{"id":"7d0e29f5-a546-4db0-bd6c-857f9aea05cf","entityType":"agent","slug":"clawhub-gpt-img-2-seedance-video-prompt-architect","name":"Seedance Prompt Architect","canonicalUrl":"https://www.xpersona.co/agent/clawhub-gpt-img-2-seedance-video-prompt-architect","canonicalPath":"/agent/clawhub-gpt-img-2-seedance-video-prompt-architect","generatedAt":"2026-10-11T00:34:59.736Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T22:04:01.146Z","emptyReason":null},"description":"Turn rough creative briefs into structured Seedance video prompt packs, reference-aware motion plans, focused variants, and debugging loops. Use for text-to-video, image-to-video, video-to-video, first-last-frame transitions, multi-shot storyboards, product ads, fashion clips, cinematic scenes, dialogue, or creator content; do not use for unrelated models or account support.","descriptionLabel":"Source description","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/10/2026.","installCommand":"clawhub skill install s170hngh0a5eh4edhc6xmvg3vs84gc12:seedance-video-prompt-architect","sourceUrl":"https://clawhub.ai/gpt-img-2/seedance-video-prompt-architect","homepage":"https://clawhub.ai/gpt-img-2/skills/seedance-video-prompt-architect","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/gpt-img-2/seedance-video-prompt-architect","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/gpt-img-2/skills/seedance-video-prompt-architect","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":40,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Seedance Prompt Architect technical dossier on Xpersona with agent coverage, OPENCLEW support, and live trust metadata."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T22:04:01.146Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T22:04:01.146Z","emptyReason":null},"stars":null,"forks":null,"downloads":1247,"packageName":null,"latestVersion":"1.1.0","tractionLabel":"1.2K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T22:04:01.145Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T22:04:01.146Z","lastCrawledAt":"2026-10-10T22:04:01.145Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T22:04:01.146Z","lastVerifiedAt":null,"highlights":[{"version":"1.1.0","createdAt":"2026-08-26T12:27:10.758Z","changelog":"Added optional read-only C Dance Prompt MCP integration, public Seedance 2.0 prompt research, workflow discovery, reference-aware motion planning, audio guidance, and first-last-frame and multi-shot support.","fileCount":3,"zipByteSize":4377},{"version":"1.0.1","createdAt":"2026-04-09T09:36:51.874Z","changelog":"- Added a README.md file for improved project documentation and onboarding. - Updated SKILL.md to include versioning, homepage, and metadata fields for better traceability. - Added canonical links to official documentation, demos, and prompt examples for easier access. - Clarified provenance, safety, and usage restrictions of the skill. - No changes to core prompt design logic or workflow.","fileCount":5,"zipByteSize":4615},{"version":"1.0.0","createdAt":"2026-04-09T09:19:45.583Z","changelog":"Initial release","fileCount":3,"zipByteSize":2333}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s170hngh0a5eh4edhc6xmvg3vs84gc12:seedance-video-prompt-architect","setupComplexity":"low","setupSteps":["Install using `clawhub skill install s170hngh0a5eh4edhc6xmvg3vs84gc12:seedance-video-prompt-architect` in an isolated environment before connecting it to live workloads.","No published capability contract is available yet, so validate auth and request/response behavior manually.","Review the upstream CLAWHUB listing at https://clawhub.ai/gpt-img-2/seedance-video-prompt-architect before using production credentials."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gpt-img-2-seedance-video-prompt-architect/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gpt-img-2-seedance-video-prompt-architect/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gpt-img-2-seedance-video-prompt-architect/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-gpt-img-2-seedance-video-prompt-architect/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-gpt-img-2-seedance-video-prompt-architect/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-gpt-img-2-seedance-video-prompt-architect/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T00:34:59.735Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gpt-img-2-seedance-video-prompt-architect/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gpt-img-2-seedance-video-prompt-architect/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gpt-img-2-seedance-video-prompt-architect/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gpt-img-2-seedance-video-prompt-architect/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T22:04:01.146Z","emptyReason":null},"readme":"Skill: Seedance Prompt Architect\n\nOwner: gpt-img-2\n\nSummary: Turn rough creative briefs into structured Seedance video prompt packs, reference-aware motion plans, focused variants, and debugging loops. Use for text-to-video, image-to-video, video-to-video, first-last-frame transitions, multi-shot storyboards, product ads, fashion clips, cinematic scenes, dialogue, or creator content; do not use for unrelated models or account support.