Agent skill

Seedance Prompting Skills For Cinematic Films

by alecs5am in alecs5am/ralphy

When to use Trigger this skill when the user requests photorealistic cinematic motion — not stylized animation, not motion design, not UGC.

MITAuto-check passedMedia & Creative

Install Seedance Prompting Skills For Cinematic Films

skills CLI
$ npx skills add alecs5am/ralphy --skill seedance-prompting-skills-for-cinematic-films -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install alecs5am/ralphy seedance-prompting-skills-for-cinematic-films --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/alecs5am/ralphy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/notes/skills/seedance-prompting-skills-for-cinematic-films .claude/skills/seedance-prompting-skills-for-cinematic-films && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
seedance-prompting-skills-for-cinematic-films
GitHub stars
138
Token cost
~3.8k tokens
SKILL.md length
2,209 words
Files
1
Skills in repo
28
Repo updated
First seen
Licence
MIT

At a glance

When to use Trigger this skill when the user requests photorealistic cinematic motion — not stylized animation, not motion design, not UGC.

  • This skill when the user requests photorealistic cinematic motion — not stylized animation
  • SKILL.md covers Core principle, The grounded cinematic prompt…, Scene-specific patterns and Driving scene (interior, day…, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Not motion design

What it does

Seedance Prompting Skills For Cinematic Films is an agent skill from alecs5am/ralphy. When to use Trigger this skill when the user requests photorealistic cinematic motion — not stylized animation, not motion design, not UGC. Specifically:

Its SKILL.md is about 3.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering AI video generation, Influencer and creator marketing and Motion graphics. It works with Seedance. The repository describes itself as: Open-source desktop app for content creation, with an agent runtime and standalone CLI. The licence is MIT.

When your agent uses it

  • This skill when the user requests photorealistic cinematic motion — not stylized animation
  • Not motion design

Example prompts

  • “/seedance-prompting-skills-for-cinematic-films”

What it can do on your machine

Read from SKILL.md and the folder at commit 8d139f0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Seedance Prompting Skills For Cinematic Films loads about 3.8k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 2,209 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~3.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from alecs5am/ralphy at commit 8d139f0, republished under its MIT licence (© alecs5am). 2,209 words, ~3,841 tokens.

Download SKILL.mdSave it as .claude/skills/seedance-prompting-skills-for-cinematic-films/SKILL.md (or your agent's skills folder).
name
seedance-prompting-skills-for-cinematic-films
description
When to use Trigger this skill when the user requests photorealistic cinematic motion — not stylized animation, not motion design, not UGC. Specifically:
license
MIT

Seedance Prompting Skills For Cinematic Films

"cinematic film prompt", "film-style scene", "shot like a movie" "realistic body movement", "grounded motion", "natural human behavior" "emotional close-up", "restrained performance", "subtle expression" "driving scene", "intimacy scene", "action sequence", "fight choreography" "environmental interaction" — wind, rain, water resistance, dust, gravity "continuity reference", "match cut", "scene-to-scene continuity" "Seedance cinematic prompt", "photorealistic motion", "live-action prompt" If the request is for animation, cartoon, motion design, UGC, or podcast, defer to the matching skill in video-generation instead.

Core principle

Cinematic realism is built from restraint, not spectacle. Every prompt enforces five grounding pillars that prevent Seedance from drifting into the over-animated, floaty, AI-looking failure modes that plague text-to-video output.

The five pillars:

  • Body weight & physics — actors have mass; movement has friction, momentum, and contact force.
  • Environmental force — wind, water, gravity, fabric, and surface texture push back on the actor.
  • Emotional restraint — micro-expressions, held beats, breath. No exaggerated facial telegraphing.
  • Camera as observer — the lens has its own physical presence (weight, breathing, drift). Not a drone, not a god.
  • Continuity anchors — lighting direction, wardrobe, time-of-day, and prop position carry across shots.
  • A prompt that drops any pillar produces "AI cinema" — technically a video, structurally a tell.

