{"id":"5aeb8aff-fa15-4b17-8d08-341ccd1a38a1","entityType":"agent","slug":"clawhub-yummysource-yummy-gen-video","name":"Yummy Gen Video","canonicalUrl":"https://www.xpersona.co/agent/clawhub-yummysource-yummy-gen-video","canonicalPath":"/agent/clawhub-yummysource-yummy-gen-video","generatedAt":"2026-10-11T14:15:14.491Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T10:26:25.193Z","emptyReason":null},"description":"Use when the user wants to generate a video with Gemini Veo through yummycli, including text-to-video, image-to-video (single starting frame), and reference-... Skill: Yummy Gen Video Owner: yummysource Summary: Use when the user wants to generate a video with Gemini Veo through yummycli, including text-to-video, image-to-video (single starting frame), and reference-... Tags: latest:1.1.0 Version history: v1.1.0 | 2026-04-17T07:54:11.701Z | auto - Initial public release of yummy-gen-video for Gemini Veo video generation via yummycli. - Supports text-to-video, image-to-video","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s171xbx4pasz0j8j5j3nct0cs984p697:yummy-gen-video","sourceUrl":"https://clawhub.ai/yummysource/yummy-gen-video","homepage":"https://clawhub.ai/yummysource/skills/yummy-gen-video","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/yummysource/yummy-gen-video","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/yummysource/skills/yummy-gen-video","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":61,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Use when the user wants to generate a video with Gemini Veo through yummycli, including text-to-video, image-to-video (single starting frame), and reference-..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T10:26:25.193Z","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":"2026-10-11T10:26:25.193Z","emptyReason":null},"stars":null,"forks":null,"downloads":1088,"packageName":null,"latestVersion":"1.1.0","tractionLabel":"1.1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T10:26:25.181Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T10:26:25.193Z","lastCrawledAt":"2026-10-11T10:26:25.181Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T10:26:25.181Z","lastVerifiedAt":null,"highlights":[{"version":"1.1.0","createdAt":"2026-04-17T07:54:11.701Z","changelog":"- Initial public release of yummy-gen-video for Gemini Veo video generation via yummycli. - Supports text-to-video, image-to-video (starting frame), and reference-image-guided generation (up to 3 images). - Intelligent CLI flag mapping for model, duration, resolution, aspect ratio, and output path based on user intent. - Built-in validation of model, duration, and resolution compatibility with clear error handling guidance. - Supports both human-friendly and provider-agnostic CLI entry points. - Includes detailed usage, parameter mapping, model selection, and execution rules.","fileCount":3,"zipByteSize":4415}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s171xbx4pasz0j8j5j3nct0cs984p697:yummy-gen-video","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"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-yummysource-yummy-gen-video/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-yummysource-yummy-gen-video/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-yummysource-yummy-gen-video/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-yummysource-yummy-gen-video/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-yummysource-yummy-gen-video/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-yummysource-yummy-gen-video/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T14:15:14.491Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-yummysource-yummy-gen-video/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-yummysource-yummy-gen-video/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-yummysource-yummy-gen-video/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-yummysource-yummy-gen-video/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":"high","updatedAt":"2026-10-11T10:26:25.193Z","emptyReason":null},"readme":"Skill: Yummy Gen Video\n\nOwner: yummysource\n\nSummary: Use when the user wants to generate a video with Gemini Veo through yummycli, including text-to-video, image-to-video (single starting frame), and reference-...\n\nTags: latest:1.1.0\n\nVersion history:\n\nv1.1.0 | 2026-04-17T07:54:11.701Z | auto\n\n- Initial public release of yummy-gen-video for Gemini Veo video generation via yummycli.