\n\nTags: latest:1.1.0, mcp:1.1.0, openclaw:1.1.0, prompt-engineering:1.1.0, seedance-2:1.1.0, video-generation:1.1.0\n\nVersion history:\n\nv1.1.0 | 2026-08-26T12:27:10.758Z | user\n\nAdded optional read-only C Dance Prompt MCP integration, public Seedance 2.0 prompt research, workflow discovery, reference-aware motion planning, audio guidance, and first-last-frame and multi-shot support.\n\nv1.0.1 | 2026-04-09T09:36:51.874Z | user\n\n- Added a README.md file for improved project documentation and onboarding.\n- Updated SKILL.md to include versioning, homepage, and metadata fields for better traceability.\n- Added canonical links to official documentation, demos, and prompt examples for easier access.\n- Clarified provenance, safety, and usage restrictions of the skill.\n- No changes to core prompt design logic or workflow.\n\nv1.0.0 | 2026-04-09T09:19:45.583Z | user\n\nInitial release\n\nArchive index:\n\nArchive v1.1.0: 3 files, 4377 bytes\n\nFiles: skill-card.md (2245b), SKILL.md (6940b), _meta.json (150b)\n\nFile v1.1.0:SKILL.md\n\n---\nname: seedance-video-prompt-architect\ndescription: Turn rough creative briefs into structured Seedance video prompt packs, reference-aware motion plans, focused variants, and debugging loops. Use for text-to-video, image-to-video, video-to-video, first-last-frame transitions, multi-shot storyboards, product ads, fashion clips, cinematic scenes, dialogue, or creator content; do not use for unrelated models or account support.\nmetadata:\n openclaw:\n homepage: https://cdance.ai/docs/seedance-video-prompt-architect\n version: 1.1.0\n---\n\n# Seedance Video Prompt Architect\n\nThis skill turns loose ideas into cleaner Seedance prompt packs with stronger motion logic, camera control, reference preservation, audio direction, and revision loops.\n\n## Canonical links\n\n- Docs: https://cdance.ai/docs/seedance-video-prompt-architect\n- Demo: https://cdance.ai/seedance-2-0-video-generator\n- Create: https://cdance.ai/create\n- Prompt gallery: https://cdance.ai/prompts/seedance-2-0\n- Raw SKILL.md: https://cdance.ai/skills/seedance-video-prompt-architect/SKILL.md\n- Prompt examples: https://cdance.ai/blog/best-seedance-2-0-prompt-examples\n- Prompt debugging guide: https://cdance.ai/blog/common-seedance-2-0-prompt-mistakes\n- C Dance Prompt MCP: https://github.com/gpt-img-2/cdance-prompt-mcp\n- OpenClaw listing: https://clawhub.ai/gpt-img-2/skills/seedance-video-prompt-architect\n\n## Provenance and safety\n\n- Maintained around the public C Dance AI prompt workflow, prompt gallery, and documentation on `cdance.ai`.\n- The skill works as a text-only prompt workflow without any external tool.\n- The optional C Dance Prompt MCP is read-only, needs no API key, and never generates video or spends credits.\n- Keep the canonical C Dance AI source URL when sharing an example returned by the MCP.\n\n## When to use\n\n- The user has a rough Seedance video idea and wants a stronger prompt\n- The user wants text-to-video, image-to-video, video-to-video, or first-last-frame guidance\n- The user needs a product ad, fashion clip, cinematic scene, dialogue clip, or creator video\n- The user needs stable identity, product geometry, composition, motion, or continuity from references\n- The user wants a multi-shot sequence or storyboard with planned beats\n- The user has unstable output and needs diagnosis plus a cleaner second-pass prompt\n\n## When not to use\n\n- The request is mainly about a different model or non-video workflow\n- The user only wants final video generation, API integration, payment help, or account support\n- The user asks for unsupported model settings, hidden system behavior, or official provider claims\n\n## Workflow\n\n1. Classify the request:\n - text-to-video\n - image-to-video\n - video-to-video\n - first-last-frame transition\n - multi-shot storyboard\n2. Extract or ask for only the missing essentials:\n - subject and intended use\n - action beats and timing\n - camera framing and movement\n - environment, style, and lighting\n - reference constraints and continuity anchors\n - dialogue, ambience, or sound effects\n - duration, aspect ratio, and hard negatives\n3. Keep the first draft focused:\n - one primary subject or continuity anchor\n - one dominant action beat per shot\n - one motivated camera rule\n - one concise constraint block\n4. Return a prompt pack with:\n - a brief diagnosis or workflow choice\n - one primary prompt\n - 2 or 3 focused variants\n - a short avoid list\n - 3 concrete revision moves for the next round\n\n## Optional C Dance Prompt MCP\n\nUse the MCP only when public examples or workflow research would materially improve the answer:\n\n1. Call `search_prompts` with a focused query, language, and small result limit.\n2. Present concise candidates with title, preview, and canonical C Dance AI source URL.\n3. Call `get_prompt` only for the selected slug; do not bulk-fetch the library.\n4. Call `list_workflows` when the user is choosing between text, image, source video, first-last-frame, or multi-shot routes.\n5. Use `build_video_prompt_brief` when the user's idea is rough, then adapt it with the rules below.\n\nInstall the read-only MCP in OpenClaw:\n\n```bash\nopenclaw mcp add cdance \\\n --command npx \\\n --arg -y \\\n --arg github:gpt-img-2/cdance-prompt-mcp \\\n --include 'search_prompts,get_prompt,list_workflows,build_video_prompt_brief'\n\nopenclaw mcp doctor cdance --probe\n```\n\nThe MCP does not provide video generation. For a final video, use a generation capability already available in the user's host or direct the user to the C Dance AI generator; do not claim a video was generated when only a prompt was produced.\n\n## Prompt construction rules\n\n- Prefer concrete subjects, actions, timing, and camera language over broad adjectives.\n- Use beat-based structure when motion matters, and keep one dominant action per beat.\n- State what must remain unchanged before describing reference-driven motion or transformation.\n- Preserve product geometry, labels, identity, spatial relationships, and lighting continuity when they matter.\n- For dialogue, quote exact lines and separate speech, ambience, and sound effects.\n- For first-last-frame work, describe a physically plausible motion path between both endpoints.\n- For multi-shot work, assign one purpose, framing rule, and continuity anchor to each shot.\n- Avoid stacking many subjects, actions, lenses, camera moves, and style changes into one short clip.\n- Do not invent unsupported model settings.\n\n## Output formats\n\n### Text-to-video\n\n```md\nGoal:\nSubject and action:\nBeat timing:\nCamera:\nEnvironment:\nStyle and lighting:\nAudio:\nConstraints:\nPrompt:\n```\n\n### Image-to-video\n\n```md\nReference anchor:\nWhat must stay stable:\nAllowed motion:\nCamera move:\nStyle and lighting:\nAudio:\nConstraints:\nPrompt:\n```\n\n### Video-to-video\n\n```md\nSource footage value:\nWhat to preserve:\nWhat to transform:\nStyle direction:\nAudio handling:\nConstraints:\nPrompt:\n```\n\n### First-last-frame or multi-shot\n\n```md\nSequence goal:\nStart state or shot:\nEnd state or next shot:\nMotion path and continuity anchor:\nCamera and timing:\nAudio:\nConstraints:\nPrompt:\n```\n\n## Debugging heuristics\n\n- If the clip feels chaotic, reduce subject count, action beats, and camera changes.\n- If identity or product geometry drifts, simplify motion and strengthen preservation rules.\n- If motion feels static, add one physically specific action verb and one motivated camera cue.\n- If a transition jumps, define intermediate motion and keep lighting, direction, and scale coherent.\n- If dialogue fails, shorten exact lines and separate speech from other audio cues.\n- If the result is attractive but off-brief, rewrite around the intended use and primary beat first.\n\n## Response style\n\n- Be structured and concise.\n- Prefer prompt packs over long theory.\n- Offer variants that test one axis at a time: action, camera, pace, lighting, audio, or constraints.\n- When external examples are useful, point to the canonical C Dance AI pages listed above.\n\nFile v1.1.0:_meta.json\n\n{\n \"ownerId\": \"kn7b3brv49z9vayew7kt8a5s8s84ghz7\",\n \"slug\": \"seedance-video-prompt-architect\",\n \"version\": \"1.1.0\",\n \"publishedAt\": 1787747230758\n}\n\nFile v1.1.0:skill-card.md\n\n## Description:\n\nTurn rough creative briefs into structured Seedance video prompt packs, reference-aware motion plans, focused variants, and debugging loops.