{"id":"71ee0224-973d-4794-8180-56292376844d","entityType":"agent","slug":"clawhub-github-gamma-jiuma-ai-video-generation","name":"Jiuma AI Video Generation (Free)","canonicalUrl":"https://www.xpersona.co/agent/clawhub-github-gamma-jiuma-ai-video-generation","canonicalPath":"/agent/clawhub-github-gamma-jiuma-ai-video-generation","generatedAt":"2026-10-10T17:34:14.217Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-10T13:59:20.757Z","emptyReason":null},"description":"免费的ai视频生成创作平台（Video Generation Skill），支持生成视频、图片、声音、视频动作模仿、视频人物替换等等。九马AI官网：https://www.jiuma.com Skill: Jiuma AI Video Generation (Free) Owner: github-gamma Summary: 免费的ai视频生成创作平台（Video Generation Skill），支持生成视频、图片、声音、视频动作模仿、视频人物替换等等。九马AI官网：https://www.jiuma.com Tags: latest:1.0.8 Version history: v1.0.8 | 2026-04-07T07:43:41.650Z | auto - Updated all command-line code examples to use the correct skill folder name jiuma-ai-video-generation. - Added repeated reminders to adapt command-line path syntax based on the","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.4K downloads reported by the source. Last updated 10/10/2026.","installCommand":"clawhub skill install s17a22w8q925xd9hnqsrjnm6gs83n8af:jiuma-ai-video-generation","sourceUrl":"https://clawhub.ai/github-gamma/jiuma-ai-video-generation","homepage":"https://clawhub.ai/github-gamma/skills/jiuma-ai-video-generation","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/github-gamma/jiuma-ai-video-generation","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/github-gamma/skills/jiuma-ai-video-generation","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":63,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"免费的ai视频生成创作平台（Video Generation Skill），支持生成视频、图片、声音、视频动作模仿、视频人物替换等等。九马AI官网：https://www.jiuma.com Skill: Jiuma AI Video Generation (Free) Owner: github-gamma Summ"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T13:59:20.757Z","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":"2026-10-10T13:59:20.757Z","emptyReason":null},"stars":null,"forks":null,"downloads":1400,"packageName":null,"latestVersion":"1.0.8","tractionLabel":"1.4K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T13:59:20.757Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T13:59:20.757Z","lastCrawledAt":"2026-10-10T13:59:20.757Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T13:59:20.757Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.8","createdAt":"2026-04-07T07:43:41.650Z","changelog":"- Updated all command-line code examples to use the correct skill folder name jiuma-ai-video-generation. - Added repeated reminders to adapt command-line path syntax based on the user's operating system, especially for Windows users. - Revised \"任务类型(task_type)\" descriptions and examples, including new naming such as \"wan2.6(ref2video)\" and \"wan2.6(text2video)\". - Improved clarity and accuracy in task parameter explanations and usage instructions. - Added and highlighted multiple \"重要\" (Important) sections to prevent path and OS-related errors for end-users.","fileCount":8,"zipByteSize":11874},{"version":"1.0.7","createdAt":"2026-04-03T09:54:45.857Z","changelog":"Major update: Completely refactored video generation workflow with modular scripts and improved authorization flow. - Split main script into modular tools: task submission, result querying, uploading, and authorization. - Added new scripts for auth, check auth status, task submission, result polling, and file upload. - Updated SKILL.md with detailed modern workflow, task_type documentation, and step-by-step usage examples. - Removed legacy scripts and previous usage instructions. - Enhanced result and upload output formats and clarified parameter requirements.","fileCount":7,"zipByteSize":10667},{"version":"1.0.6","createdAt":"2026-03-28T08:31:06.188Z","changelog":"- Skill name updated from \"jiuma\" to \"jiuma-ai-video-generation\" - Script and usage examples now use the new directory and naming convention: jiuma-ai-video-generation - Added an Installation section with instructions to install \"keyring\" - No changes were made to the main workflow or API parameters - Channel/media handling instructions unchanged","fileCount":4,"zipByteSize":6717},{"version":"1.0.5","createdAt":"2026-03-28T07:55:01.956Z","changelog":"Version 1.0.5 - Added _meta.json metadata file. - Clarified and updated the process for sending media to the openclaw-weixin channel. - Improved instructions on delivering QR code images for authorization. - Updated description to emphasize video generation platform focus. - No changes to core functionality; workflow and command usage remain the same.","fileCount":4,"zipByteSize":6951},{"version":"1.0.4","createdAt":"2026-03-27T10:18:35.826Z","changelog":"- 增加了技能描述，明确支持上传图片生成数字人说话视频，并提供九马AI官网链接。 - 扩充了平台介绍，说明用户可通过上传图片生成数字人口播视频，九马AI提供算力支持。 - 其它功能与使用方式保持不变。","fileCount":4,"zipByteSize":6422},{"version":"1.0.3","createdAt":"2026-03-27T10:14:41.290Z","changelog":"- Updated skill description for clarity and brevity. - Clarified and adjusted example commands to use explicit absolute paths instead of \"{baseDir}\" and “~”. - Added instructions to always replace “~” with a full absolute path when running scripts. - Introduced usage of the --channel parameter for session/channel context, with example values. - Removed outdated website help instructions from the description. - Improved formatting and command examples for easier reference.","fileCount":4,"zipByteSize":6330},{"version":"1.0.2","createdAt":"2026-03-26T10:18:27.708Z","changelog":"- 更新描述，明确支持通过上传图片生成数字人说话视频 - 增加“九马AI提供算力支持”与九马官网帮助链接 - 其他功能和使用方式未变，接口和示例保持一致","fileCount":4,"zipByteSize":6312},{"version":"1.0.0","createdAt":"2026-03-26T10:04:32.624Z","changelog":"jiuma-ai-video-generation 1.0.0 - Initial release of the skill. - Supports submitting asynchronous video generation tasks via API. - Enables file upload (images, videos, sounds) to the platform and returns resource URLs. - Provides clear usage instructions for command-line execution, including parameter passing rules. - Implements status polling and sends generated video files to users upon