skills or system-wide settings. It runs on demand and requires an explicit API key; no elevated persistence or cross-skill privileges are requested.

Assessment

This package appears coherent for calling WeryAI Seedance 2.0. Before installing: only set WERYAI_API_KEY if you trust the source; review scripts/video_gen.js yourself (it will send your prompt and any public image URLs to api.weryai.com and api-growth-agent.weryai.com); run in an isolated or short-lived environment if you prefer; note the script requires you to pass model:"SEEDANCE_2_0" (the code enforces a non-empty model but not the specific model); expect usage to consume WeryAI credits and ensure your images are public https URLs.

Fantasy & magic style transform (Seedance 2.0)

Turn ordinary moments into fantasy-forward shorts: subjects feel enchanted, props read as magical artifacts, space becomes mysterious, light breaks into particles, motion feels ritual, and audio leans ethereal when generate_audio is on.

Dependencies: WERYAI_API_KEY + Node.js 18+. This skill uses only SEEDANCE_2_0. When you run the CLI, {baseDir}/scripts/video_gen.js must exist; WERYAI_VIDEO_API.md must exist under {baseDir}/resources/ (supply both via publish or pre-use assembly). Full commands and JSON fields: see resources/WERYAI_VIDEO_API.md. No other Cursor skills required.

Prerequisites

• WERYAI_API_KEY must be set before running video_gen.js.
• Node.js 18+; image inputs must be public https URLs (no local paths).
• Model (caller / agent): The bundled video_gen.js requires a non-empty model in JSON—if model is missing or blank, the CLI exits with MISSING_PARAM (no default model). The script does not enforce this skill's allowed model in code: you must set "model":"SEEDANCE_2_0" for this package and show it in the confirmation table before submit—see WERYAI_VIDEO_API.md (model row).
• Each wait run may consume credits; re-run creates new paid tasks.

Security, secrets, and API hosts

• WERYAI_API_KEY: Treat as a secret. Only configure it if you trust this skill's source; it is listed in OpenClaw metadata as requires.env / primaryEnv so installers know it is mandatory at runtime (never commit it inside the skill package).
• API hosts (fixed in video_gen.js): Video tasks use https://api.weryai.com; the models list uses https://api-growth-agent.weryai.com. Child skills must not document or rely on URL environment-variable overrides—only WERYAI_API_KEY is read from the environment.
• Higher assurance: Run generation in a short-lived or isolated environment (separate account or container), and review scripts/video_gen.js (HTTPS submit + poll loop) before production use.

Prompt expansion (mandatory)

video_gen.js does not expand prompts. Before every wait --json, turn the user's short or vague brief into a full English production prompt that re-styles the described event into this skill's look.

When: User input is short, vague, or missing cinematic detail. Exception: They supply a finished long prompt within 2000 characters and ask you not to rewrite—still show the full text in the confirmation table.

Always add: shot size and angle; camera move; lighting and color grade aligned to this skill; subject action paced to duration; one clear payoff; platform framing (9:16 unless user chose another allowed ratio); if generate_audio is true, describe ambience / SFX in generic words (no copyrighted music references).

Length: Stay within prompt_length_limit 2000 for SEEDANCE_2_0; trim adjectives before losing the core transformation beat.

Confirmation: The pre-submit table must include the full expanded prompt.

Style transformation checklist

• Subject fantasy: crowns, runes, familiars, subtle glamour—keep identity readable if image-to-video.
• Props as magic: wands, grimoires, floating sigils, glowing liquids—integrate with the user’s core action.
• Mysterious space: mist, ancient arches, floating platforms, depth haze—vertical 9:16 composition.
• Particle & glow: motes, ember trails, soft bloom—motivated by “magic source,” not random noise.
• Ritual motion: deliberate gestures, circle pacing, slow reveals—paced to duration.
• Sound (if audio on): airy pads, chimes, distant choir hints—describe in prompt; no copyrighted tracks.

Fits: Festival energy, dreamlike tone, fairy-tale read, isekai / otherworld vibe.