The grounded cinematic prompt structure

Seedance 2.0 prompts for cinematic film follow this six-block order. The order is load-bearing — Seedance weights the earliest blocks most heavily for compositional decisions, and the later blocks for motion and audio.

[STYLE & MOOD] [SHOT DIRECTION] [ACTOR BEHAVIOR] [ENVIRONMENTAL FORCE] [CAMERA BEHAVIOR] [AUDIO] Block 1 — Style & Mood (1 line) One sentence. Cinematographer lexicon. Pick a film stock or DP reference if the user has given you one; otherwise default to "35mm anamorphic, naturalistic color, soft contrast."

✓ "35mm anamorphic, naturalistic skin tones, soft window light, muted teal-and-amber palette." ✗ "Cinematic, beautiful, dramatic, epic." Adjective stacks ("cinematic, beautiful, dramatic") flatten output. Specificity sharpens it.

Block 2 — Shot Direction (1 sentence) The action distilled. Subject, verb, object, location. No adjectives that aren't doing structural work.

✓ "A woman in her forties leans against a kitchen counter, reading a folded letter." ✗ "A beautiful sad woman sadly reads a heartbreaking letter in a sad kitchen." Block 3 — Actor Behavior (2-3 sentences) This is where grounding lives. Write the actor's body the way a director gives notes — physical, specific, restrained.

Always include:

  • A weight cue — where the body's mass is settled ("weight on her right hip", "shoulders dropped", "hand braced on the counter").
  • A micro-action — a small involuntary motion ("she swallows", "his jaw tightens once", "her thumb traces the paper's edge").
  • A held beat — a moment of stillness with intent ("she pauses for two seconds before reading the next line").

Forbidden:

  • "Tears stream down her face" → Seedance over-renders this. Use: "her eyes glass over; she does not blink."
  • "He runs furiously" → Use: "he breaks into a run, shoulder leading, arms compact."
  • "Smiles widely" → Use: "the corner of her mouth lifts, then settles."
  • Block 4 — Environmental Force (1-2 sentences)
  • What pushes back on the actor. Without this, Seedance generates actors in a vacuum and the shot reads as a soundstage.

Categories:

Air: wind direction and strength on hair, fabric, dust.

Water: rain weight on shoulders, water sheeting off surfaces, droplet trails.

Gravity: how the actor's weight transfers — hip-shift, knee-bend, contact with chair/wall/ground.

Surface: floor compliance (carpet absorbs step, hardwood transmits sound), wall texture catching light.

Light source: where is it, is it moving (passing car headlights, candle flicker, blinds shifting).

✓ "Wind from the open window lifts the left edge of her hair; the curtain breathes inward once."

✓ "Rain hits his shoulders in irregular bursts; water beads at his collar and falls."

Block 5 — Camera Behavior (1 sentence) The camera is a body too. Give it weight, intent, and limits.

Default cinematic camera lexicon Seedance understands well:

  • "Locked-off static frame, no movement."
  • "Slow handheld breathing, micro-drift."
  • "Dolly-in at walking pace, ending in medium close-up."
  • "Slow push from medium to close-up over 6 seconds."
  • "Slow truck right, following the actor's shoulder."
  • "Rack focus from foreground hand to background eyes."
  • "Anamorphic dolly, slight lens flare from off-screen window."

Forbidden:

  • "Epic sweeping drone shot" — produces flying, weightless, video-game camera.
  • "Cinematic camera movement" — too vague; Seedance defaults to floaty.
  • "360-degree rotation" — almost always breaks continuity and produces morph artifacts.
  • Block 6 — Audio (1 line)
  • Seedance generates native audio. Specify ambient first, then any vocal line.

✓ "Ambient: distant traffic, refrigerator hum, paper rustling. No dialogue." ✓ "Ambient: rain on glass, single car passing. She whispers, 'I'm still here.'" If silence is intended, write: "Ambient: room tone only. No dialogue, no music."

Scene-specific patterns

Below are battle-tested patterns for the scene types this skill is most often invoked for. Use them as starting templates, not rigid forms.

Driving scene (interior, day or night)

35mm anamorphic, naturalistic skin tones, low-key interior with passing exterior light.