task completion. - Includes detailed documentation on workflow, parameters, and output interpretation.","fileCount":4,"zipByteSize":6226}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17a22w8q925xd9hnqsrjnm6gs83n8af:jiuma-ai-video-generation","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","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-github-gamma-jiuma-ai-video-generation/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-github-gamma-jiuma-ai-video-generation/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-github-gamma-jiuma-ai-video-generation/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-github-gamma-jiuma-ai-video-generation/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-github-gamma-jiuma-ai-video-generation/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-github-gamma-jiuma-ai-video-generation/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T17:34:14.216Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-github-gamma-jiuma-ai-video-generation/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-github-gamma-jiuma-ai-video-generation/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-github-gamma-jiuma-ai-video-generation/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-github-gamma-jiuma-ai-video-generation/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":"2026-10-10T13:59:20.757Z","emptyReason":null},"readme":"Skill: Jiuma AI Video Generation (Free)\n\nOwner: github-gamma\n\nSummary: 免费的ai视频生成创作平台（Video Generation Skill），支持生成视频、图片、声音、视频动作模仿、视频人物替换等等。九马AI官网：https://www.jiuma.com\n\nTags: latest:1.0.8\n\nVersion history:\n\nv1.0.8 | 2026-04-07T07:43:41.650Z | auto\n\n- Updated all command-line code examples to use the correct skill folder name jiuma-ai-video-generation.\n- Added repeated reminders to adapt command-line path syntax based on the user's operating system, especially for Windows users.\n- Revised \"任务类型(task_type)\" descriptions and examples, including new naming such as \"wan2.6(ref2video)\" and \"wan2.6(text2video)\".\n- Improved clarity and accuracy in task parameter explanations and usage instructions.\n- Added and highlighted multiple \"重要\" (Important) sections to prevent path and OS-related errors for end-users.\n\nv1.0.7 | 2026-04-03T09:54:45.857Z | auto\n\nMajor update: Completely refactored video generation workflow with modular scripts and improved authorization flow.\n\n- Split main script into modular tools: task submission, result querying, uploading, and authorization.\n- Added new scripts for auth, check auth status, task submission, result polling, and file upload.\n- Updated SKILL.md with detailed modern workflow, task_type documentation, and step-by-step usage examples.\n- Removed legacy scripts and previous usage instructions.\n- Enhanced result and upload output formats and clarified parameter requirements.\n\nv1.0.6 | 2026-03-28T08:31:06.188Z | user\n\n- Skill name updated from \"jiuma\" to \"jiuma-ai-video-generation\"\n- Script and usage examples now use the new directory and naming convention: jiuma-ai-video-generation\n- Added an Installation section with instructions to install \"keyring\"\n- No changes were made to the main workflow or API parameters\n- Channel/media handling instructions unchanged\n\nv1.0.5 | 2026-03-28T07:55:01.956Z | user\n\nVersion 1.0.5\n\n- Added _meta.json metadata file.\n- Clarified and updated the process for sending media to the openclaw-weixin channel.\n- Improved instructions on delivering QR code images for authorization.\n- Updated description to emphasize video generation platform focus.\n- No changes to core functionality; workflow and command usage remain the same.\n\nv1.0.4 | 2026-03-27T10:18:35.826Z | user\n\n- 增加了技能描述，明确支持上传图片生成数字人说话视频，并提供九马AI官网链接。\n- 扩充了平台介绍，说明用户可通过上传图片生成数字人口播视频，九马AI提供算力支持。\n- 其它功能与使用方式保持不变。\n\nv1.0.3 | 2026-03-27T10:14:41.290Z | user\n\n- Updated skill description for clarity and brevity.\n- Clarified and adjusted example commands to use explicit absolute paths instead of \"{baseDir}\" and “~”.\n- Added instructions to always replace “~” with a full absolute path when running scripts.\n- Introduced usage of the --channel parameter for session/channel context, with example values.\n- Removed outdated website help instructions from the description.\n- Improved formatting and command examples for easier reference.\n\nv1.0.2 | 2026-03-26T10:18:27.708Z | user\n\n- 更新描述，明确支持通过上传图片生成数字人说话视频\n- 增加“九马AI提供算力支持”与九马官网帮助链接\n- 其他功能和使用方式未变，接口和示例保持一致\n\nv1.0.0 | 2026-03-26T10:04:32.624Z | user\n\njiuma-ai-video-generation 1.0.0\n\n- Initial release of the skill.\n- Supports submitting asynchronous video generation tasks via API.\n- Enables file upload (images, videos, sounds) to the platform and returns resource URLs.\n- Provides clear usage instructions for command-line execution, including parameter passing rules.\n- Implements status polling and sends generated video files to users upon task completion.\n- Includes detailed documentation on workflow, parameters, and output interpretation.\n\nArchive index:\n\nArchive v1.0.8: 8 files, 11874 bytes\n\nFiles: scripts/auth.py (4953b), scripts/check_auth_status.py (1150b), scripts/submit_generation_task.py (3034b), scripts/task_result.py (2867b), scripts/upload_file.py (1912b), skill-card.md (1845b), SKILL.md (8255b), _meta.json (144b)\n\nFile v1.0.8:SKILL.md\n\n---\nname: jiuma-ai-video-generation\ndescription: 免费的ai视频生成创作平台（Video Generation Skill），支持生成视频、图片、声音、视频动作模仿、视频人物替换等等。