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[gpt-img-2](https://clawhub.ai/user/gpt-img-2)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal creators, developers, and marketing teams use this skill to turn Seedance video ideas into structured prompt packs for text-to-video, image-to-video, video-to-video, first-last-frame transitions, and multi-shot storyboards.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The optional setup asks users to run an unpinned GitHub MCP package through npx, which expands local execution risk beyond the text-only skill.\n\nMitigation: Before enabling the MCP, review the GitHub repository, prefer a pinned commit or verified release, and run it only in a restricted environment without sensitive files, credentials, or broad network access.\n\n## Reference(s):\n\n- [C Dance AI Seedance Prompt Architect Docs](https://cdance.ai/docs/seedance-video-prompt-architect)\n- [Seedance 2.0 Prompt Gallery](https://cdance.ai/prompts/seedance-2-0)\n- [Seedance 2.0 Prompt Examples](https://cdance.ai/blog/best-seedance-2-0-prompt-examples)\n- [Seedance 2.0 Prompt Debugging Guide](https://cdance.ai/blog/common-seedance-2-0-prompt-mistakes)\n- [C Dance Prompt MCP](https://github.com/gpt-img-2/cdance-prompt-mcp)\n- [ClawHub Skill Listing](https://clawhub.ai/gpt-img-2/skills/seedance-video-prompt-architect)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, guidance]\n\n**Output Format:** [Markdown prompt packs with optional shell command snippets]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Text-only by default; optional read-only MCP usage can provide public examples and workflow research.]\n\n## Skill Version(s):\n\n1.1.0 (source: evidence release version and OpenClaw metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.0.1: 5 files, 4615 bytes\n\nFiles: agents/openai.yaml (313b), README.md (1195b), skill-card.md (2652b), SKILL.md (4719b), _meta.json (150b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: seedance-video-prompt-architect\ndescription: Turn rough creative briefs into structured Seedance 2.0 video prompt packs, tighter variants, and debugging plans. Use when the user wants better text-to-video, image-to-video, or video-to-video prompts for ads, fashion clips, cinematic scenes, or creator content.\nversion: 1.0.0\nhomepage: https://cdance.ai/docs/seedance-video-prompt-architect\nmetadata:\n openclaw:\n homepage: https://cdance.ai/docs/seedance-video-prompt-architect\n---\n\n# Seedance Video Prompt Architect\n\nThis skill turns loose ideas into cleaner Seedance 2.0 prompt packs with stronger motion logic, camera control, and revision loops.\n\n## Canonical links\n\n- Docs: https://cdance.ai/docs/seedance-video-prompt-architect\n- Demo: https://cdance.ai/seedance-2-0-video-generator\n- Raw SKILL.md: https://cdance.ai/skills/seedance-video-prompt-architect/SKILL.md\n- Prompt examples: https://cdance.ai/blog/best-seedance-2-0-prompt-examples\n- Prompt debugging guide: https://cdance.ai/blog/common-seedance-2-0-prompt-mistakes\n\n## Provenance and safety\n\n- Maintained around the public C Dance AI prompt workflow and documentation on `cdance.ai`.\n- This is a text-only skill pack with no helper scripts, no local binaries, and no environment variables.\n- It does not autonomously call external services or write files. It only guides prompt design and may reference public documentation URLs listed above.\n\n## When to use\n\n- The user has a rough Seedance 2.0 video idea and wants a better prompt\n- The user wants text-to-video, image-to-video, or video-to-video prompt rewrites\n- The user needs 2 to 3 focused prompt variants for fast testing\n- The user has unstable outputs and needs a diagnosis plus a cleaner second-pass prompt\n\n## When not to use\n\n- The request is mainly about a different model or toolchain\n- The user needs a full storyboard, treatment, or production script instead of a short AI video prompt package\n- The user only wants a one-line idea without any optimization\n\n## Workflow\n\n1. Classify the request as text-to-video, image-to-video, or video-to-video.\n2. Extract or ask for only the missing essentials:\n - subject\n - action\n - camera behavior\n - environment\n - style and lighting\n - duration and aspect ratio\n - hard constraints\n3. Keep the first draft simple:\n - one primary subject\n - one dominant action beat\n - one camera rule\n - one short constraint block\n4. Return a prompt pack with:\n - a brief diagnosis\n - one primary prompt\n - 2 or 3 tighter variants\n - a focused avoid list\n - 3 concrete revision moves for the next round\n\n## Prompt construction rules\n\n- Prefer concrete visual language over abstract adjectives.