A man in his late thirties drives alone on a two-lane highway at dusk.

His hands rest on the wheel at 9 and 3, grip relaxed. He glances at the rearview mirror once, then back to the road. His jaw is set; he has not spoken in some time.

Light from passing streetlamps and oncoming headlights sweeps across his face in slow rhythmic bands. The cabin is enclosed; dust motes catch in the side window light.

Locked-off frame on the driver, slight handheld breathing. Background out-of-focus highway moving at speed.

Ambient: tire hum on asphalt, faint heater fan, occasional passing vehicle. No music, no dialogue. Critical: lock the camera or use very gentle handheld. Aggressive camera in a driving cabin reads as music video, not film.

Emotional close-up (held, restrained)

35mm anamorphic, naturalistic skin tones, soft north-facing window light, shallow depth of field.

A woman in her forties stands at a kitchen window, holding a folded letter.

She does not open it. Her thumb traces the fold once. Her shoulders settle, the weight of her body shifting to her left foot. Her eyes glass over but she does not blink; she swallows once.

Daylight from the window catches the side of her face; the curtain behind her stirs faintly. Dust visible in the light beam.

Slow push from medium to tight close-up over the full shot duration, ending at her eyes.

Ambient: distant kitchen radio playing softly under the noise floor, refrigerator hum, paper rustling between her fingers. No dialogue. Critical: no tears, no telegraphed grief. The performance lives in the held beat and the micro-action.

Action sequence (foot chase / pursuit, grounded)

35mm anamorphic, naturalistic color, overcast daylight, handheld vérité.

A man in his thirties runs down a narrow alley between brick buildings, pursued from off-screen.

His stride is compact, arms tucked, shoulder leading into each turn. He clips a steel trash can with his hip without slowing. His breathing is audible, irregular. He glances back once, then forward.

Wet pavement catches the gray sky; puddles splash where his feet land. A loose plastic bag tumbles past him in the wind. Brick walls close on both sides.

Handheld camera following at his shoulder height, two paces behind, breathing with his stride. Lens flares briefly when he passes an open doorway.

Ambient: footsteps on wet concrete, his breathing, distant city traffic, the bag scraping against the wall. No music. Critical: keep stride compact. Seedance over-renders "sprinting" as bouncy, weightless action-hero pose. Write "compact, shoulder-leading" to ground it.

Intimacy scene (restrained, close)

35mm, naturalistic skin tones, warm low-key practical light from a bedside lamp, shallow depth of field.

Two people in their thirties sit close on the edge of a bed, neither speaking. One rests their forehead against the other's temple.

They breathe in near-sync. One hand finds the other's, fingers settling without grip. Neither moves to kiss; the stillness holds. A small smile passes between them, then fades.

The bedside lamp throws warm light across one side of both faces; the room behind is in shadow. Bedding compresses where they sit.

Static frame, no camera movement. Shallow focus held on the contact point between their foreheads.

Ambient: room tone, faint clock ticking, soft fabric movement. No dialogue, no music. Critical: intimacy is built from non-action. Resist the urge to add a kiss, a tear, a whispered line — Seedance over-renders all three.

Show full SKILL.md (861 more words)Show less

Environmental interaction (weather as character)

35mm anamorphic, naturalistic color, late-afternoon overcast, slight teal cast.

A woman in her fifties walks slowly along a coastal cliff path, hands in her coat pockets.

Her stride is measured, weight settling into each step against the slope. The wind catches her hair from the left; she does not push it back. Her coat collar flutters; she pulls it tighter once.

Strong onshore wind shapes everything in frame — grass laid flat, her coat pressed against her body, salt spray visible in the air. The sea below is gray and churning; gulls hold position against the wind.

Slow truck right, matching her pace, framing her in medium-wide profile with the sea beyond. The horizon line stays level.

Ambient: wind through grass, distant surf, gull calls. Her footsteps soft on the path. No dialogue, no music. Critical: the wind must shape multiple elements (hair, coat, grass, gulls) — single-element wind reads as a fan on set.