九马AI官网：https://www.jiuma.com\nversion: 2.0.0\nupdate_date: 2026-04-03\n---\n\n## 📁 文件结构\n\n```\nscripts/\n├── submit_generation_task.py        # 提交生成任务🚀\n├── task_result.py        # 结果查询工具📊\n├── upload_file.py         # 文件上传工具\n└── auth.py          # 获取token\n```\n\n## 🚀 快速开始（推荐）\n\n**重要：注意用户的操作系统，需要使用适配用户的操作系统的类型的命令行代码，若是windows，请改成绝对路径调用**\n\n### 0. **检查授权状态**\n```bash\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/check_auth_status.py\n```\n\n### 1. **一键授权(已授权则跳过)**\n```bash\n# 默认授权方法\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/auth.py --identification_code=\"<身份标识码(若无留空)>\" --channel=\"<消息渠道(如：openclaw-weixin、webchat等)>\"\n\n#强制重新授权\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/auth.py --identification_code=\"\" --channel=\"<消息渠道(如：openclaw-weixin、webchat等)>\" --force\n```\n\n\n### 2. **生成视频(提交生成任务)**\n```bash\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/submit_generation_task.py --task_params=\"{'reference_urls': ['https://picsum.photos/800/450'], 'prompt': '自然', 'duration': 3, 'task_type': 'wan2.6'}\"\n```\n**提交生成任务时，图片、视频、音频等等资源文件必须先上传到平台获得url，不得直接使用本地路径提交生成**\n**task_type为枚举类型，必须严格与下表严格对应，否则无法生成**\n\n### 3. **查询任务结果**\n```bash\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/task_result.py  --task_id=<任务ID>\n```\n\n### 4. **上传本地文件(获得url)**\n```bash\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/upload_file.py --file_path=<文件路径>\n```\n\n### 支持的任务类型(task_type)\n|task_type(必须严格对应,枚举类型)|名称|功能描述|任务参数|提示词要求|提示词示例|\n|---------|----|--------|--------|---------|----------|\n|\"wan2.6(ref2video)\"|万象2.6模型|图像生成视频（可控制说话、动作、运镜、画面内容）|reference_urls:array,参考图片或者视频的url;prompt:string,动作描述+画面描述+运镜描述+说话内容;duration:int,视频秒数,取值2~10,最大10秒，最小2秒|同一段提示词里面包含：动作描述+画面描述+运镜描述+说话内容，提示词通过“character1、character2”这类标识引用角色。角色顺序与 reference_urls 数组一一对应，即第 1 个 URL 为 character1，第 2 个为 character2，依此类推。|character2 坐在靠窗的椅子上，手持 character3，在 character4 旁演奏一首舒缓的美国乡村民谣。character1 对character2开口说道：“听起来不错”。|\n|\"wan2.6(text2video)\"|万象2.6文生视频|模型可自动进行分镜切换，例如从全景切换到特写，适合制作MV等场景。|prompt:string,动作描述+画面描述+运镜描述+说话内容;duration:int,视频秒数,取值2~10,最大15秒，最小2秒，请勿超出时长|同一段提示词里面包含：动作描述+画面描述+运镜描述+说话内容|一段紧张刺激的侦探追查故事，展现电影级叙事能力。第1个镜头[0-3秒] 全景：雨夜的纽约街头，霓虹灯闪烁，一位身穿黑色风衣的侦探快步行走。 第2个镜头[3-6秒] 中景：侦探进入一栋老旧建筑，雨水打湿了他的外套，门在他身后缓缓关闭。 第3个镜头[6-9秒] 特写：侦探的眼神坚毅专注，远处传来警笛声，他微微皱眉思考。 第4个镜头[9-12秒] 中景：侦探在昏暗走廊中小心前行，手电筒照亮前方。 第5个镜头[12-15秒] 特写：侦探发现关键线索，脸上露出恍然大悟的表情。|\n|\"action_imitation_user_background_onetoall(prompt)\"|动作模仿(用户特别要求适配身高时使用)|自动适配角色的身高，特别是针对小朋友、卡通角色等等动作模仿|image_url:url,角色图片;video_url,url,参考动作视频;prompt,text,动作提示词|一个角色在跳舞|\n|\"action_imitation_user_background(prompt)\"|动作模仿(常用)|图片中的人物模仿视频中的角色的动作|image_url:url,角色图片;video_url,url,参考动作视频;prompt,text,动作提示词|一个角色在跳舞|\n|\"action_imitation_video_backgound(prompt)\"|人物替换/角色替换|把视频中的角色换成图片中的角色|image_url:url,角色图片;video_url,url,参考动作视频;prompt,text,动作提示词|一个角色在跳舞|\n\n注意：task_type需要严格对应，否则无法制作\n\n\n## 🎬 完整示例：制作短视频\n\n**重要：注意用户的操作系统，需要使用适配用户的操作系统的类型的命令行代码，若是windows，请改成绝对路径调用**\n\n### 步骤0：检测授权状态\n```bash\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/check_auth_status.py\n```\n\n**重要：注意用户的操作系统，需要使用适配用户的操作系统的类型的命令行代码，若是windows，请改成绝对路径调用**\n\n### 步骤1：授权(已授权则跳过)\n```bash\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/auth.py --identification_code=\"58fe87fb26b579b309ad782afb7a157155d338f31ad2a26419ae8550cda16747\" --channel=\"openclaw-weixin\"\n```\n\n**重要：注意用户的操作系统，需要使用适配用户的操作系统的类型的命令行代码，若是windows，请改成绝对路径调用**\n\n### 步骤2：生成分镜\n```bash\n# 分镜1：开场特效（3秒）\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/submit_generation_task.py --task_params=\"{'reference_urls': ['https://picsum.photos/800/450'], 'prompt': '纯黑背景，白色发光文字快速闪现，科技感光晕', 'duration': 3, 'task_type': 'wan2.6'}\"\n\n# 分镜2：情感铺垫（9秒）\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/submit_generation_task.py --task_params=\"{'reference_urls': ['https://picsum.photos/800/450'], 'prompt': '年轻人拿着泛黄老照片，表情落寞，怀旧色调', 'duration': 9, 'task_type': 'wan2.6'}\"\n\n# 分镜3：AI处理（10秒）\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/submit_generation_task.py --task_params=\"{'reference_urls': ['https://picsum.photos/800/450'], 'prompt': '照片被AI扫描处理，科技感特效，代码流动画', 'duration': 10, 'task_type': 'wan2.6'}\"\n```\n\n**重要：注意用户的操作系统，需要使用适配用户的操作系统的类型的命令行代码，若是windows，请改成绝对路径调用**\n\n### 步骤3：检查进度\n```bash\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/task_result.py  --task_id=ai-69cf39df3e61e1280\n```\n\n\n## 📄 输出说明\n\n### 任务结果\nJSON格式输出，关键字段：\n- `task_id`: 任务唯一标识\n- `task_status`: 任务状态（`PENDING`、`RUNNING`、`SUCCEEDED`、`FAILED`、`CANCELED`）\n- `video_url`: 生成的视频地址（任务成功时）\n- `image_url`: 生成的图片地址（任务成功时）\n\n### 上传结果\n- `file_url`: 上传的文件地址\n\n## 🏆 总结\n\n**改进版技能优势：**\n1. ✅ **快速上手** - 新用户5分钟内开始生成视频\n2. ✅ **稳定运行** - 减少授权相关问题  \n3. ✅ **方便管理** - 随时查看任务状态\n4. ✅ **批量处理** - 支持多任务工作流\n\n---\n\n**重要：注意用户的操作系统，需要使用适配用户的操作系统的类型的命令行代码**\n**💡 提示**: 首次使用建议运行 `python ~/.openclaw/workspace/skills/jiuma/scripts/auth.py --identification_code=\"<身份标识码(会话历史中无则留空)>\" --channel=\"<消息渠道(如：openclaw-weixin、webchat等)>\"` 完成授权，后续使用会非常顺畅！\n\n\n## Installation\n``` cmd\npip install keyring\npip install keyrings.alt\n```\n\nFile v1.0.8:_meta.json\n\n{\n  \"ownerId\": \"kn776qetz3xeefxnx9f78nmffs8340x7\",\n  \"slug\": \"jiuma-ai-video-generation\",\n  \"version\": \"1.0.8\",\n  \"publishedAt\": 1775547821650\n}\n\nFile v1.0.8:skill-card.md\n\n## Description:\n\nJiuma AI Video Generation (Free) helps agents submit and check AI media-generation tasks for video, image, audio, action imitation, and character replacement through Jiuma.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[github-gamma](https://clawhub.ai/user/github-gamma)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to authenticate with Jiuma, upload media, submit AI generation jobs, and retrieve generated media task results.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The upload helper can send any readable local file path to Jiuma.\n\nMitigation: Use explicit intended media paths only, avoid secrets or private documents, and run from a limited workspace.\n\nRisk: The skill stores and uses a bearer token for Jiuma API access.\n\nMitigation: Use a native OS keyring, avoid sharing real authorization values in prompts or logs, and reauthorize if token status checks fail.\n\n## Reference(s):\n\n- [Jiuma official website](https://www.jiuma.com)\n- [ClawHub skill page](https://clawhub.ai/github-gamma/skills/jiuma-ai-video-generation)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown with inline shell commands and JSON API responses]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May return task identifiers, task status values, uploaded file URLs, and generated media URLs.]