\n- Use beat-based structure when motion matters.\n- Avoid cramming multiple subjects, conflicting actions, and camera changes into one short clip.\n- If identity or composition must stay stable, recommend image-to-video instead of pure text-to-video.\n- If motion timing already exists in source footage, recommend video-to-video and preserve timing before style changes.\n- Keep the constraint block focused on likely failure modes such as flicker, warped hands, unstable faces, drifting composition, or chaotic camera movement.\n- Do not invent unsupported model settings.\n\n## Output formats\n\n### Text-to-video\n\nUse this structure:\n\n```md\nGoal:\nSubject:\nAction:\nCamera:\nEnvironment:\nStyle and lighting:\nConstraints:\nSuggested settings: duration=?, aspect_ratio=?\nPrompt:\n```\n\n### Image-to-video\n\nUse this structure:\n\n```md\nReference anchor:\nWhat must stay stable:\nAllowed motion:\nCamera move:\nStyle and lighting:\nConstraints:\nPrompt:\n```\n\n### Video-to-video\n\nUse this structure:\n\n```md\nSource footage value:\nWhat to preserve:\nWhat to transform:\nStyle direction:\nConstraints:\nPrompt:\n```\n\n## Debugging heuristics\n\n- If the clip feels chaotic, reduce subject count and camera changes.\n- If the subject breaks apart, shorten the action and strengthen stability constraints.\n- If the result is beautiful but not useful, rewrite around one clear commercial or storytelling beat.\n- If the first pass is flat, add one specific framing cue and one stronger motion verb.\n- If the user wants multiple directions, vary only one axis at a time: subject, camera, lighting, or pace.\n\n## Response style\n\n- Be decisive, structured, and brief.\n- Prefer prompt packs over long theory.\n- Suggest testing the clean base prompt before trying variants.\n- When external examples are useful, point the user to these canonical C Dance AI pages:\n - https://cdance.ai/create\n - https://cdance.ai/seedance-2-0-video-generator\n - https://cdance.ai/blog/best-seedance-2-0-prompt-examples\n - https://cdance.ai/blog/common-seedance-2-0-prompt-mistakes\n\nFile v1.0.1:README.md\n\n# Seedance Video Prompt Architect\n\n`seedance-video-prompt-architect` is a public prompt-design skill for turning rough video ideas into tighter Seedance 2.0 prompt packs, variants, and debugging loops.\n\n## Links\n\n- Docs: https://cdance.ai/docs/seedance-video-prompt-architect\n- Demo: https://cdance.ai/seedance-2-0-video-generator\n- Raw SKILL.md: https://cdance.ai/skills/seedance-video-prompt-architect/SKILL.md\n- Prompt examples: https://cdance.ai/blog/best-seedance-2-0-prompt-examples\n- Prompt debugging guide: https://cdance.ai/blog/common-seedance-2-0-prompt-mistakes\n\n## What it does\n\n- Converts rough creative briefs into structured Seedance 2.0 prompts\n- Chooses between text-to-video, image-to-video, and video-to-video\n- Produces a clean base prompt plus tighter variants\n- Adds a short debugging and revision loop for unstable outputs\n\n## Safety profile\n\n- Text-only skill pack\n- No scripts\n- No binaries\n- No required environment variables\n- No autonomous network calls\n\n## Best fit\n\nUse this skill for product ads, fashion clips, cinematic scenes, anime-style shots, creator content, and other short-form video ideas that need stronger motion structure and cleaner prompt control.\n\nFile v1.0.1:_meta.json\n\n{\n \"ownerId\": \"kn7b3brv49z9vayew7kt8a5s8s84ghz7\",\n \"slug\": \"seedance-video-prompt-architect\",\n \"version\": \"1.0.1\",\n \"publishedAt\": 1775727411874\n}\n\nFile v1.0.1:skill-card.md\n\n## Description:
\nTurn rough creative briefs into structured Seedance 2.0 video prompt packs, tighter variants, and debugging plans.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[aitools101](https://clawhub.ai/user/aitools101)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nExternal creators, marketers, and developers use this skill to turn rough short-form video ideas into structured Seedance 2.0 prompt packs with variants and revision guidance for text-to-video, image-to-video, or video-to-video workflows.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Generated prompt workflows may expose confidential campaign details, personal data, or private footage descriptions if users paste sensitive material into the request.
\nMitigation: Avoid including confidential, personal, or private footage details in prompts; redact sensitive context before using the skill.
\nRisk: Implicit invocation may apply the prompt-design workflow when a user only wanted a general response.
