[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75EXDAVE4YRT227WCVMRTWJ":3,"skill-same:01M75EXDAVE4YRT227WCVMRTWJ":45},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":25,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":28,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M75EXDAVE4YRT227WCVMRTWJ","seedance-2-prompt-engineering-skill",null,"javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fdandysuper\u002Fseedance-2-prompt-engineering-skill\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"# Seedance 2.0 JiMeng Skill (OpenClaw \u002F ClawHub)\n\n## Purpose\nCreate high-control English prompts for **Seedance 2.0** and **Seedance 2.0 Fast** using multimodal references (image\u002Fvideo\u002Faudio\u002Ftext).\n\nThis skill is for:\n- Prompt design from rough idea to production-ready prompt\n- Mode choice: **Text-only** vs **First\u002FLast Frame** vs **All-Reference**\n- `@asset` mapping (what each image\u002Fvideo\u002Faudio controls)\n- 4-15s duration planning and timeline beats\n- Multi-segment stitching for videos **>15s**\n- Video extension \u002F continuation prompts\n- Character replacement and directed editing prompts\n- Camera-language replication from reference videos\n- Scenario-specific strategies (product ads, short drama, fantasy, music video, etc.)\n\n---\n\n## Core Rules\n\n1. Always declare mode first.\n2. Always include an explicit **Assets Mapping** section.\n3. Use timecoded beats with one major action per segment.\n4. Keep prompts concise and controllable (avoid vague poetic-only wording).\n5. Add negative constraints when user needs clean output.\n6. **Be specific and visual** — \"a woman in a red trench coat walks through rain-soaked neon streets\" >> \"a woman walking\".\n7. **Separate dialogue\u002Fsound from visuals** — write dialogue with character name + emotion tag, then sound effects as a distinct layer.\n8. **Match reference image style to video theme** — e.g., ink-wash style images for historical themes, neon renders for cyberpunk.\n\n---\n\n## Platform Limits (Seedance 2.0)\n\n- Mixed inputs total (image+video+audio): **max 12 files**\n- Images: jpeg\u002Fpng\u002Fwebp\u002Fbmp\u002Ftiff\u002Fgif, **max 9**, each \u003C 30MB\n- Videos: mp4\u002Fmov, **max 3**, total duration 2-15s, total \u003C 50MB\n- Audio: mp3\u002Fwav, **max 3**, total \u003C= 15s, total \u003C 15MB\n- Generation duration: **4-15s**\n- Realistic human face references may be blocked by platform compliance\n\n---\n\n## Output Format (use by default)\n\n1. **Mode**\n2. **Assets Mapping**\n3. **Final Prompt**\n4. **Negative Constraints**\n5. **Generation Settings**\n\nExample skeleton:\n\n```text\nMode: All-Reference\nAssets Mapping:\n- @image1: first frame \u002F identity anchor\n- @video1: camera language + motion rhythm\n- @audio1: optional soundtrack pacing\n\nFinal Prompt:\n[ratio], [duration], [style].\n0-3s: [action + camera].\n3-7s: [action + transition].\n7-10s: [reveal\u002Fclimax + end frame].\nPreserve identity and scene continuity. Use physically plausible motion and coherent lighting.\n\nNegative Constraints:\nno watermark, no logo, no subtitles, no on-screen text.\n\nGeneration Settings:\nDuration: 10s\nAspect Ratio: 9:16\n```\n\n---\n\n## IP \u002F Copyright Avoidance (Moderation-Safe Prompting)\n\nSeedance 2.0 has platform-side content moderation. Prompts referencing recognizable franchises, characters, or brand aesthetics will be **rejected** even if no name is used. Follow these rules:\n\n### Core Principles\n\n1. **Never use franchise names, character names, or brand terms** — not even as \"style of\" references.\n2. **Invent fully original names** for characters and creatures. Use descriptive nicknames (e.g., \"Alloy Sentinel\", \"Storm-Rabbit\").\n3. **Describe aesthetics generically** — replace recognizable signature features with original alternatives:\n   - ❌ \"arc reactor\" → ✅ \"hex-light energy core\"\n   - ❌ \"yellow lightning mouse\" → ✅ \"tiny storm-rabbit with glowing cyan antlers\"\n   - ❌ \"red-gold armored suit\" → ✅ \"custom exo-suit with smooth ceramic panels\"\n4. **Add explicit negative constraints** listing every franchise name, character name, and brand term that could be inferred.\n5. **Use family-friendly \u002F PG-13 tone markers** — they help pass moderation.\n\n### Progressive Fallback Strategy\n\nIf a prompt is rejected, escalate distance from the source IP:\n\n1. **Level 1**: Replace all names with original nicknames, keep general aesthetic.\n2. **Level 2**: Replace signature visual features (colors, silhouette, iconic props) with fully original designs.\n3. **Level 3**: Change character type entirely (e.g., humanoid hero → autonomous mech + drone; creature battle → abstract elemental spirits).\n\n### Toy \u002F Figure Animation\n\nWhen animating toy or doll references from images:\n- Strip all brand indicators from the prompt.\n- Use \"original vinyl-style toy figure\" or \"collectible art figure\" instead of any brand name.\n- Bind `@image1` to proportions, colors, outfit shape only — never preserve logos or trademarks.