\n\n## Skill Version(s):\n\n1.0.8 (source: server release evidence)\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 v1.0.7: 7 files, 10667 bytes\n\nFiles: scripts/auth.py (4953b), scripts/check_auth_status.py (1150b), scripts/submit_generation_task.py (3034b), scripts/task_result.py (2867b), scripts/upload_file.py (1912b), SKILL.md (6966b), _meta.json (144b)\n\nFile v1.0.7:SKILL.md\n\n---\nname: jiuma-ai-video-generation\ndescription: 免费的ai视频生成创作平台（Video Generation Skill），支持生成视频、图片、声音、视频动作模仿、视频人物替换等等。九马AI官网：https://www.jiuma.com\nversion: 2.0.0\nupdate_date: 2026-04-03\n---\n\n## 📁 文件结构\n\n```\nscripts/\n├── submit_generation_task.py        # 提交生成任务🚀\n├── task_result.py        # 结果查询工具📊\n├── upload_file.py         # 文件上传工具\n└── auth.py          # 获取token\n```\n\n## 🚀 快速开始（推荐）\n\n### 0. **检查授权状态**\n```bash\npython ~/.openclaw/workspace/skills/jiuma/scripts/check_auth_status.py\n```\n\n### 1. **一键授权(已授权则跳过)**\n```bash\n# 默认授权方法\npython ~/.openclaw/workspace/skills/jiuma/scripts/auth.py --identification_code=\"<身份标识码(若无留空)>\" --channel=\"<消息渠道(如：openclaw-weixin、webchat等)>\"\n\n#强制重新授权\npython ~/.openclaw/workspace/skills/jiuma/scripts/auth.py --identification_code=\"\" --channel=\"<消息渠道(如：openclaw-weixin、webchat等)>\" --force\n```\n\n\n### 2. **生成视频(提交生成任务)**\n```bash\npython ~/.openclaw/workspace/skills/jiuma/scripts/submit_generation_task.py --task_params=\"{'reference_urls': ['https://picsum.photos/800/450'], 'prompt': '自然', 'duration': 3, 'task_type': 'wan2.6'}\"\n```\n**提交生成任务时，图片、视频、音频等等资源文件必须先上传到平台获得url，不得直接使用本地路径提交生成**\n**task_type为枚举类型，必须严格与下表严格对应，否则无法生成**\n\n### 3. **查询任务结果**\n```bash\npython ~/.openclaw/workspace/skills/jiuma/scripts/task_result.py  --task_id=<任务ID>\n```\n\n### 4. **上传本地文件(获得url)**\n```bash\npython ~/.openclaw/workspace/skills/jiuma/scripts/upload_file.py --file_path=<文件路径>\n```\n\n### 支持的任务类型(task_type)\n|task_type(必须严格对应,枚举类型)|名称|功能描述|任务参数|提示词要求|提示词示例|\n|---------|----|--------|--------|---------|----------|\n|\"wan2.6\"|万象2.6模型|图像生成视频（可控制说话、动作、运镜、画面内容）|reference_urls:array,参考图片或者视频的url;prompt:string,动作描述+画面描述+运镜描述+说话内容;duration:int,视频秒数,取值2~10,最大10秒，最小2秒|同一段提示词里面包含：动作描述+画面描述+运镜描述+说话内容，提示词通过“character1、character2”这类标识引用角色。角色顺序与 reference_urls 数组一一对应，即第 1 个 URL 为 character1，第 2 个为 character2，依此类推。|character2 坐在靠窗的椅子上，手持 character3，在 character4 旁演奏一首舒缓的美国乡村民谣。character1 对character2开口说道：“听起来不错”。|\n|\"wan2.6-t2v\"|万象2.6文生视频|模型可自动进行分镜切换，例如从全景切换到特写，适合制作MV等场景。|任务参数|同一段提示词里面包含：动作描述+画面描述+运镜描述+说话内容|一段紧张刺激的侦探追查故事，展现电影级叙事能力。第1个镜头[0-3秒] 全景：雨夜的纽约街头，霓虹灯闪烁，一位身穿黑色风衣的侦探快步行走。 第2个镜头[3-6秒] 中景：侦探进入一栋老旧建筑，雨水打湿了他的外套，门在他身后缓缓关闭。 第3个镜头[6-9秒] 特写：侦探的眼神坚毅专注，远处传来警笛声，他微微皱眉思考。 第4个镜头[9-12秒] 中景：侦探在昏暗走廊中小心前行，手电筒照亮前方。 第5个镜头[12-15秒] 特写：侦探发现关键线索，脸上露出恍然大悟的表情。|\n|\"action_imitation_user_background_onetoall(prompt)\"|动作模仿(用户特别要求适配身高时使用)|自动适配角色的身高，特别是针对小朋友、卡通角色等等动作模仿|image_url:url,角色图片;video_url,url,参考动作视频;prompt,text,动作提示词|一个角色在跳舞|\n|\"action_imitation_user_background(prompt)\"|动作模仿(常用)|图片中的人物模仿视频中的角色的动作|image_url:url,角色图片;video_url,url,参考动作视频;prompt,text,动作提示词|一个角色在跳舞|\n|\"action_imitation_video_backgound(prompt)\"|人物替换/角色替换|把视频中的角色换成图片中的角色|image_url:url,角色图片;video_url,url,参考动作视频;prompt,text,动作提示词|一个角色在跳舞|\n\n注意：task_type需要严格对应，否则无法制作\n\n\n## 🎬 完整示例：制作短视频\n\n### 步骤0：检测授权状态\n```bash\npython ~/.openclaw/workspace/skills/jiuma/scripts/check_auth_status.py\n```\n\n### 步骤1：授权(已授权则跳过)\n```bash\npython ~/.openclaw/workspace/skills/jiuma/scripts/auth.py --identification_code=\"58fe87fb26b579b309ad782afb7a157155d338f31ad2a26419ae8550cda16747\" --channel=\"openclaw-weixin\"\n```\n\n### 步骤2：生成分镜\n```bash\n# 分镜1：开场特效（3秒）\npython ~/.openclaw/workspace/skills/jiuma/scripts/submit_generation_task.py --task_params=\"{'reference_urls': ['https://picsum.photos/800/450'], 'prompt': '纯黑背景，白色发光文字快速闪现，科技感光晕', 'duration': 3, 'task_type': 'wan2.6'}\"\n\n# 分镜2：情感铺垫（9秒）\npython ~/.openclaw/workspace/skills/jiuma/scripts/submit_generation_task.py --task_params=\"{'reference_urls': ['https://picsum.photos/800/450'], 'prompt': '年轻人拿着泛黄老照片，表情落寞，怀旧色调', 'duration': 9, 'task_type': 'wan2.6'}\"\n\n# 分镜3：AI处理（10秒）\npython ~/.openclaw/workspace/skills/jiuma/scripts/submit_generation_task.py --task_params=\"{'reference_urls': ['https://picsum.photos/800/450'], 'prompt': '照片被AI扫描处理，科技感特效，代码流动画', 'duration': 10, 'task_type': 'wan2.6'}\"\n```\n\n### 步骤3：检查进度\n```bash\npython ~/.openclaw/workspace/skills/jiuma/scripts/task_result.py  --task_id=ai-69cf39df3e61e1280\n```\n\n\n\n## 📄 输出说明\n\n### 任务结果\nJSON格式输出，关键字段：\n- `task_id`: 任务唯一标识\n- `task_status`: 任务状态（`PENDING`、`RUNNING`、`SUCCEEDED`、`FAILED`、`CANCELED`）\n- `video_url`: 生成的视频地址（任务成功时）\n- `image_url`: 生成的图片地址（任务成功时）\n\n### 上传结果\n- `file_url`: 上传的文件地址\n\n## 🏆 总结\n\n**改进版技能优势：**\n1. ✅ **快速上手** - 新用户5分钟内开始生成视频\n2. ✅ **稳定运行** - 减少授权相关问题  \n3. ✅ **方便管理** - 随时查看任务状态\n4. ✅ **批量处理** - 支持多任务工作流\n\n---\n\n**💡 提示**: 首次使用建议运行 `python ~/.openclaw/workspace/skills/jiuma/scripts/auth.py --identification_code=\"<身份标识码(会话历史中无则留空)>\" --channel=\"<消息渠道(如：openclaw-weixin、webchat等)>\"` 完成授权，后续使用会非常顺畅！\n\n\n## Installation\n``` cmd\npip install keyring\npip install keyrings.alt\n```\n\nFile v1.0.7:_meta.json\n\n{\n  \"ownerId\": \"kn776qetz3xeefxnx9f78nmffs8340x7\",\n  \"slug\": \"jiuma-ai-video-generation\",\n  \"version\": \"1.0.7\",\n  \"publishedAt\": 1775210085857\n}\n\nArchive v1.0.6: 4 files, 6717 bytes\n\nFiles: scripts/jmai_upload.py (3549b), scripts/jmai.py (5806b), SKILL.md (4932b), _meta.json (144b)\n\nFile v1.0.6:SKILL.md\n\n---\nname: jiuma-ai-video-generation\ndescription: 免费的ai视频生成创作平台，支持生成视频、图片、声音等等，用户上传图片可生成数字人说话的视频，九马AI提供算力支持，若有疑问请访问九马官网需求帮助，九马AI官网：https://www.jiuma.com\n---\n\n# Video Generation Skill\n\n通过调用指定API，提交图片/视频生成任务，并轮询获取生成结果。\n\n## 默认工作流\n\n由于生成是异步任务且耗时较长，工作流主要是提交任务 是否登录 和轮询状态。请在子代理运行以下流程，等一会儿有结果通知用户：\n1.  **确认需求**：跟用户确认需求，提醒用户提供必要的资源，可多轮确认，确保用户提供了足够的信息\n2.  **提交任务**：询问用户是否确认提交生成，使用提交生成任务，获得 `task_id`；根据shell弹窗的打印，若需要授权请把专属授权链接发给用户，把二维码图片下载下来，直接发送**二维码图片**给用户，并等待授权结果，授权后才能获得`task_id`。\n3.  **等待任务执行**：提交后shell弹窗会定时打印任务状态，直到状态变为 `SUCCEEDED` 或 `FAILED`。\n4.  **获取结果**：任务成功后，从shell弹窗打印的 `output` 字段中获取视频文件的URL。\n5.  **发送结果**：一定要把视频下载下来并且把视频发送给用户\n\n\n发送媒体到openclaw-weixin渠道的流程：\n脚本输出 { \"video_url\": \"...\" } \n    ↓\n我用 message 工具的 media 参数传递 URL\n    ↓\nchannel (openclaw-weixin) 自己负责下载并发送\n\n\n## Usage\n1.