\nMitigation: Disable implicit invocation when the skill should be called only by explicit user request.
\nRisk: Unsupported Seedance settings or over-specified prompts can mislead users or reduce generation quality.
\nMitigation: Keep settings to documented fields and use the skill's revision loop to simplify subject, action, camera, and constraint choices.
\n\n\n## Reference(s):
\n- [ClawHub skill page](https://clawhub.ai/aitools101/seedance-video-prompt-architect)
\n- [C Dance AI documentation](https://cdance.ai/docs/seedance-video-prompt-architect)
\n- [Seedance 2.0 video generator demo](https://cdance.ai/seedance-2-0-video-generator)
\n- [Prompt examples](https://cdance.ai/blog/best-seedance-2-0-prompt-examples)
\n- [Prompt debugging guide](https://cdance.ai/blog/common-seedance-2-0-prompt-mistakes)
\n\n\n## Skill Output:
\n**Output Type(s):** [text, markdown, guidance]
\n**Output Format:** [Markdown prompt pack with structured fields, variants, avoid list, and revision moves]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Text-only output; no code execution, files, credentials, or autonomous network calls.]
\n\n## Skill Version(s):
\n1.0.1 (source: server release metadata)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
\n\nFile v1.0.1:agents/openai.yaml\n\ninterface:\n display_name: \"Seedance Prompt Architect\"\n short_description: \"Turns briefs into structured Seedance video prompts\"\n default_prompt: \"Use $seedance-video-prompt-architect to turn my idea into a Seedance 2.0 prompt pack with variants and a revision plan.\"\n\npolicy:\n allow_implicit_invocation: true\n\nArchive v1.0.0: 3 files, 2333 bytes\n\nFiles: agents/openai.yaml (313b), SKILL.md (3801b), _meta.json (150b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: seedance-video-prompt-architect\ndescription: Turn rough creative briefs into structured Seedance 2.0 video prompt packs, tighter variants, and debugging plans. Use when the user wants better text-to-video, image-to-video, or video-to-video prompts for ads, fashion clips, cinematic scenes, or creator content.\nlicense: MIT\n---\n\n# Seedance Video Prompt Architect\n\nThis skill turns loose ideas into cleaner Seedance 2.0 prompt packs with stronger motion logic, camera control, and revision loops.\n\n## When to use\n\n- The user has a rough Seedance 2.0 video idea and wants a better prompt\n- The user wants text-to-video, image-to-video, or video-to-video prompt rewrites\n- The user needs 2 to 3 focused prompt variants for fast testing\n- The user has unstable outputs and needs a diagnosis plus a cleaner second-pass prompt\n\n## When not to use\n\n- The request is mainly about a different model or toolchain\n- The user needs a full storyboard, treatment, or production script instead of a short AI video prompt package\n- The user only wants a one-line idea without any optimization\n\n## Workflow\n\n1. Classify the request as text-to-video, image-to-video, or video-to-video.\n2. Extract or ask for only the missing essentials:\n - subject\n - action\n - camera behavior\n - environment\n - style and lighting\n - duration and aspect ratio\n - hard constraints\n3. Keep the first draft simple:\n - one primary subject\n - one dominant action beat\n - one camera rule\n - one short constraint block\n4. Return a prompt pack with:\n - a brief diagnosis\n - one primary prompt\n - 2 or 3 tighter variants\n - a focused avoid list\n - 3 concrete revision moves for the next round\n\n## Prompt construction rules\n\n- Prefer concrete visual language over abstract adjectives.\n- Use beat-based structure when motion matters.\n- Avoid cramming multiple subjects, conflicting actions, and camera changes into one short clip.\n- If identity or composition must stay stable, recommend image-to-video instead of pure text-to-video.\n- If motion timing already exists in source footage, recommend video-to-video and preserve timing before style changes.\n- Keep the constraint block focused on likely failure modes such as flicker, warped hands, unstable faces, drifting composition, or chaotic camera movement.\n- Do not invent unsupported model settings.\n\n## Output formats\n\n### Text-to-video\n\nUse this structure:\n\n```md\nGoal:\nSubject:\nAction:\nCamera:\nEnvironment:\nStyle and lighting:\nConstraints:\nSuggested settings: duration=?, aspect_ratio=?