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 anymouschina/TapCanvas --skill seedance-recipesgit clone --depth 1 https://github.com/anymouschina/TapCanvasWrote 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/anymouschina/tapcanvas/seedance-recipes)<a href="https://agentmods.dev/skills/anymouschina/tapcanvas/seedance-recipes"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/seedance-recipes/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/anymouschina/tapcanvas/seedance-recipes"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/seedance-recipes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00052 | $0.01306 |
| Opus 5.5 | $0.00021 | $0.00522 |
| Sonnet 5.5 | $0.00010 | $0.00261 |
| Haiku 4.5 | $0.00005 | $0.00131 |
Grade A, and why
seedance-recipes 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 1mo 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.
This is a copy
84% identical to seedance-recipes — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
seedance-recipes
Surface reference contract: every literal @Image1/@Image2/@Video1/@Audio1 recipe below is a Seedance 2.0 surface example. Substitute only exact tokens supplied by the user or active structured surface; on Seedance 2.5 without token mapping, use neutral asset-role names and never emit the example tags.
Use recipes as starting patterns, not rigid prompt templates. Pick the recipe that matches the user's outcome, then customize subject, action, camera, lighting, audio, and constraints. Recipes should preserve the one-beat discipline of a short clip.
Load [ref:genre-guides] for genre patterns, [ref:examples-by-mode] when the user needs copy-ready examples, [ref:shot-list-continuity] for professional multi-shot sequences or commercials, and [ref:multilingual-community-examples] when the recipe should reflect Chinese/Russian/Japanese/Korean/Spanish community-style structures.
Intent
A recipe is a head start, never a mold. The user wants the confidence of a proven shape with their own story inside it. Bend the recipe to the story every time; a user who feels templated has been failed even if the output is competent.
Recipe Families
| Family | Best use | Core pattern |
|---|---|---|
| Product | Ads, ecommerce, hero shots, material reveals. | product anchor + one material change + controlled camera + logo preservation |
| Lifestyle | Human use, food, travel, social clips. | simple action + lived environment + handheld or natural light + ambient sound |
| Drama | Emotion, dialogue, short narrative beats. | character tag + gesture + motivated camera + silence or sparse sound |
| Music video | Beat sync, dance, stylized edits. | rhythm reference + visible beat changes + light pulses + clear character blocking |
| Landscape | Establishing shots, nature, atmosphere. | slow camera + weather motion + layered depth + natural sound |
| Commercial | Brand-safe polish and function. | problem/use/result beat + precise product constraint + clean light |
| Animation | Original characters and stylized motion. | medium + shape language + palette + elastic or weighted motion |
| VFX | Transformations, particles, weather, energy. | source + material behavior + interaction + dissipation endpoint |
| First/last frame | In-between transitions, product state changes, character pose targets. | first frame + last frame + continuous transition + identity locks |
| Commercial campaign | 6/10/15/30s variants, vertical/social cutdowns, textless/localized masters. | hook + product proof + end state + cutdown matrix + delivery notes |
| Short drama (短剧) | Fast-cut vertical mini-drama beats: setup, reversal, cliffhanger. | two or three labeled shots + one emotional reversal + held reaction close + cut on the sting |
| Talking head (口播) | Presenter, explainer, livestream-style pitch to camera. | locked medium close-up + short quoted lines + minimal head motion + caption-safe framing + room tone |
| Home / space tour | Walkthrough of a room, venue, or property. | single continuous take + steady forward path + light changes per zone + ambient sound only |
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.
- 1mo ago First seen · 75 lines · 52 tokens per session scan A e547ae020211
seedance-recipes is a skill published in the GitHub repository anymouschina/TapCanvas (686 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 1,306 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 84% identical to seedance-recipes, differing in 10 lines, and is treated as a copy.
Other skills, from other repositories
seedance-recipes
This skill should be used when the user asks for a Seedance 2.0 template, genre recipe, product ad, lifestyle video, drama scene, music video, landscape shot, commercial, animation scene, or reusable production pattern.
seedance-recipes
This skill should be used when the user asks for a Seedance 2.0 template, genre recipe, product ad, lifestyle video, drama scene, music video, landscape shot, commercial, animation scene, or reusable production pattern.
seedance-recipes
This skill should be used when the user asks for a Seedance 2.0 template, genre recipe, product ad, lifestyle video, drama scene, music video, landscape shot, commercial, animation scene, or reusable production pattern.
seedance-recipes
This skill should be used when the user asks for a Seedance 2.0 template, genre recipe, product ad, lifestyle video, drama scene, music video, landscape shot, commercial, animation scene, or reusable production pattern.
dramake
A production workflow for turning an idea, story, script, storyboard, or existing footage into a short AI drama or film. It covers planning, generation, voice, editing, and quality checks for formats such as vertical and horizontal video.
seedance-recipes
Apply genre recipe templates to Seedance 2.0 — product ads, fight scenes, brand films, mood pieces, dialogue clips, one-take journeys, music videos, novel adaptations, architecture walkthroughs, and action transfers. Use when you need a ready-made prompt structure for a known genre or format.