提交任务并等待最终结果\n命令行代码请按照一下规则：\n*必须使用绝对路径进行调用\n*必须调用jmai.py脚本进行生成\n*参数必须以英文双引号包裹，并且以字典的形式传递\n*字段中的key必须使用单引号，不得使用双引号\n\n```\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/jmai.py \"<DICT>\"\n```\n**注意：运行脚本时，需要把“~”换成绝对路径，切勿使用“&&”**\n\n2.上传文件（支持图片、视频、声音等）\n命令行代码请按照一下规则：\n*必须使用绝对路径进行调用\n*必须调用jmai_upload.py脚本进行生成\n*参数必须以英文双引号包裹，并且以字典的形式传递\n*字段中的key必须使用单引号，不得使用双引号\n\n```\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/jmai_upload.py \"<DICT>\"\n```\n**注意：运行脚本时，必须把“~”换成绝对路径，切勿使用“&&”**\n\n## Request Parameters\n\n调用时，key需与下表“Param”列对应\n\n1.提交任务：\n| Param | Type | Required | Default | Description |\n|-------|------|----------------|--------|------\n| reference_urls | array | yes | - | 参考图片/视频的URL列表 （注：本地文件需要使用上传文件接口传到平台上获得URL）\n| prompt | str  | yes | - | 对生成画面的文字描述 \n| duration | str  | yes | - |视频时长，如 3, 5, 10 (秒) \n| task_type | str | yes |`wan2.6` | 任务类型\n\n2.上传文件：\n| Param | Type | Required | Default | Description |\n|-------|------|----------------|--------|------\n| file_path | str | yes | - | 文件绝对路径地址 \n\n注意：--channel参数为会话渠道，取值通常为webchat、openclaw-wechat、twitter等等\n## Examples\n示例1: 提交一个完整的视频生成任务，字典参数请使用单引号\n```cmd\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/jmai.py \"{'reference_urls': ['https://picsum.photos/800/450', 'https://picsum.photos/800/450'], 'prompt': '自然', 'duration': 3, 'task_type': 'wan2.6'}\" --channel=\"openclaw-weixin\"\n\n```\n**注意：运行脚本时，必须把“~”换成绝对路径，切勿使用“&&”**\n\n示例2: 上传一张图片\n```cmd\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/jmai_upload.py \"{'file_path': '文件绝对路径'}\" --channel=\"openclaw-weixin\"\n\n```\n**注意：运行脚本时，必须把“~”换成绝对路径，切勿使用“&&”**\n\n## 输出说明\n1.任务结果\n查询状态跟获取结果，脚本的输出为JSON格式，\ndata关键字段说明：\n- `task_id`: 任务唯一标识。\n- `task_status`: 任务状态，可能值为 `PENDING`（排队中）, `RUNNING`（处理中）, `SUCCEEDED`（成功）, `FAILED`（失败）, `CANCELED`（已取消）, `UNKNOWN`（未知）。\n- 当 `task_status` 为 `SUCCEEDED` 时，`output` 字段中会包含结果URL：\n    - `output.video_url`: 生成的视频地址。\n    - `output.image_url`: 生成的图片地址。\n    - `output.video_first_frame_url`: 视频首帧图片地址。\n\n2.上传结果\ndata关键字段说明：\n- `file_url`: 上传的文件地址\n\n## 当前状态\n\n功能完整，已实现任务提交、状态轮询与结果获取。\n\n## Installation\n\n```cmd\npip install keyring\n```\n\nFile v1.0.6:_meta.json\n\n{\n  \"ownerId\": \"kn776qetz3xeefxnx9f78nmffs8340x7\",\n  \"slug\": \"jiuma-ai-video-generation\",\n  \"version\": \"1.0.6\",\n  \"publishedAt\": 1774686666188\n}\n\nArchive v1.0.5: 4 files, 6951 bytes\n\nFiles: scripts/jmai_upload.py (3745b), scripts/jmai.py (6093b), SKILL.md (4783b), _meta.json (144b)\n\nFile v1.0.5:SKILL.md\n\n---\nname: jiuma\ndescription: 免费的ai视频生成创作平台，支持生成视频、图片、声音等等，用户上传图片可生成数字人说话的视频，九马AI提供算力支持，若有疑问请访问九马官网需求帮助，九马AI官网：https://www.jiuma.com\n---\n\n# Video Generation Skill\n\n通过调用指定API，提交图片/视频生成任务，并轮询获取生成结果。\n\n## 默认工作流\n\n由于生成是异步任务且耗时较长，工作流主要是提交任务 是否登录 和轮询状态。请在子代理运行以下流程，等一会儿有结果通知用户：\n1.  **确认需求**：跟用户确认需求，提醒用户提供必要的资源，可多轮确认，确保用户提供了足够的信息\n2.  **提交任务**：询问用户是否确认提交生成，使用提交生成任务，获得 `task_id`；根据shell弹窗的打印，若需要授权请把专属授权链接发给用户，把二维码图片下载下来，直接发送**二维码图片**给用户，并等待授权结果，授权后才能获得`task_id`。\n3.  **等待任务执行**：提交后shell弹窗会定时打印任务状态，直到状态变为 `SUCCEEDED` 或 `FAILED`。\n4.  **获取结果**：任务成功后，从shell弹窗打印的 `output` 字段中获取视频文件的URL。\n5.  **发送结果**：一定要把视频下载下来并且把视频发送给用户\n\n\n发送媒体到openclaw-weixin渠道的流程：\n脚本输出 { \"video_url\": \"...\" } \n    ↓\n我用 message 工具的 media 参数传递 URL\n    ↓\nchannel (openclaw-weixin) 自己负责下载并发送\n\n\n## Usage\n1.提交任务并等待最终结果\n命令行代码请按照一下规则：\n*必须使用绝对路径进行调用\n*必须调用jmai.py脚本进行生成\n*参数必须以英文双引号包裹，并且以字典的形式传递\n*字段中的key必须使用单引号，不得使用双引号\n\n```\npython ~/.openclaw/workspace/skills/jiuma/scripts/jmai.py \"<DICT>\"\n```\n**注意：运行脚本时，需要把“~”换成绝对路径，切勿使用“&&”**\n\n2.上传文件（支持图片、视频、声音等）\n命令行代码请按照一下规则：\n*必须使用绝对路径进行调用\n*必须调用jmai_upload.py脚本进行生成\n*参数必须以英文双引号包裹，并且以字典的形式传递\n*字段中的key必须使用单引号，不得使用双引号\n\n```\npython ~/.openclaw/workspace/skills/jiuma/scripts/jmai_upload.py \"<DICT>\"\n```\n**注意：运行脚本时，必须把“~”换成绝对路径，切勿使用“&&”**\n\n## Request Parameters\n\n调用时，key需与下表“Param”列对应\n\n1.提交任务：\n| Param | Type | Required | Default | Description |\n|-------|------|----------------|--------|------\n| reference_urls | array | yes | - | 参考图片/视频的URL列表 （注：本地文件需要使用上传文件接口传到平台上获得URL）\n| prompt | str  | yes | - | 对生成画面的文字描述 \n| duration | str  | yes | - |视频时长，如 3, 5, 10 (秒) \n| task_type | str | yes |`wan2.6` | 任务类型\n\n2.上传文件：\n| Param | Type | Required | Default | Description |\n|-------|------|----------------|--------|------\n| file_path | str | yes | - | 文件绝对路径地址 \n\n注意：--channel参数为会话渠道，取值通常为webchat、openclaw-wechat、twitter等等\n## Examples\n示例1: 提交一个完整的视频生成任务，字典参数请使用单引号\n```cmd\npython ~/.openclaw/workspace/skills/jiuma/scripts/jmai.py \"{'reference_urls': ['https://picsum.photos/800/450', 'https://picsum.photos/800/450'], 'prompt': '自然', 'duration': 3, 'task_type': 'wan2.6'}\" --channel=\"openclaw-weixin\"\n\n```\n**注意：运行脚本时，必须把“~”换成绝对路径，切勿使用“&&”**\n\n示例2: 上传一张图片\n```cmd\npython ~/.openclaw/workspace/skills/jiuma/scripts/jmai_upload.py \"{'file_path': '文件绝对路径'}\" --channel=\"openclaw-weixin\"\n\n```\n**注意：运行脚本时，必须把“~”换成绝对路径，切勿使用“&&”**\n\n## 输出说明\n1.任务结果\n查询状态跟获取结果，脚本的输出为JSON格式，\ndata关键字段说明：\n- `task_id`: 任务唯一标识。\n- `task_status`: 任务状态，可能值为 `PENDING`（排队中）, `RUNNING`（处理中）, `SUCCEEDED`（成功）, `FAILED`（失败）, `CANCELED`（已取消）, `UNKNOWN`（未知）。\n- 当 `task_status` 为 `SUCCEEDED` 时，`output` 字段中会包含结果URL：\n    - `output.video_url`: 生成的视频地址。\n    - `output.image_url`: 生成的图片地址。\n    - `output.video_first_frame_url`: 视频首帧图片地址。\n\n2.上传结果\ndata关键字段说明：\n- `file_url`: 上传的文件地址\n\n## 当前状态\n\n功能完整，已实现任务提交、状态轮询与结果获取。\n\nFile v1.0.5:_meta.json\n\n{\n  \"ownerId\": \"kn776qetz3xeefxnx9f78nmffs8340x7\",\n  \"slug\": \"jiuma-ai-video-generation\",\n  \"version\": \"1.0.5\",\n  \"publishedAt\": 1774684501956\n}\n\nArchive v1.0.4: 4 files, 6422 bytes\n\nFiles: scripts/jmai_upload.py (2709b), scripts/jmai.py (6469b), SKILL.md (4559b), _meta.json (144b)\n\nFile v1.0.4:SKILL.md\n\n---\nname: jiuma\ndescription: 免费的ai创作平台，支持生成视频、图片、声音等等，用户上传图片可生成数字人说话的视频，九马AI提供算力支持，若有疑问请访问九马官网需求帮助，九马AI官网：https://www.jiuma.com\n---\n\n# Video Generation Skill\n\n通过调用指定API，提交图片/视频生成任务，并轮询获取生成结果。\n\n## 默认工作流\n\n由于生成是异步任务且耗时较长，工作流主要是提交任务 是否登录 和轮询状态。请在子代理运行以下流程，等一会儿有结果通知用户：\n1.  **确认需求**：跟用户确认需求，提醒用户提供必要的资源，可多轮确认，确保用户提供了足够的信息\n2.  **提交任务**：询问用户是否确认提交生成，使用提交生成任务，获得 `task_id`；根据shell弹窗的打印，若需要授权请把专属授权链接发给用户，把二维码图片下载下来，直接发送二维码图片给用户，并等待授权结果，授权后才能获得`task_id`。\n3.  **等待任务执行**：提交后shell弹窗会定时打印任务状态，直到状态变为 `SUCCEEDED` 或 `FAILED`。\n4.  **获取结果**：任务成功后，从shell弹窗打印的 `output` 字段中获取视频文件的URL。\n5.  **发送结果**：一定要把视频下载下来并且把视频发送给用户\n\n\n## Usage\n1.提交任务并等待最终结果\n命令行代码请按照一下规则：\n*必须使用绝对路径进行调用\n*必须调用jmai.py脚本进行生成\n*参数必须以英文双引号包裹，并且以字典的形式传递\n*字段中的key必须使用单引号，不得使用双引号\n\n```\npython ~/.openclaw/workspace/skills/jiuma/scripts/jmai.py \"<DICT>\"\n```\n**注意：运行脚本时，需要把“~”换成绝对路径，切勿使用“&&”**\n\n2.上传文件（支持图片、视频、声音等）\n命令行代码请按照一下规则：\n*必须使用绝对路径进行调用\n*必须调用jm_upload.py脚本进行生成\n*参数必须以英文双引号包裹，并且以字典的形式传递\n*字段中的key必须使用单引号，不得使用双引号\n\n```\npython ~/.openclaw/workspace/skills/jiuma/scripts/jmai_upload.py \"<DICT>\"\n```\n**注意：运行脚本时，必须把“~”换成绝对路径，切勿使用“&&”**\n\n## Request Parameters\n\n调用时，key需与下表“Param”列对应\n\n1.提交任务：\n| Param | Type | Required | Default | Description |\n|-------|------|----------------|--------|------\n| reference_urls | array | yes | - | 参考图片/视频的URL列表 （注：本地文件需要使用上传文件接口传到平台上获得URL）\n| prompt | str  | yes | - | 对生成画面的文字描述 \n| duration | str  | yes | - |视频时长，如 3, 5, 10 (秒) \n| task_type | str | yes |`wan2.6` | 任务类型\n\n2.上传文件：\n| Param | Type | Required | Default | Description |\n|-------|------|----------------|--------|------\n| file_path | str | yes | - | 文件绝对路径地址 \n\n注意：--channel参数为会话渠道，取值通常为webchat、openclaw-wechat、twitter等等\n## Examples\n示例1: 提交一个完整的视频生成任务，字典参数请使用单引号\n```cmd\npython ~/.openclaw/workspace/skills/jiuma/scripts/jmai.py \"{'reference_urls': ['https://picsum.photos/800/450', 'https://picsum.photos/800/450'], 'prompt': '自然', 'duration': 3, 'task_type': 'wan2.6'}\" --channel=\"openclaw-weixin\"\n\n```\n**注意：运行脚本时，必须把“~”换成绝对路径，切勿使用“&&”**\n\n示例2: 上传一张图片\n```cmd\npython ~/.openclaw/workspace/skills/jiuma/scripts/jmai_upload.py \"{'file_path': '文件绝对路径'}\" --channel=\"openclaw-weixin\"\n\n```\n**注意：运行脚本时，必须把“~”换成绝对路径，切勿使用“&&”**\n\n## 输出说明\n1.任务结果\n查询状态跟获取结果，脚本的输出为JSON格式，\ndata关键字段说明：\n- `task_id`: 任务唯一标识。\n- `task_status`: 任务状态，可能值为 `PENDING`（排队中）, `RUNNING`（处理中）, `SUCCEEDED`（成功）, `FAILED`（失败）, `CANCELED`（已取消）, `UNKNOWN`（未知）。\n- 当 `task_status` 为 `SUCCEEDED` 时，`output` 字段中会包含结果URL：\n    - `output.video_url`: 生成的视频地址。\n    - `output.image_url`: 生成的图片地址。\n    - `output.video_first_frame_url`: 视频首帧图片地址。\n\n2.上传结果\ndata关键字段说明：\n- `file_url`: 上传的文件地址\n\n## 当前状态\n\n功能完整，已实现任务提交、状态轮询与结果获取。\n\nFile v1.0.4:_meta.json\n\n{\n  \"ownerId\": \"kn776qetz3xeefxnx9f78nmffs8340x7\",\n  \"slug\": \"jiuma-ai-video-generation\",\n  \"version\": \"1.0.4\",\n  \"publishedAt\": 1774606715826\n}\n\nArchive v1.0.3: 4 files, 6330 bytes\n\nFiles: scripts/jmai_upload.py (2709b), scripts/jmai.py (6469b), SKILL.md (4387b), _meta.json (144b)\n\nFile v1.0.3:SKILL.md\n\n---\nname: jiuma\ndescription: 免费的ai创作平台，支持生成视频、图片、声音等等\n---\n\n# Video Generation Skill\n\n通过调用指定API，提交图片/视频生成任务，并轮询获取生成结果。\n\n## 默认工作流\n\n由于生成是异步任务且耗时较长，工作流主要是提交任务 是否登录 和轮询状态。请在子代理运行以下流程，等一会儿有结果通知用户：\n1.  **确认需求**：跟用户确认需求，提醒用户提供必要的资源，可多轮确认，确保用户提供了足够的信息\n2.  **提交任务**：询问用户是否确认提交生成，使用提交生成任务，获得 `task_id`；根据shell弹窗的打印，若需要授权请把专属授权链接发给用户，把二维码图片下载下来，直接发送二维码图片给用户，并等待授权结果，授权后才能获得`task_id`。\n3.  **等待任务执行**：提交后shell弹窗会定时打印任务状态，直到状态变为 `SUCCEEDED` 或 `FAILED`。\n4.  **获取结果**：任务成功后，从shell弹窗打印的 `output` 字段中获取视频文件的URL。\n5.  **发送结果**：一定要把视频下载下来并且把视频发送给用户\n\n\n## Usage\n1.提交任务并等待最终结果\n命令行代码请按照一下规则：\n*必须使用绝对路径进行调用\n*必须调用jmai.py脚本进行生成\n*参数必须以英文双引号包裹，并且以字典的形式传递\n*字段中的key必须使用单引号，不得使用双引号\n\n```\npython ~/.openclaw/workspace/skills/jiuma/scripts/jmai.py \"<DICT>\"\n```\n**注意：运行脚本时，需要把“~”换成绝对路径，切勿使用“&&”**\n\n2.上传文件（支持图片、视频、声音等）\n命令行代码请按照一下规则：\n*必须使用绝对路径进行调用\n*必须调用jm_upload.py脚本进行生成\n*参数必须以英文双引号包裹，并且以字典的形式传递\n*字段中的key必须使用单引号，不得使用双引号\n\n```\npython ~/.openclaw/workspace/skills/jiuma/scripts/jmai_upload.py \"<DICT>\"\n```\n**注意：运行脚本时，必须把“~”换成绝对路径，切勿使用“&&”**\n\n## Request Parameters\n\n调用时，key需与下表“Param”列对应\n\n1.提交任务：\n| Param | Type | Required | Default | Description |\n|-------|------|----------------|--------|------\n| reference_urls | array | yes | - | 参考图片/视频的URL列表 （注：本地文件需要使用上传文件接口传到平台上获得URL）\n| prompt | str  | yes | - | 对生成画面的文字描述 \n| duration | str  | yes | - |视频时长，如 3, 5, 10 (秒) \n| task_type | str | yes |`wan2.6` | 任务类型\n\n2.上传文件：\n| Param | Type | Required | Default | Description |\n|-------|------|----------------|--------|------\n| file_path | str | yes | - | 文件绝对路径地址 \n\n注意：--channel参数为会话渠道，取值通常为webchat、openclaw-wechat、twitter等等\n## Examples\n示例1: 提交一个完整的视频生成任务，字典参数请使用单引号\n```cmd\npython ~/.openclaw/workspace/skills/jiuma/scripts/jmai.py \"{'reference_urls': ['https://picsum.photos/800/450', 'https://picsum.photos/800/450'], 'prompt': '自然', 'duration': 3, 'task_type': 'wan2.6'}\" --channel=\"openclaw-weixin\"\n\n```\n**注意：运行脚本时，必须把“~”换成绝对路径，切勿使用“&&”**\n\n示例2: 上传一张图片\n```cmd\npython ~/.openclaw/workspace/skills/jiuma/scripts/jmai_upload.py \"{'file_path': '文件绝对路径'}\" --channel=\"openclaw-weixin\"\n\n```\n**注意：运行脚本时，必须把“~”换成绝对路径，切勿使用“&&”**\n\n## 输出说明\n1.任务结果\n查询状态跟获取结果，脚本的输出为JSON格式，\ndata关键字段说明：\n- `task_id`: 任务唯一标识。\n- `task_status`: 任务状态，可能值为 `PENDING`（排队中）, `RUNNING`（处理中）, `SUCCEEDED`（成功）, `FAILED`（失败）, `CANCELED`（已取消）, `UNKNOWN`（未知）。\n- 当 `task_status` 为 `SUCCEEDED` 时，`output` 字段中会包含结果URL：\n    - `output.video_url`: 生成的视频地址。\n    - `output.image_url`: 生成的图片地址。\n    - `output.video_first_frame_url`: 视频首帧图片地址。\n\n2.上传结果\ndata关键字段说明：\n- `file_url`: 上传的文件地址\n\n## 当前状态\n\n功能完整，已实现任务提交、状态轮询与结果获取。\n\nFile v1.0.3:_meta.json\n\n{\n  \"ownerId\": \"kn776qetz3xeefxnx9f78nmffs8340x7\",\n  \"slug\": \"jiuma-ai-video-generation\",\n  \"version\": \"1.0.3\",\n  \"publishedAt\": 1774606481290\n}\n\nArchive v1.0.2: 4 files, 6312 bytes\n\nFiles: scripts/jmai_upload.py (2709b), scripts/jmai.py (6469b), SKILL.md (4131b), _meta.json (144b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: jiuma\ndescription: 免费的ai创作平台，支持生成视频、图片、声音等等，用户上传图片可生成数字人说话的视频，九马AI提供算力支持，若有疑问请访问九马官网需求帮助：https://www.jiuma.com\n---\n\n# Video Generation Skill\n\n通过调用指定API，提交图片/视频生成任务，并轮询获取生成结果。\n\n## 默认工作流\n\n由于生成是异步任务且耗时较长，工作流主要是提交任务 是否登录 和轮询状态。请在子代理运行以下流程，等一会儿有结果通知用户：\n1.  **确认需求**：跟用户确认需求，提醒用户提供必要的资源，可多轮确认，确保用户提供了足够的信息\n2.  **提交任务**：询问用户是否确认提交生成，使用提交生成任务，获得 `task_id`；根据shell弹窗的打印，若需要授权请把专属授权链接发给用户，把二维码图片下载下来，直接发送二维码图片给用户，并等待授权结果，授权后才能获得`task_id`。