\nPrompt:\n```\n\n### Image-to-video\n\nUse this structure:\n\n```md\nReference anchor:\nWhat must stay stable:\nAllowed motion:\nCamera move:\nStyle and lighting:\nConstraints:\nPrompt:\n```\n\n### Video-to-video\n\nUse this structure:\n\n```md\nSource footage value:\nWhat to preserve:\nWhat to transform:\nStyle direction:\nConstraints:\nPrompt:\n```\n\n## Debugging heuristics\n\n- If the clip feels chaotic, reduce subject count and camera changes.\n- If the subject breaks apart, shorten the action and strengthen stability constraints.\n- If the result is beautiful but not useful, rewrite around one clear commercial or storytelling beat.\n- If the first pass is flat, add one specific framing cue and one stronger motion verb.\n- If the user wants multiple directions, vary only one axis at a time: subject, camera, lighting, or pace.\n\n## Response style\n\n- Be decisive, structured, and brief.\n- Prefer prompt packs over long theory.\n- Suggest testing the clean base prompt before trying variants.\n- When external examples are useful, point the user to these canonical C Dance AI pages:\n - https://cdance.ai/create\n - https://cdance.ai/seedance-2-0-video-generator\n - https://cdance.ai/blog/best-seedance-2-0-prompt-examples\n - https://cdance.ai/blog/common-seedance-2-0-prompt-mistakes\n\nFile v1.0.0:_meta.json\n\n{\n \"ownerId\": \"kn7b3brv49z9vayew7kt8a5s8s84ghz7\",\n \"slug\": \"seedance-video-prompt-architect\",\n \"version\": \"1.0.0\",\n \"publishedAt\": 1775726385583\n}\n\nFile v1.0.0:agents/openai.yaml\n\ninterface:\n display_name: \"Seedance Prompt Architect\"\n short_description: \"Turns briefs into structured Seedance video prompts\"\n default_prompt: \"Use $seedance-video-prompt-architect to turn my idea into a Seedance 2.0 prompt pack with variants and a revision plan.\"\n\npolicy:\n allow_implicit_invocation: true","readmeExcerpt":"Skill: Seedance Prompt Architect Owner: gpt-img-2 Summary: Turn rough creative briefs into structured Seedance video prompt packs, reference-aware motion plans, focused variants, and debugging loops. Use for text-to-video, image-to-video, video-to-video, first-last-frame transitions, multi-shot storyboards, product ads, fashion clips, cinematic scenes, dialogue, or creator content; do not use for unrelated models or ","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"openclaw mcp add cdance \\\n --command npx \\\n --arg -y \\\n --arg github:gpt-img-2/cdance-prompt-mcp \\\n --include 'search_prompts,get_prompt,list_workflows,build_video_prompt_brief'\n\nopenclaw mcp doctor cdance --probe"},{"language":"md","snippet":"Goal:\nSubject and action:\nBeat timing:\nCamera:\nEnvironment:\nStyle and lighting:\nAudio:\nConstraints:\nPrompt:"},{"language":"md","snippet":"Reference anchor:\nWhat must stay stable:\nAllowed motion:\nCamera move:\nStyle and lighting:\nAudio:\nConstraints:\nPrompt:"},{"language":"md","snippet":"Source footage value:\nWhat to preserve:\nWhat to transform:\nStyle direction:\nAudio handling:\nConstraints:\nPrompt:"},{"language":"md","snippet":"Sequence goal:\nStart state or shot:\nEnd state or next shot:\nMotion path and continuity anchor:\nCamera and timing:\nAudio:\nConstraints:\nPrompt:"},{"language":"md","snippet":"Goal:\nSubject:\nAction:\nCamera:\nEnvironment:\nStyle and lighting:\nConstraints:\nSuggested settings: duration=?, aspect_ratio=?\nPrompt:"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: seedance-video-prompt-architect\ndescription: Turn rough creative briefs into structured Seedance video prompt packs, reference-aware motion plans, focused variants, and debugging loops. Use for text-to-video, image-to-video, video-to-video, first-last-frame transitions, multi-shot storyboards, product ads, fashion clips, cinematic scenes, dialogue, or creator content; do not use for unrelated models or account support.\nmetadata:\n openclaw:\n homepage: https://cdance.ai/docs/seedance-video-prompt-architect\n version: 1.1.0\n---\n\n# Seedance Video Prompt Architect\n\nThis skill turns loose ideas into cleaner Seedance prompt packs with stronger motion logic, camera control, reference preservation, audio direction, and revision loops.\n\n## Canonical links\n\n- Docs: https://cdance.ai/docs/seedance-video-prompt-architect\n- Demo: https://cdance.ai/seedance-2-0-video-generator\n- Create: https://cdance.ai/create\n- Prompt gallery: https://cdance.ai/prompts/seedance-2-0\n- Raw SKILL.md: https://cdance.ai/skills/seedance-video-prompt-architect/SKILL.md\n- Prompt examples: https://cdance.ai/blog/best-seedance-2-0-prompt-examples\n- Prompt debugging guide: https://cdance.ai/blog/common-seedance-2-0-prompt-mistakes\n- C Dance Prompt MCP: https://github.com/gpt-img-2/cdance-prompt-mcp\n- OpenClaw listing: https://clawhub.ai/gpt-img-2/skills/seedance-video-prompt-architect\n\n## Provenance and safety\n\n- Maintained around the public C Dance AI prompt workflow, prompt gallery, and documentation on `cdance.ai`.