\n- Supports text-to-video, image-to-video (starting frame), and reference-image-guided generation (up to 3 images).\n- Intelligent CLI flag mapping for model, duration, resolution, aspect ratio, and output path based on user intent.\n- Built-in validation of model, duration, and resolution compatibility with clear error handling guidance.\n- Supports both human-friendly and provider-agnostic CLI entry points.\n- Includes detailed usage, parameter mapping, model selection, and execution rules.\n\nArchive index:\n\nArchive v1.1.0: 3 files, 4415 bytes\n\nFiles: skill-card.md (2055b), SKILL.md (7461b), _meta.json (134b)\n\nFile v1.1.0:SKILL.md\n\n---\nname: yummy-gen-video\nversion: 1.0.0\ndescription: \"Use when the user wants to generate a video with Gemini Veo through yummycli, including text-to-video, image-to-video (single starting frame), and reference-image-guided generation (up to 3 images).\"\nmetadata:\n  requires:\n    bins: [\"yummycli\"]\n    skills: [\"yummy-shared\"]\n  openclaw:\n    requires:\n      bins: [\"yummycli\"]\n    primaryEnv: GEMINI_API_KEY\n    related_skills: [\"yummy-shared\"]\n  hermes:\n    tags: [video, gemini, veo, generation, image-to-video, multimodal]\n    related_skills: [\"yummy-shared\"]\n    requires_toolsets: [\"yummycli\"]\ninstall:\n  - kind: node\n    package: \"@yummysource/yummycli\"\n    bins: [\"yummycli\"]\n---\n\n# Generate Video\n\nCreate videos with `yummycli gemini veo` using Google Veo.\n\n## When to Use\n\nLoad this skill when the user asks to generate, create, or animate a video using AI — including text-to-video, animating a still image, or generating a video guided by reference images.\n\n> **Prerequisite:** Apply the `yummy-shared` skill first.\n\nThis skill covers three generation modes with a single command:\n\n- Text-to-video (no images)\n- Image-to-video (one starting frame)\n- Reference-guided video (two or three reference images)\n\n## Command Contract\n\nTwo equivalent entry points are available:\n\n| Entry point | When to use |\n|-------------|-------------|\n| `yummycli gemini veo` | Default — human-friendly, Gemini Veo presets applied |\n| `yummycli video generate --provider gemini` | Scripting / automation — explicit, provider-agnostic form |\n\nBoth share the same flags and defaults. Prefer `gemini veo` unless the task explicitly requires the provider-agnostic form.\n\nBasic usage:\n\n```bash\nyummycli gemini veo --prompt \"<prompt>\"\n```\n\nWith one or more input images:\n\n```bash\nyummycli gemini veo \\\n  --prompt \"<prompt>\" \\\n  --input-image ./frame.png \\\n  --input-image ./style.jpg\n```\n\nOptional output controls:\n\n```bash\n--output <file.mp4>\n--model <model>\n--aspect-ratio <ratio>\n--duration <seconds>\n--resolution <resolution>\n```\n\nDefault values when omitted: `--model veo-3.1-fast-generate-preview`, `--aspect-ratio 16:9`, `--duration 8`, `--resolution 1080p`.\n\n## Image Routing Rules\n\nThe number of `--input-image` flags determines the API path automatically:\n\n| Count | Behaviour |\n|-------|-----------|\n| 0 | Text-to-video. Prompt drives the entire generation. |\n| 1 | Image-to-video. The image is used as the starting frame. |\n| 2–3 | Reference-guided. Images are passed as ASSET reference images; the prompt describes the motion and content. |\n\nNever pass more than 3 `--input-image` flags — the API rejects it.\n\n## Model Selection\n\nDefault model: `veo-3.1-fast-generate-preview`.\n\nUse the following mapping when the user explicitly names a model variant:\n\n| User says | Use |\n|-----------|-----|\n| `veo 3.1`, `3.1 fast`, or no preference | `veo-3.1-fast-generate-preview` (default) |\n| `veo 3.1 full` or `veo 3.1 standard` | `veo-3.1-generate-preview` |\n| `veo 3`, `veo 3 fast` | `veo-3.0-fast-generate-001` |\n| `veo 3 standard` | `veo-3.0-generate-001` |\n| `veo 2` | `veo-2.0-generate-001` |\n\nDo not switch models from vague quality words alone. Only apply a mapping when the user's wording clearly refers to model choice.\n\n## Model Compatibility\n\n### Supported duration values (seconds)\n\nDuration accepts only discrete values — not a range.\n\n| Model | Valid durations |\n|-------|----------------|\n| `veo-2.0-generate-001` | 5, 6, 7, 8 |\n| `veo-3.0-*` | 4, 6, 8 |\n| `veo-3.1-*` | 4, 6, 8 |\n\n### Supported resolutions\n\n| Model | Supported resolutions |\n|-------|-----------------------|\n| `veo-2.0-generate-001` | `720p` only |\n| `veo-3.0-*` | `720p`, `1080p` |\n| `veo-3.1-*` | `720p`, `1080p`, `4k` |\n\nConstraints:\n- `1080p` requires `--duration 8`.