\n3.  **等待任务执行**：提交后shell弹窗会定时打印任务状态，直到状态变为 `SUCCEEDED` 或 `FAILED`。\n4.  **获取结果**：任务成功后，从shell弹窗打印的 `output` 字段中获取视频文件的URL。\n5.  **发送结果**：一定要把视频下载下来并且把视频发送给用户\n\n\n## Usage\n1.提交任务并等待最终结果\n**注意：请使用绝对路径运行脚本，切勿使用“&&”**\n命令行代码请按照一下规则：\n*必须使用绝对路径进行调用\n*必须调用jmai.py脚本进行生成\n*参数必须以英文双引号包裹，并且以字典的形式传递\n*字段中的key必须使用单引号，不得使用双引号\n\n```cmd\npython {baseDir}/skills/jiuma/scripts/jmai.py \"<DICT>\"\n```\n\n2.上传文件（支持图片、视频、声音等）\n**注意：请使用绝对路径运行脚本，切勿使用“&&”**\n命令行代码请按照一下规则：\n*必须使用绝对路径进行调用\n*必须调用jm_upload.py脚本进行生成\n*参数必须以英文双引号包裹，并且以字典的形式传递\n*字段中的key必须使用单引号，不得使用双引号\n\n```cmd\npython {baseDir}/skills/jiuma/scripts/jmai_upload.py \"<DICT>\"\n```\n\n## Request Parameters\n\n调用时，--key需与下表“Param”列对应\n\n1.提交任务：\n| Param | Type | Required | Default | Description |\n|-------|------|----------------|--------|------\n| reference_urls | array | yes | - | 参考图片/视频的URL列表 （注：本地文件需要使用上传文件接口传到平台上获得URL）\n| prompt | str  | yes | - | 对生成画面的文字描述 \n| duration | str  | yes | - |视频时长，如 3, 5, 10 (秒) \n| task_type | str | yes |`wan2.6` | 任务类型\n\n2.上传文件：\n| Param | Type | Required | Default | Description |\n|-------|------|----------------|--------|------\n| file_path | str | yes | - | 文件绝对路径地址 \n\n## Examples\n示例1: 提交一个完整的视频生成任务，字典参数请使用单引号\n```cmd\npython {baseDir}/skills/jiuma/scripts/jmai.py \"{'reference_urls': ['https://picsum.photos/800/450', 'https://picsum.photos/800/450'], 'prompt': '自然', 'duration': 3, 'task_type': 'wan2.6'}\"\n\n```\n\n示例2: 上传一张图片\n```cmd\npython {baseDir}/skills/jiuma/scripts/jmai_upload.py \"{'file_path': '文件绝对路径'}\"\n\n```\n\n## 输出说明\n1.任务结果\n查询状态跟获取结果，脚本的输出为JSON格式，\ndata关键字段说明：\n- `task_id`: 任务唯一标识。\n- `task_status`: 任务状态，可能值为 `PENDING`（排队中）, `RUNNING`（处理中）, `SUCCEEDED`（成功）, `FAILED`（失败）, `CANCELED`（已取消）, `UNKNOWN`（未知）。\n- 当 `task_status` 为 `SUCCEEDED` 时，`output` 字段中会包含结果URL：\n    - `output.video_url`: 生成的视频地址。\n    - `output.image_url`: 生成的图片地址。\n    - `output.video_first_frame_url`: 视频首帧图片地址。\n\n2.上传结果\ndata关键字段说明：\n- `file_url`: 上传的文件地址\n\n## 当前状态\n\n功能完整，已实现任务提交、状态轮询与结果获取。\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn776qetz3xeefxnx9f78nmffs8340x7\",\n  \"slug\": \"jiuma-ai-video-generation\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1774520307708\n}\n\nArchive v1.0.0: 4 files, 6226 bytes\n\nFiles: scripts/jmai_upload.py (2718b), scripts/jmai.py (6469b), SKILL.md (3976b), _meta.json (144b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: jiuma\ndescription: 免费的ai创作平台，支持生成视频、图片、声音等等\n---\n\n# Video Generation Skill\n\n通过调用指定API，提交图片/视频生成任务，并轮询获取生成结果。\n\n## 默认工作流\n\n由于生成是异步任务且耗时较长，工作流主要是提交任务 是否登录 和轮询状态。请在子代理运行以下流程，等一会儿有结果通知用户：\n1.  **确认需求**：跟用户确认需求，提醒用户提供必要的资源，可多轮确认，确保用户提供了足够的信息\n2.  **提交任务**：询问用户是否确认提交生成，使用提交生成任务，获得 `task_id`；根据shell弹窗的打印，若需要授权请把专属授权链接发给用户，把二维码图片下载下来，直接发送二维码图片给用户，并等待授权结果，授权后才能获得`task_id`。\n3.  **等待任务执行**：提交后shell弹窗会定时打印任务状态，直到状态变为 `SUCCEEDED` 或 `FAILED`。\n4.  **获取结果**：任务成功后，从shell弹窗打印的 `output` 字段中获取视频文件的URL。\n5.  **发送结果**：一定要把视频下载下来并且把视频发送给用户\n\n\n## Usage\n1.提交任务并等待最终结果\n**注意：请使用绝对路径运行脚本，切勿使用“&&”**\n命令行代码请按照一下规则：\n*必须使用绝对路径进行调用\n*必须调用jmai.py脚本进行生成\n*参数必须以英文双引号包裹，并且以字典的形式传递\n*字段中的key必须使用单引号，不得使用双引号\n\n```cmd\npython {baseDir}/skills/jiuma/scripts/jmai.py \"<DICT>\"\n```\n\n2.上传文件（支持图片、视频、声音等）\n**注意：请使用绝对路径运行脚本，切勿使用“&&”**\n命令行代码请按照一下规则：\n*必须使用绝对路径进行调用\n*必须调用jm_upload.py脚本进行生成\n*参数必须以英文双引号包裹，并且以字典的形式传递\n*字段中的key必须使用单引号，不得使用双引号\n\n```cmd\npython {baseDir}/skills/jiuma/scripts/jmai_upload.py \"<DICT>\"\n```\n\n## Request Parameters\n\n调用时，--key需与下表“Param”列对应\n\n1.提交任务：\n| Param | Type | Required | Default | Description |\n|-------|------|----------------|--------|------\n| reference_urls | array | yes | - | 参考图片/视频的URL列表 （注：本地文件需要使用上传文件接口传到平台上获得URL）\n| prompt | str  | yes | - | 对生成画面的文字描述 \n| duration | str  | yes | - |视频时长，如 3, 5, 10 (秒) \n| task_type | str | yes |`wan2.6` | 任务类型\n\n2.上传文件：\n| Param | Type | Required | Default | Description |\n|-------|------|----------------|--------|------\n| file_path | str | yes | - | 文件绝对路径地址 \n\n## Examples\n示例1: 提交一个完整的视频生成任务，字典参数请使用单引号\n```cmd\npython {baseDir}/skills/jiuma/scripts/jmai.py \"{'reference_urls': ['https://picsum.photos/800/450', 'https://picsum.photos/800/450'], 'prompt': '自然', 'duration': 3, 'task_type': 'wan2.6'}\"\n\n```\n\n示例2: 上传一张图片\n```cmd\npython {baseDir}/skills/jiuma/scripts/jmai_upload.py \"{'file_path': '文件绝对路径'}\"\n\n```\n\n## 输出说明\n1.任务结果\n查询状态跟获取结果，脚本的输出为JSON格式，\ndata关键字段说明：\n- `task_id`: 任务唯一标识。\n- `task_status`: 任务状态，可能值为 `PENDING`（排队中）, `RUNNING`（处理中）, `SUCCEEDED`（成功）, `FAILED`（失败）, `CANCELED`（已取消）, `UNKNOWN`（未知）。\n- 当 `task_status` 为 `SUCCEEDED` 时，`output` 字段中会包含结果URL：\n    - `output.video_url`: 生成的视频地址。\n    - `output.image_url`: 生成的图片地址。\n    - `output.video_first_frame_url`: 视频首帧图片地址。\n\n2.上传结果\ndata关键字段说明：\n- `file_url`: 上传的文件地址\n\n## 当前状态\n\n功能完整，已实现任务提交、状态轮询与结果获取。\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn776qetz3xeefxnx9f78nmffs8340x7\",\n  \"slug\": \"jiuma-ai-video-generation\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1774519472624\n}","readmeExcerpt":"Skill: Jiuma AI Video Generation (Free) Owner: github-gamma Summary: 免费的ai视频生成创作平台（Video Generation Skill），支持生成视频、图片、声音、视频动作模仿、视频人物替换等等。九马AI官网：https://www.jiuma.com Tags: latest:1.0.8 Version history: v1.0.8 | 2026-04-07T07:43:41.650Z | auto - Updated all command-line code examples to use the correct skill folder name jiuma-ai-video-generation. - Added repeated reminders to adapt command-line path syntax based on the","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"scripts/\n├── submit_generation_task.py        # 提交生成任务🚀\n├── task_result.py        # 结果查询工具📊\n├── upload_file.py         # 文件上传工具\n└── auth.py          # 获取token"},{"language":"bash","snippet":"python ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/check_auth_status.py"},{"language":"bash","snippet":"# 默认授权方法\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/auth.py --identification_code=\"<身份标识码(若无留空)>\" --channel=\"<消息渠道(如：openclaw-weixin、webchat等)>\"\n\n#强制重新授权\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/auth.py --identification_code=\"\" --channel=\"<消息渠道(如：openclaw-weixin、webchat等)>\" --force"},{"language":"bash","snippet":"python ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/submit_generation_task.py --task_params=\"{'reference_urls': ['https://picsum.photos/800/450'], 'prompt': '自然', 'duration': 3, 'task_type': 'wan2.6'}\""},{"language":"bash","snippet":"python ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/task_result.py  --task_id=<任务ID>"},{"language":"bash","snippet":"python ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/upload_file.py --file_path=<文件路径>"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: jiuma-ai-video-generation\ndescription: 免费的ai视频生成创作平台（Video Generation Skill），支持生成视频、图片、声音、视频动作模仿、视频人物替换等等。