Continuity references — multi-shot scenes When the user asks for a multi-shot cinematic sequence (a beat, a scene, an exchange), continuity is enforced through anchors that appear in every shot's prompt, not through hoping Seedance will remember.

For every shot in the sequence, copy these anchors verbatim into the prompt:

  • Lighting anchor: same source, same direction. "Late-afternoon window light from screen-left" — in every prompt.
  • Wardrobe anchor: full description, same wording. "Navy wool coat, gray scarf, no jewelry" — in every prompt.
  • Time-of-day anchor: explicit. "Overcast late afternoon, ~4pm light" — in every prompt.
  • Geography anchor: where the actor was at the end of the previous shot. "She has just stepped back from the kitchen counter; in this shot she stands at the window."
  • Audio bed anchor: same ambient signature. "Ambient: distant kitchen radio, refrigerator hum" — across all interior shots.

For visual identity continuity (same face across shots), use the persistent element pattern from skills/media/video-generation/SKILL.md — generate one anchor portrait, register it as a character element, embed <<<element_id>>> in every shot's prompt. Do not re-upload portraits per shot.

For visual continuity of a location, register the establishing shot as an environment element similarly.

Submission

After authoring the prompt, submit via Seedance 2.0:

json

higgsfield_generate({ "requests": [{ "type": "generation", "model": "seedance_2_0", "media_type": "video", "params": { "prompt": "<the six-block prompt>", "duration": 8, "aspect_ratio": "21:9", "generate_audio": true } }] }) Defaults for cinematic film:

  • aspect_ratio: 21:9 (anamorphic feel) or 16:9 (standard). Use 9:16 only when the user explicitly requests vertical.
  • duration: 6-10s for single shots. 4-5s for hard cuts. 12-15s only for slow held scenes (intimacy, environmental).
  • generate_audio: always true unless the user requests silence (and even then write "Ambient: room tone only").

Failure modes and how to fix them Symptom Cause Fix Actor moves like they're floating / no weight No body-weight cue in Block 3 Add "weight settled on her right hip" / "shoulders dropped" / "hand braced on the counter" Hair, fabric, environment look static No environmental force in Block 4 Add a wind/gravity/surface line Face is over-acted, telegraphed grief/joy Verbs like "cries", "smiles widely", "rages" Replace with micro-actions: "swallows once", "corner of mouth lifts then settles" Camera flies, drones, swoops "Sweeping" / "epic" / "drone" / "cinematic camera movement" Replace with specific lexicon: "locked-off", "slow handheld", "dolly-in at walking pace" Scene reads as soundstage No environmental force AND no audio bed Add both Block 4 and Block 6 in full Continuity drift across shots No anchors repeated in each prompt Copy the five anchors verbatim into every shot's prompt Driving scene feels like a music video Camera moves too much Lock the frame; use slight handheld breathing only

Output discipline

Return only what the user needs:

  • The submitted job_ids (handled by the frontend — do not paste them into the reply).
  • A brief plain-language description of what was made ("Here's the held close-up at the kitchen window, 21:9, 8 seconds, ambient room tone").

Never paste:

  • The full six-block prompt (unless the user explicitly asks to see it).
  • Tool internals, media IDs, element IDs.
  • The framework itself ("I applied the five grounding pillars…") — the user wants the shot, not the methodology.
  • Pitfalls
  • Do not stack adjectives in Block 1. "Cinematic, beautiful, dramatic, epic, stunning" produces flatter output than a single specific film-stock reference.
  • Do not write the actor's emotion as a verb. Write the body, write the micro-action — emotion emerges from restraint, not declaration.
  • Do not skip Block 4. Without environmental force, every cinematic prompt reads as a soundstage no matter how good the rest is.
  • Do not give the camera unlimited freedom. A locked-off frame is more cinematic than a swooping drone shot 90% of the time.
  • Do not generate one shot per beat in a multi-shot scene without anchors. Continuity is not automatic; it is enforced via repeated wardrobe/light/audio descriptions in every prompt.
  • Do not use this skill for animation, cartoons, motion design, or UGC. Defer to the matching skill in video-generation/references/.
  • Verification

After submission, the user sees the rendered video from the frontend automatically. The agent does not need to poll unless the result is feeding into a downstream generation in the same turn (see video-generation/SKILL.md fire-and-forget policy).