\n- The skill works as a text-only prompt workflow without any external tool.\n- The optional C Dance Prompt MCP is read-only, needs no API key, and never generates video or spends credits.\n- Keep the canonical C Dance AI source URL when sharing an example returned by the MCP.\n\n## When to use\n\n- The user has a rough Seedance video idea and wants a stronger prompt\n- The user wants text-to-video, image-to-video, video-to-video, or first-last-frame guidance\n- The user needs a product ad, fashion clip, cinematic scene, dialogue clip, or creator video\n- The user needs stable identity, product geometry, composition, motion, or continuity from references\n- The user wants a multi-shot sequence or storyboard with planned beats\n- The user has unstable output and needs diagnosis plus a cleaner second-pass prompt\n\n## When not to use\n\n- The request is mainly about a different model or non-video workflow\n- The user only wants final video generation, API integration, payment help, or account support\n- The user asks for unsupported model settings, hidden system behavior, or official provider claims\n\n## Workflow\n\n1. Classify the request:\n - text-to-video\n - image-to-video\n - video-to-video\n - first-last-frame transition\n - multi-shot storyboard\n2. Extract or ask for only the missing essentials:\n - subject and intended use\n - action beats and timing\n - camera framing and movement\n - environment, style, and lighting\n - reference constraints and continuity anc"},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn7b3brv49z9vayew7kt8a5s8s84ghz7\",\n \"slug\": \"seedance-video-prompt-architect\",\n \"version\": \"1.1.0\",\n \"publishedAt\": 1787747230758\n}"},{"path":"skill-card.md","content":"## Description:\n\nTurn rough creative briefs into structured Seedance video prompt packs, reference-aware motion plans, focused variants, and debugging loops.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[gpt-img-2](https://clawhub.ai/user/gpt-img-2)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal creators, developers, and marketing teams use this skill to turn Seedance video ideas into structured prompt packs for text-to-video, image-to-video, video-to-video, first-last-frame transitions, and multi-shot storyboards.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The optional setup asks users to run an unpinned GitHub MCP package through npx, which expands local execution risk beyond the text-only skill.\n\nMitigation: Before enabling the MCP, review the GitHub repository, prefer a pinned commit or verified release, and run it only in a restricted environment without sensitive files, credentials, or broad network access.\n\n## Reference(s):\n\n- [C Dance AI Seedance Prompt Architect Docs](https://cdance.ai/docs/seedance-video-prompt-architect)\n- [Seedance 2.0 Prompt Gallery](https://cdance.ai/prompts/seedance-2-0)\n- [Seedance 2.0 Prompt Examples](https://cdance.ai/blog/best-seedance-2-0-prompt-examples)\n- [Seedance 2.0 Prompt Debugging Guide](https://cdance.ai/blog/common-seedance-2-0-prompt-mistakes)\n- [C Dance Prompt MCP](https://github.com/gpt-img-2/cdance-prompt-mcp)\n- [ClawHub Skill Listing](https://clawhub.ai/gpt-img-2/skills/seedance-video-prompt-architect)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, guidance]\n\n**Output Format:** [Markdown prompt packs with optional shell command snippets]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Text-only by default; optional read-only MCP usage can provide public examples and workflow research.]\n\n## Skill Version(s):\n\n1.1.0 (source: evidence release version and OpenClaw metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":null,"editorialQuality":{"score":100,"threshold":65,"status":"thin","wordCount":1201,"uniquenessScore":44,"reasons":["uniqueness-below-45"]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T22:04:01.146Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-10T22:04:01.146Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-11T00:34:59.736Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}