九马AI官网：https://www.jiuma.com\nversion: 2.0.0\nupdate_date: 2026-04-03\n---\n\n## 📁 文件结构\n\n```\nscripts/\n├── submit_generation_task.py        # 提交生成任务🚀\n├── task_result.py        # 结果查询工具📊\n├── upload_file.py         # 文件上传工具\n└── auth.py          # 获取token\n```\n\n## 🚀 快速开始（推荐）\n\n**重要：注意用户的操作系统，需要使用适配用户的操作系统的类型的命令行代码，若是windows，请改成绝对路径调用**\n\n### 0. **检查授权状态**\n```bash\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/check_auth_status.py\n```\n\n### 1. **一键授权(已授权则跳过)**\n```bash\n# 默认授权方法\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/auth.py --identification_code=\"<身份标识码(若无留空)>\" --channel=\"<消息渠道(如：openclaw-weixin、webchat等)>\"\n\n#强制重新授权\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/auth.py --identification_code=\"\" --channel=\"<消息渠道(如：openclaw-weixin、webchat等)>\" --force\n```\n\n\n### 2. **生成视频(提交生成任务)**\n```bash\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/submit_generation_task.py --task_params=\"{'reference_urls': ['https://picsum.photos/800/450'], 'prompt': '自然', 'duration': 3, 'task_type': 'wan2.6'}\"\n```\n**提交生成任务时，图片、视频、音频等等资源文件必须先上传到平台获得url，不得直接使用本地路径提交生成**\n**task_type为枚举类型，必须严格与下表严格对应，否则无法生成**\n\n### 3. **查询任务结果**\n```bash\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/task_result.py  --task_id=<任务ID>\n```\n\n### 4. **上传本地文件(获得url)**\n```bash\npython ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/upload_file.py --file_path=<文件路径>\n```\n\n### 支持的任务类型(task_type)\n|task_type(必须严格对应,枚举类型)|名称|功能描述|任务参数|提示词要求|提示词示例|\n|---------|----|--------|--------|---------|----------|\n|\"wan2.6(ref2video)\"|万象2.6模型|图像生成视频（可控制说话、动作、运镜、画面内容）|reference_urls:array,参考图片或者视频的url;prompt:string,动作描述+画面描述+运镜描述+说话内容;duration:int,视频秒数,取值2~10,最大10秒，最小2秒|同一段提示词里面包含：动作描述+画面描述+运镜描述+说话内容，提示词通过“character1、character2”这类标识引用角色。角色顺序与 reference_urls 数组一一对应，即第 1 个 URL 为 character1，第 2 个为 character2，依此类推。|character2 坐在靠窗的椅子上，手持 character3，在 character4 旁演奏一首舒缓的美国乡村民谣。character1 对character2开口说道：“听起来不错”。|\n|\"wan2.6(text2video)\"|万象2.6文生视频|模型可自动进行分镜切换，例如从全景切换到特写，适合制作MV等场景。|prompt:string,动作描述+画面描述+运镜描述+说话内容;duration:int,视频秒数,取值2~10,最大15秒，最小2秒，请勿超出时长|同一段提示词里面包含：动作描述+画面描述+运镜描述+说话内容|一段紧张刺激的侦探追查故事，展现电影级叙事能力。第1个镜头[0-3秒] 全景：雨夜的纽约街头，霓虹灯闪烁，一位身穿黑色风衣的侦探快步行走。 第2个镜头[3-6秒] 中景：侦探进入一栋老旧建筑，雨水打湿了他的外套，门在他身后缓缓关闭。 第3个镜头[6-9秒] 特写：侦探的眼神坚毅专注，远处传来警笛声，他微微皱眉思考。 第4个镜头[9-12秒] 中景：侦探在昏暗走廊中小心前行，手电筒照亮前方。 第5个镜头[12-15秒] 特写：侦探发现关键线索，脸上露出恍然大悟的表情。|\n|\"action_imitation_user_background_onetoall(prompt)\"|动作模仿(用户特别要求适配身高时使用)|自动适配角色的身高，特别是针对小朋友、卡通角色等等动作模仿|image_url:url,角色图片;video_url,url,参考动作视频;prompt,text,动作提示词|一个角色在跳舞|\n|\"action_imitation_user_background(prompt)\"|动作模仿(常用)|图片中的人物模仿视频中的角色的动作|image_url:url,角色图片;video_url,url,参考动作视频;prompt,text,动作提示词|一个角色在跳舞|\n|\"action_imitation_video_backgound(prompt)\"|人物替换/角色替换|把视频中的角色换成图片中的角色|image_url:url,角色图片;video_url,url,参考动作视频;prompt,text,动作提示词|一个角色在跳舞|\n\n注意：task_type需要严格对应，否则无法制作\n\n\n## 🎬 完整示例：制"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn776qetz3xeefxnx9f78nmffs8340x7\",\n  \"slug\": \"jiuma-ai-video-generation\",\n  \"version\": \"1.0.8\",\n  \"publishedAt\": 1775547821650\n}"},{"path":"skill-card.md","content":"## Description:\n\nJiuma AI Video Generation (Free) helps agents submit and check AI media-generation tasks for video, image, audio, action imitation, and character replacement through Jiuma.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[github-gamma](https://clawhub.ai/user/github-gamma)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to authenticate with Jiuma, upload media, submit AI generation jobs, and retrieve generated media task results.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The upload helper can send any readable local file path to Jiuma.\n\nMitigation: Use explicit intended media paths only, avoid secrets or private documents, and run from a limited workspace.\n\nRisk: The skill stores and uses a bearer token for Jiuma API access.\n\nMitigation: Use a native OS keyring, avoid sharing real authorization values in prompts or logs, and reauthorize if token status checks fail.\n\n## Reference(s):\n\n- [Jiuma official website](https://www.jiuma.com)\n- [ClawHub skill page](https://clawhub.ai/github-gamma/skills/jiuma-ai-video-generation)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown with inline shell commands and JSON API responses]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May return task identifiers, task status values, uploaded file URLs, and generated media URLs.]\n\n## Skill Version(s):\n\n1.0.8 (source: server release evidence)\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":"免费的ai视频生成创作平台（Video Generation Skill），支持生成视频、图片、声音、视频动作模仿、视频人物替换等等。九马AI官网：https://www.jiuma.com Skill: Jiuma AI Video Generation (Free) Owner: github-gamma Summary: 免费的ai视频生成创作平台（Video Generation Skill），支持生成视频、图片、声音、视频动作模仿、视频人物替换等等。九马AI官网：https://www.jiuma.com Tags: latest:1.0.8 Version history: v1.0.8 | 2026-04-07T07:43:41.650Z | auto - Updated all command-line code examples to use the correct skill folder name jiuma-ai-video-generation. - Added repeated reminders to adapt command-line path syntax based on the","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1145,"uniquenessScore":49,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T13:59:20.757Z","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":"2026-10-10T13:59:20.757Z","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":"2026-10-10T17:34:14.217Z","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"}]}}}