If the user reports a failure mode, consult the table above and rewrite the offending block — do not switch models. Quality lives in the prompt structure, not the engine.

© alecs5am, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in notes/skills/seedance-prompting-skills-for-cinematic-films of alecs5am/ralphy.

Open the folder on GitHubat commit 8d139f0

Compare with similar skills

Seedance Prompting Skills For Cinematic Films next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Seedance Prompting Skills For Cinematic Films compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Seedance Prompting Skills For Cinematic Films this skillalecs5am/ralphy138—~3.8kAutomated safety check: PassMIT
Super Video MakerBomx/super-video-maker-skill310—~11kAutomated safety check: NotesNone
Seedance Cartoonbeshuaxian/higgsfield-seedance2-jineng952—~20kAutomated safety check: PassNone
Seedance AI Avatarrediumvex/ai-video-generator-claude409—~6.7kAutomated safety check: PassMIT
Seedance Motion Design Adbeshuaxian/higgsfield-seedance2-jineng952—~14kAutomated safety check: PassNone
Seedance Motion Design Adbeshuaxian/higgsfield-seedance2-jineng952—~1.8kAutomated safety check: PassNone

Similar skills

  • Super Video Maker

    Bomx/super-video-maker-skill

    End-to-end AI video production skill for agentic frameworks.

    310 GitHub stars~11k tokensUpdated 2 mo ago
    Media & CreativeAuto-check: notes
  • Seedance Cartoon

    beshuaxian/higgsfield-seedance2-jineng

    Generate cartoon and animation style video prompts for Seedance 2.0 on Higgsfield.

    952 GitHub stars~20k tokensUpdated 6 mo ago
    Media & CreativeAuto-check passed
  • Seedance AI Avatar

    rediumvex/ai-video-generator-claude

    Generate AI avatar and digital persona video prompts for Seedance 2.0 on Higgsfield.

    409 GitHub stars~6.7k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed
  • Seedance Motion Design Ad

    beshuaxian/higgsfield-seedance2-jineng

    Generate motion design advertisement video prompts for software and tech companies using Seedance 2.0 on Higgsfield.

    952 GitHub stars~14k tokensUpdated 6 mo ago
    Media & CreativeAuto-check passed
  • Seedance Motion Design Ad

    beshuaxian/higgsfield-seedance2-jineng

    为软件和技术公司使用 Seedance 2.0(Higgsfield)生成运动设计广告视频提示。在用户想要创建软件产品广告、SaaS推广、应用启动视频、技术演示、UI展示、启动视频或技术公司的运动图形时使用。触发条件:软件广告、SaaS视频、产品发布、应用推广、技术商业广告、UI动画、运动设计广告、启动视频、产品演示视频、功能展示,或任何软件/技术推广视频请求。即使是"为我的应用制作视频"或"推…

    952 GitHub stars~1.8k tokensUpdated 6 mo ago
    Media & CreativeAuto-check passed
  • Analyze Video

    krusemediallc/arcads-claude-code

    Analyze a reference video and reverse-engineer its style into a reusable Seedance 2.0 prompting template.

    1.6k GitHub stars~4.2k tokensUpdated 18 days ago
    Media & CreativeAuto-check passed

More from alecs5am/ralphy

All 28 skills in this repo
  • Gsap

    alecs5am/ralphy

    GSAP animation reference for HyperFrames. An agent skill from alecs5am/ralphy.

    138 GitHub stars~2.4k tokensUpdated 18 days ago
    Auto-check passed
  • Researcher

    alecs5am/ralphy

    Deep-research workflow for UGC reference material — turns one or more URLs / handles / trend queries into a single cited research report (report.md + sources.json) that a scenarist or art-director…

    138 GitHub stars~1.9k tokensUpdated 18 days ago
    Auto-check passed
  • Editor

    alecs5am/ralphy

    Composition and render craft — assembles scenario.json plus asset-manifest.json into a HyperFrames HTML composition and renders the mp4.