### Example prompts below are richness targets only—always derive from the user's actual brief.

Workflow

1. Confirm the request matches this skill (text-to-video and/or single image-to-video).
2. Collect the user's brief, optional image URL, and tier (best / good / fast)—all map to SEEDANCE_2_0 with different duration defaults (see Recommended models).
3. Expand prompt (mandatory): Unless the user opted out with a finished long prompt, expand using ## Prompt expansion (mandatory). Do not submit only the user's minimal words.
4. Validate model is SEEDANCE_2_0 only; validate duration, aspect_ratio, resolution, generate_audio against the frozen tables.
5. Show the confirmation table with the full expanded prompt; wait for confirm or edits.
6. Run node {baseDir}/scripts/video_gen.js wait --json '...'.
7. Parse stdout JSON; return videos URLs or explain errors.
8. When presenting playable URLs to the user, use Markdown inline links only (e.g. [Video](https://...)). Do not wrap user-facing links in code fences.

CLI reference

node {baseDir}/scripts/video_gen.js wait --json '{"model":"SEEDANCE_2_0","prompt":"…","duration":10,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}'

Full reference: WERYAI_VIDEO_API.md.

Definition of done

Done when the user gets at least one playable Video-style link, or a clear failure with next steps. Submitted prompt must be the expanded prompt unless the user explicitly opted out. Never use another model_key in this skill.

Boundaries (out of scope)

• Do not use any model other than SEEDANCE_2_0 for this package.
• Do not link to weryai-model-capabilities.md or shared ../references/ paths; use resources/WERYAI_VIDEO_API.md for CLI/API details.
• Do not use local file paths for image; never embed the secret value of WERYAI_API_KEY in files.
• Do not invent API fields; do not send negative_prompt (not supported for this model).
• Do not wrap user-facing playable URLs in Markdown code fences.

Example prompts

• Office worker pours coffee → liquid turns into glowing stardust spiral, ritual slow pour, 9:16
• Street crossing at night → lanterns and floating runes, gentle particle snow, cinematic vertical
• HTTPS portrait → same person, subtle magic aura pulse, ceremonial hand lift, soft particles

---

Model and API constraints (frozen for this skill)

Derived from node {baseDir}/scripts/video_gen.js models alignment at authoring time; re-run models after platform upgrades. This skill is locked to SEEDANCE_2_0 only.

Text-to-video

model_key	durations	aspect_ratios	resolutions	Audio	negative_prompt	prompt limit
SEEDANCE_2_0	5, 10, 15	9:16, 1:1, 16:9	480p, 720p	Yes	No (do not send)	2000

Image-to-video (single image)

model_key	durations	aspect_ratios	resolutions	Audio	negative_prompt	upload_image_limit
SEEDANCE_2_0	5, 10, 15	9:16, 1:1, 16:9	480p, 720p	Yes	No (do not send)	3

---

Recommended models

Tier	model_key	Notes
⭐ Best (default)	SEEDANCE_2_0	Prefer duration 10 or 15, resolution 720p, generate_audio true for fullest mood
👍 Good	SEEDANCE_2_0	Balanced: duration 10, resolution 720p, audio per user
⚡ Fast	SEEDANCE_2_0	Snappy: duration 5, resolution 480p or 720p, audio optional

Tier only changes duration / resolution / audio defaults—never the model.

---

Default parameters

Field	Value
Model	SEEDANCE_2_0 (fixed)
Aspect ratio	9:16
Duration	10 (use 5 for punchy; 15 for slower ceremony)
Resolution	720p (480p allowed)
Audio	true unless user wants silent

---

Scenario: Text-to-video style transform

Flow

1. Capture the user's mundane event in one or two sentences.
2. Expand into English with the Style transformation checklist; keep identity generic unless user names a character.
3. Confirmation table → user confirm.
4. Execute:

node {baseDir}/scripts/video_gen.js wait --json '{"model":"SEEDANCE_2_0","prompt":"<expanded>","duration":10,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}'

5. Return [Video](url) links.

---

Scenario: Image-to-video style transform

Before use: image must be https:// and reachable.

1. Plan how the still re-styles in motion (props, light, environment) without breaking likeness if the user requests preservation.
2. Expand prompt; add image to the confirmation table.
3. After confirm:

node {baseDir}/scripts/video_gen.js wait --json '{"model":"SEEDANCE_2_0","prompt":"<expanded>","image":"https://…","duration":10,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}'

4. Return [Video](url) links.

---

Loop seam (optional)

If the user asks for a seamless loop, append a short English trio at the end of the expanded prompt: seamless loop, perfect loop, ends where it begins—no separate API flag.

Generated for skill fantasy-transform-video-gen-seedance2.0.