\n- `4k` requires `--duration 8` and a veo-3.1 model.\n\n### Supported aspect ratios\n\nAll models: `16:9` (landscape) and `9:16` (portrait).\n\n## Intent to Parameters\n\nTranslate clear user intent into CLI flags when the mapping is obvious.\n\n**Aspect ratio guidance:**\n- Use `--aspect-ratio 9:16` for vertical/portrait outputs: phone wallpaper, short-form vertical video, story format.\n- Use `--aspect-ratio 16:9` for landscape outputs: film, presentation, widescreen. This is the default.\n- If the user already specifies a ratio, pass it through directly.\n\n**Duration guidance:**\n- Use the longest valid duration for the model unless the user requests shorter.\n- If the user says \"short clip\" or \"quick\", use `--duration 4` (veo-3+) or `--duration 5` (veo-2).\n- Never pass a duration that is not in the valid set for the selected model.\n\n**Resolution guidance:**\n- Default (`1080p`) is appropriate for most requests.\n- Use `--resolution 4k` only when the user explicitly asks for 4K quality and a veo-3.1 model is in use; pair with `--duration 8`.\n- Use `--resolution 720p` when the user asks for a smaller or faster result.\n\n**Output path guidance:**\n- If `--output` is omitted, `yummycli` generates a timestamped `.mp4` filename in the current working directory. Do not invent your own filename unless the user provides one.\n- The output path must end in `.mp4`. Reject or correct any other extension.\n\n## Output Contract\n\nVideo commands return JSON on stdout. Read the response and use the `output` field as the generated file path.\n\nExample (text-to-video):\n\n```json\n{\n  \"provider\": \"gemini\",\n  \"output\": \"veo_20260417_142301_047.mp4\",\n  \"model\": \"veo-3.1-fast-generate-preview\",\n  \"duration_seconds\": 8,\n  \"aspect_ratio\": \"16:9\",\n  \"resolution\": \"1080p\",\n  \"elapsed_seconds\": 73\n}\n```\n\nExample (image-to-video, one starting frame):\n\n```json\n{\n  \"provider\": \"gemini\",\n  \"output\": \"veo_20260417_143010_112.mp4\",\n  \"model\": \"veo-3.1-fast-generate-preview\",\n  \"duration_seconds\": 8,\n  \"aspect_ratio\": \"16:9\",\n  \"resolution\": \"1080p\",\n  \"elapsed_seconds\": 89,\n  \"input_images\": [\"./dog.jpg\"]\n}\n```\n\n## Execution Rules\n\n- Check `yummycli auth status --provider gemini` before running if credentials may not be configured.\n- Use one `--input-image` flag per local image file; preserve the user-specified order.\n- Validate duration and resolution against the selected model's constraints before running.\n- Video generation is slow (typically 45–120 seconds). Inform the user that generation is in progress; do not treat a long wait as an error.\n- If the command returns a validation error (bad duration, unsupported resolution, missing file), fix the arguments before retrying. Do not retry with the same invalid arguments.\n- Report the final `output` path back to the user after a successful run.\n\n## Examples\n\nText-to-video:\n\n```bash\nyummycli gemini veo \\\n  --prompt \"A golden retriever puppy chasing a red ball in a sunny park\"\n```\n\nImage-to-video (animate a still):\n\n```bash\nyummycli gemini veo \\\n  --prompt \"The dog starts running toward the camera\" \\\n  --input-image ./dog.jpg\n```\n\nReference-guided (two images):\n\n```bash\nyummycli gemini veo \\\n  --prompt \"Combine the character from the first image with the environment from the second\" \\\n  --input-image ./character.png \\\n  --input-image ./background.jpg\n```\n\nShort portrait clip with veo-2:\n\n```bash\nyummycli gemini veo \\\n  --prompt \"Falling cherry blossoms in slow motion\" \\\n  --model veo-2.0-generate-001 \\\n  --aspect-ratio 9:16 \\\n  --duration 5 \\\n  --resolution 720p\n```\n\n4K landscape with veo-3.1:\n\n```bash\nyummycli gemini veo \\\n  --prompt \"Timelapse of clouds moving over mountain peaks at golden hour\" \\\n  --resolution 4k \\\n  --duration 8\n```\n\nFile v1.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn76424txcas1znj1nnqz34bah84pb53\",\n  \"slug\": \"yummy-gen-video\",\n  \"version\": \"1.1.0\",\n  \"publishedAt\": 1776412451701\n}\n\nFile v1.1.0:skill-card.md\n\n## Description:\n\nUse when the user wants to generate a video with Gemini Veo through yummycli, including text-to-video, image-to-video (single starting frame), and reference-image-guided generation (up to 3 images).\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[yummysource](https://clawhub.ai/user/yummysource)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and external users use this skill to translate text-to-video, image-to-video, and reference-guided video requests into validated Gemini Veo commands through yummycli.