Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add alecs5am/ralphy --skill seedance-prompting-skills-for-cinematic-filmsgit clone --depth 1 https://github.com/alecs5am/ralphyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alecs5am/ralphy/seedance-prompting-skills-for-cinematic-films)<a href="https://agentmods.dev/skills/alecs5am/ralphy/seedance-prompting-skills-for-cinematic-films"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/seedance-prompting-skills-for-cinematic-films/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alecs5am/ralphy/seedance-prompting-skills-for-cinematic-films"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/seedance-prompting-skills-for-cinematic-films.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 262 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00045 | $0.03454 |
| Opus 5 | $0.00023 | $0.01727 |
| Sonnet 5 | $0.00009 | $0.00691 |
| Haiku 4.5 | $0.00005 | $0.00345 |
Grade A, and why
seedance-prompting-skills-for-cinematic-films scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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."
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 265 lines · 45 tokens per session scan A 1f8672162908
seedance-prompting-skills-for-cinematic-films is a skill published in the GitHub repository alecs5am/ralphy (133 stars, last pushed 3d ago), licensed Apache-2.0. It adds 45 tokens to every session and 3,454 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
video-gen
Use when generate videos with AI models — Runway, Kling, Sora, Pika, Seedance 2.0, Grok Imagine, Veo. Text-to-video, image-to-video, video extension, multi-modal references. Use when generating video from text prompts, animating images, or creating AI video content.
clinical-reports
Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation…
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
clinical-decision-support
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading…
immunology-assays
Computational analysis of immunology experimental data. ATAC-seq differential accessibility, immune cell tracking from microscopy, ELISA data processing with 4-parameter logistic fitting, immunohistochemistry quantification, antibody titer analysis, and cell cycle phase duration estimation. For flow cytometry use…
molecular-cloning
Molecular cloning simulation and design. PCR amplicon prediction, restriction enzyme digestion, Golden Gate and Gibson assembly simulation, primer design, CRISPR sgRNA design, and plasmid annotation. For protein-level sequence analysis use biopython or esm; for database lookups use gene-database or ensembl-database.