    138 GitHub stars~3.6k tokensUpdated 18 days ago
    Auto-check passed
  • Evaluator

    alecs5am/ralphy

    Quality evaluation of rendered UGC mp4s — scene segmentation, audio loudness / dead-air, caption density, and per-scene visual analysis.

    138 GitHub stars~3.6k tokensUpdated 18 days ago
    Auto-check passed
  • Producer

    alecs5am/ralphy

    End-to-end orchestration — the wrapper that drives the whole production contract across roles, plus batch production.

    138 GitHub stars~4.7k tokensUpdated 18 days ago
    Auto-check passed
  • Scenarist

    alecs5am/ralphy

    Scenario and script craft — writes and reworks the scene-by-scene scenario.json: hook, beat structure, per-scene VO, on-screen text, pacing, and the language/aspect pre-flight.

    138 GitHub stars~3.2k tokensUpdated 18 days ago
    Auto-check passed

Works with

Questions about Seedance Prompting Skills For Cinematic Films

What does Seedance Prompting Skills For Cinematic Films do?

When to use Trigger this skill when the user requests photorealistic cinematic motion — not stylized animation, not motion design, not UGC. Seedance Prompting Skills For Cinematic Films is an agent skill from alecs5am/ralphy. When to use Trigger this skill when the user requests photorealistic cinematic motion — not stylized animation, not motion design, not UGC.

When should I use Seedance Prompting Skills For Cinematic Films?

Seedance Prompting Skills For Cinematic Films fits situations like: this skill when the user requests photorealistic cinematic motion — not stylized animation; not motion design.

How do I install Seedance Prompting Skills For Cinematic Films in Claude Code?

Run `npx skills add alecs5am/ralphy --skill seedance-prompting-skills-for-cinematic-films -a claude-code`. Or copy the skill folder (notes/skills/seedance-prompting-skills-for-cinematic-films in alecs5am/ralphy) into .claude/skills/seedance-prompting-skills-for-cinematic-films in your project. Claude Code loads it when a task matches its description.

How do I install Seedance Prompting Skills For Cinematic Films in Codex?

Run `npx skills add alecs5am/ralphy --skill seedance-prompting-skills-for-cinematic-films -a codex`. Or copy the skill folder (notes/skills/seedance-prompting-skills-for-cinematic-films in alecs5am/ralphy) into .agents/skills/seedance-prompting-skills-for-cinematic-films in your project. Codex loads it when a task matches its description.

Can I use Seedance Prompting Skills For Cinematic Films in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add alecs5am/ralphy --skill seedance-prompting-skills-for-cinematic-films -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/seedance-prompting-skills-for-cinematic-films, .gemini/skills/seedance-prompting-skills-for-cinematic-films, .github/skills/seedance-prompting-skills-for-cinematic-films and .opencode/skills/seedance-prompting-skills-for-cinematic-films in your project.

What does Seedance Prompting Skills For Cinematic Films need to run?

SKILL.md names no scripts, command-line tools or credentials: Seedance Prompting Skills For Cinematic Films is instructions for the agent only.

Does Seedance Prompting Skills For Cinematic Films access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Seedance Prompting Skills For Cinematic Films safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Seedance Prompting Skills For Cinematic Films use?

Seedance Prompting Skills For Cinematic Films is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Seedance Prompting Skills For Cinematic Films use?

About 3.8k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Seedance Prompting Skills For Cinematic Films?

Skills that share tags, products or a category with Seedance Prompting Skills For Cinematic Films: Super Video Maker (Bomx/super-video-maker-skill, 310 stars), Seedance Cartoon (beshuaxian/higgsfield-seedance2-jineng, 952 stars), Seedance AI Avatar (rediumvex/ai-video-generator-claude, 409 stars) and Seedance Motion Design Ad (beshuaxian/higgsfield-seedance2-jineng, 952 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Seedance Prompting Skills For Cinematic Films?

alecs5am (a GitHub user) maintains it in alecs5am/ralphy, which has 138 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on September 22, 2026.

Source: alecs5am/ralphy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.