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill relies on an unpinned third-party executable CLI.\n\nMitigation: Install only a trusted, pinned, and reviewed version of @yummysource/yummycli.\n\nRisk: Shell-style command templates can be unsafe if prompts or file paths are assembled into command strings.\n\nMitigation: Pass prompts and file paths as literal CLI arguments and expose only the required GEMINI_API_KEY.\n\nRisk: Generated video commands can fail when model, duration, resolution, image count, or output path constraints are invalid.\n\nMitigation: Validate model compatibility, duration, resolution, image count, and .mp4 output paths before execution.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/yummysource/skills/yummy-gen-video)\n\n## Skill Output:\n\n**Output Type(s):** [shell commands, configuration, guidance]\n\n**Output Format:** [Markdown with inline bash commands and JSON response handling guidance]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Commands require yummycli, GEMINI_API_KEY, and the related yummy-shared skill.]\n\n## Skill Version(s):\n\n1.1.0 (source: server release metadata; artifact frontmatter says 1.0.0)\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.","readmeExcerpt":"Skill: Yummy Gen Video Owner: yummysource Summary: Use when the user wants to generate a video with Gemini Veo through yummycli, including text-to-video, image-to-video (single starting frame), and reference-... Tags: latest:1.1.0 Version history: v1.1.0 | 2026-04-17T07:54:11.701Z | auto - Initial public release of yummy-gen-video for Gemini Veo video generation via yummycli. - Supports text-to-video, image-to-video ","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"yummycli gemini veo --prompt \"<prompt>\""},{"language":"bash","snippet":"yummycli gemini veo \\\n  --prompt \"<prompt>\" \\\n  --input-image ./frame.png \\\n  --input-image ./style.jpg"},{"language":"bash","snippet":"--output <file.mp4>\n--model <model>\n--aspect-ratio <ratio>\n--duration <seconds>\n--resolution <resolution>"},{"language":"json","snippet":"{\n  \"provider\": \"gemini\",\n  \"output\": \"veo_20260417_142301_047.mp4\",\n  \"model\": \"veo-3.1-fast-generate-preview\",\n  \"duration_seconds\": 8,\n  \"aspect_ratio\": \"16:9\",\n  \"resolution\": \"1080p\",\n  \"elapsed_seconds\": 73\n}"},{"language":"json","snippet":"{\n  \"provider\": \"gemini\",\n  \"output\": \"veo_20260417_143010_112.mp4\",\n  \"model\": \"veo-3.1-fast-generate-preview\",\n  \"duration_seconds\": 8,\n  \"aspect_ratio\": \"16:9\",\n  \"resolution\": \"1080p\",\n  \"elapsed_seconds\": 89,\n  \"input_images\": [\"./dog.jpg\"]\n}"},{"language":"bash","snippet":"yummycli gemini veo \\\n  --prompt \"A golden retriever puppy chasing a red ball in a sunny park\""}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: yummy-gen-video\nversion: 1.0.0\ndescription: \"Use when the user wants to generate a video with Gemini Veo through yummycli, including text-to-video, image-to-video (single starting frame), and reference-image-guided generation (up to 3 images).\"\nmetadata:\n  requires:\n    bins: [\"yummycli\"]\n    skills: [\"yummy-shared\"]\n  openclaw:\n    requires:\n      bins: [\"yummycli\"]\n    primaryEnv: GEMINI_API_KEY\n    related_skills: [\"yummy-shared\"]\n  hermes:\n    tags: [video, gemini, veo, generation, image-to-video, multimodal]\n    related_skills: [\"yummy-shared\"]\n    requires_toolsets: [\"yummycli\"]\ninstall:\n  - kind: node\n    package: \"@yummysource/yummycli\"\n    bins: [\"yummycli\"]\n---\n\n# Generate Video\n\nCreate videos with `yummycli gemini veo` using Google Veo.\n\n## When to Use\n\nLoad this skill when the user asks to generate, create, or animate a video using AI — including text-to-video, animating a still image, or generating a video guided by reference images.\n\n> **Prerequisite:** Apply the `yummy-shared` skill first.\n\nThis skill covers three generation modes with a single command:\n\n- Text-to-video (no images)\n- Image-to-video (one starting frame)\n- Reference-guided video (two or three reference images)\n\n## Command Contract\n\nTwo equivalent entry points are available:\n\n| Entry point | When to use |\n|-------------|-------------|\n| `yummycli gemini veo` | Default — human-friendly, Gemini Veo presets applied |\n| `yummycli video generate --provider gemini` | Scripting / automation — explicit, provider-agnostic form |\n\nBoth share the same flags and defaults. Prefer `gemini veo` unless the task explicitly requires the provider-agnostic form.