\n\n---\n\n## Special Cases\n\n### A) Extend Video\nExplicitly write: `Extend @video1 by Xs`.\nUse generation duration equal to the **newly added segment**, not the full final length.\n\n### B) Replace Character\nBind base motion\u002Fcamera to `@video1`, bind replacement identity to `@image1`, and request strict choreography\u002Ftiming preservation.\n\n### C) Beat Sync\nUse `@video`\u002F`@audio` rhythm references and lock beats by time range.\n\n### D) Text-Only Generation\nUse when no reference assets are provided. Prompt must carry all visual direction: style, color palette, character descriptions, camera, and timeline beats. Especially useful for original creature\u002Fcharacter concepts and IP-safe scenes.\n\n### E) Multi-Segment Stitching (Videos > 15s)\nSeedance 2.0 max generation is **15s per segment**. For longer videos, split into chained segments:\n\n1. **Segment 1**: Generate normally (up to 15s). End on a **clean handoff frame** (stable pose, clear composition).\n2. **Segment 2+**: Upload previous segment as `@video1`, write `Extend @video1 by Xs`. Include a **continuity note** describing exactly what the last frame looks like.\n3. Repeat until target duration is reached.\n\nAlways include:\n- **Total duration** and **segment count** at the top.\n- **Handoff description** at the end of each segment (what the last frame shows).\n- Explicit continuity instructions: preserve identity, outfit, lighting, camera direction.\n\n### F) Short Drama with Dialogue\nFor scripted scenes with character speech:\n- Write visual action and dialogue as **separate layers** per time segment.\n- Tag dialogue: `Dialogue (CharacterName, emotion): \"line\"`\n- Tag sound: `Sound: [description]`\n- Keep dialogue short — one line per 3-5s segment works best.\n\n### G) Product Showcase \u002F E-Commerce Ad\nFor product demos and ads:\n- Bind product image to `@image1` as identity anchor.\n- Use techniques: **360° rotation**, **3D exploded view**, **reassembly animation**, **hero lighting**.\n- Keep background clean (studio, gradient, or contextual lifestyle).\n- Specify material rendering: glass reflections, metallic sheen, matte texture, etc.\n\n### H) One-Take Long Shot (Multi-Image Waypoints)\nFor continuous tracking shots without cuts:\n- Assign each `@image` to a **scene waypoint** (location, character, or prop encountered along the path).\n- Write the prompt as a continuous camera movement visiting each waypoint in order.\n- Explicitly state: `no cuts, single continuous shot` or `one-take`.\n- Use `@image1` as first frame, subsequent images as reference for environments\u002Fcharacters encountered.\n\n---\n\n## Scenario-Specific Strategies\n\n| Scenario | Key Techniques | Typical Mode |\n|---|---|---|\n| **E-commerce \u002F Product Ad** | 360° spin, 3D exploded view, hero lighting, clean studio BG | All-Reference |\n| **Short Drama \u002F Dialogue** | Dialogue tags with emotion, sound FX layer, actor blocking | All-Reference or First Frame |\n| **Fantasy \u002F Xianxia Animation** | Spell FX particles, martial arts choreography, energy auras | Text-only or All-Reference |\n| **Science \u002F Education** | 4K CGI, transparent anatomy, labeled zoom sequences | Text-only |\n| **Music Video \u002F Beat Sync** | Beat-locked cuts, widescreen 16:9, multi-image montage | All-Reference with @audio |\n| **One-Take Tracking Shot** | Multi-image waypoints, continuous camera, no cuts | All-Reference |\n| **IP-Safe Original Characters** | Invented names, unique features, explicit negative constraints | Text-only |\n\n---\n\n## Files in this skill\n\n- `SKILL.md` — main skill behavior\n- `SKILL.sh` — quick local test helper\n- `scripts\u002Fsetup_seedance_prompt_workspace.sh` — scaffold helper files\n- `references\u002Frecipes.md` — ready-to-use prompt recipes\n- `references\u002Fmodes-and-recipes.md` — mode and control notes\n- `references\u002Fcamera-and-styles.md` — camera language and visual styles vocabulary\n",{},"main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fdandysuper\u002Fseedance-2-prompt-engineering-skill",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":7,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill seedance-2-prompt-engineering-skill",{"tool":37,"command":38},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill seedance-2-prompt-engineering-skill",{"tool":40,"command":41},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill seedance-2-prompt-engineering-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fdandysuper\u002Fseedance-2-prompt-engineering-skill\u002FSKILL.md",true,[],[46,54,61,68,75,82],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":53},"01M778GGXG2VQ0YF31W2MKGMQZ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":53},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":53},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":53},"01M778FQQNSEYA3HJKZBPQ4M9Z","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":53},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":53},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]