\n\nBasic usage:\n\n```bash\nyummycli gemini veo --prompt \"<prompt>\"\n```\n\nWith one or more input images:\n\n```bash\nyummycli gemini veo \\\n  --prompt \"<prompt>\" \\\n  --input-image ./frame.png \\\n  --input-image ./style.jpg\n```\n\nOptional output controls:\n\n```bash\n--output <file.mp4>\n--model <model>\n--aspect-ratio <ratio>\n--duration <seconds>\n--resolution <resolution>\n```\n\nDefault values when omitted: `--model veo-3.1-fast-generate-preview`, `--aspect-ratio 16:9`, `--duration 8`, `--resolution 1080p`.\n\n## Image Routing Rules\n\nThe number of `--input-image` flags determines the API path automatically:\n\n| Count | Behaviour |\n|-------|-----------|\n| 0 | Text-to-video. Prompt drives the entire generation. |\n| 1 | Image-to-video. The image is used as the starting frame. |\n| 2–3 | Reference-guided. Images are passed as ASSET reference images; the prompt describes the motion and content. |\n\nNever pass more than 3 `--input-image` flags — the API rejects it.\n\n## Model Selection\n\nDefault model: `veo-3.1-fast-generate-preview`.\n\nUse the following mapping when the user explicitly names a model variant:\n\n| User says | Use |\n|-----------|-----|\n| `veo 3.1`, `3.1 fast`, or no preference | `veo-3.1-fast-generate-preview` (default) |\n| `veo 3.1 full` or `veo 3.1 standard` | `veo-3.1-generate-preview` |\n| `veo 3`, `veo 3 fast` | `veo-3.0-fast-generate"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn76424txcas1znj1nnqz34bah84pb53\",\n  \"slug\": \"yummy-gen-video\",\n  \"version\": \"1.1.0\",\n  \"publishedAt\": 1776412451701\n}"},{"path":"skill-card.md","content":"## Description:\n\nUse when the user wants to generate a video with Gemini Veo through yummycli, including text-to-video, image-to-video (single starting frame), and reference-image-guided generation (up to 3 images).\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[yummysource](https://clawhub.ai/user/yummysource)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and external users use this skill to translate text-to-video, image-to-video, and reference-guided video requests into validated Gemini Veo commands through yummycli.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill relies on an unpinned third-party executable CLI.\n\nMitigation: Install only a trusted, pinned, and reviewed version of @yummysource/yummycli.\n\nRisk: Shell-style command templates can be unsafe if prompts or file paths are assembled into command strings.\n\nMitigation: Pass prompts and file paths as literal CLI arguments and expose only the required GEMINI_API_KEY.\n\nRisk: Generated video commands can fail when model, duration, resolution, image count, or output path constraints are invalid.\n\nMitigation: Validate model compatibility, duration, resolution, image count, and .mp4 output paths before execution.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/yummysource/skills/yummy-gen-video)\n\n## Skill Output:\n\n**Output Type(s):** [shell commands, configuration, guidance]\n\n**Output Format:** [Markdown with inline bash commands and JSON response handling guidance]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Commands require yummycli, GEMINI_API_KEY, and the related yummy-shared skill.]\n\n## Skill Version(s):\n\n1.1.0 (source: server release metadata; artifact frontmatter says 1.0.0)\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":"Use when the user wants to generate a video with Gemini Veo through yummycli, including text-to-video, image-to-video (single starting frame), and reference-... Skill: Yummy Gen Video Owner: yummysource Summary: Use when the user wants to generate a video with Gemini Veo through yummycli, including text-to-video, image-to-video (single starting frame), and reference-... Tags: latest:1.1.0 Version history: v1.1.0 | 2026-04-17T07:54:11.701Z | auto - Initial public release of yummy-gen-video for Gemini Veo video generation via yummycli. - Supports text-to-video, image-to-video","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1105,"uniquenessScore":46,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T10:26:25.193Z","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":"2026-10-11T10:26:25.193Z","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":"2026-10-11T14:15:14.491Z","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"}]}}}