[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MDV94AVBAS50XSQRG9DJJ6":3,"skill-same:01M6MDV94AVBAS50XSQRG9DJJ6":62},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":27,"linkOnly":28,"markdownContent":29,"markdownBody":30,"frontMatter":31,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":37,"ownerHtmlUrl":38,"ownerBlogUrl":39,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M6MDV94AVBAS50XSQRG9DJJ6","omnimodal",null,"为纯文本主模型提供多模态能力：识别图片、视频、音频，并生成图片、视频、音频。遇到图片路径、截图、UI\u002F网页截图、图表、错误弹窗、OCR、音频\u002F视频理解、文生图\u002F文生视频\u002FTTS 或任何需要多模态能力的任务时自动启用。","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FZXY1240\u002Fread-image\u002Fskills\u002Fomnimodal\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26],"image","ui","ocr","tts","视频","生成","文本","图表","2026-11-10 10:12:30",false,"---\nname: omnimodal\ndescription: 为纯文本主模型提供多模态能力：识别图片、视频、音频，并生成图片、视频、音频。遇到图片路径、截图、UI\u002F网页截图、图表、错误弹窗、OCR、音频\u002F视频理解、文生图\u002F文生视频\u002FTTS 或任何需要多模态能力的任务时自动启用。\n---\n\n# Omnimodal\n\n主模型使用纯文本模型时，只要任务需要看媒体、听媒体或生成媒体，就自动调用 `omnimodal_*` MCP 工具，不要等用户手动开启，也不要自行假设媒体内容。\n\n## 自动触发\n\n- 用户消息中有图片、视频、音频路径或附件。\n- 任务包含 OCR、截图、UI、设计稿、图表、表格图片、错误弹窗、音频\u002F视频理解。\n- 主任务不是媒体任务，但为了完成它必须知道媒体内容。\n- 用户要求生成图片、视频、语音、音乐、声音克隆或声音设计。\n\n## 识别工具\n\n- 单张图片：`omnimodal_recognize_image(image, task, mode)`。`image` 支持本地路径、`data:` URL 和可解码的 base64。\n- 多张图片：`omnimodal_recognize_images_batch(images, task, mode, max_workers)`。\n- 单个视频：`omnimodal_recognize_video(video, task, mode)`。\n- 批量视频：`omnimodal_recognize_videos_batch(videos, task, mode, max_workers)`。\n- 单个音频：`omnimodal_recognize_audio(audio, task, mode)`，长音频自动走 ASR 转写。\n- 批量音频：`omnimodal_recognize_audios_batch(audios, task, mode, max_workers)`。\n- 剪贴板图片：`omnimodal_read_clipboard_image(task, mode)`。\n- 拖拽媒体：`omnimodal_read_dragged_image` \u002F `omnimodal_read_dragged_video` \u002F `omnimodal_read_dragged_audio`。\n\n网页动态内容先调用 `omnimodal_capture_page(url, actions, viewport, output_dir)`，再把截图路径交给批量识别。Windows 全屏、主屏或指定窗口截图先调用 `omnimodal_list_windows()`，再调用 `omnimodal_capture_windows(mode, window, output_dir)`。\n\n## 生成工具\n\n- `omnimodal_generate_image(prompt, tier, size, n, wait, confirm)`：文生图。\n- `omnimodal_generate_video(prompt, tier, duration, resolution, wait, confirm)`：文生视频。\n- `omnimodal_generate_video_from_image(image, prompt, tier, duration, resolution, wait, confirm)`：图生视频。\n- `omnimodal_edit_video(video, prompt, tier, duration, resolution, reference_image, wait, confirm)`：视频编辑。\n- `omnimodal_generate_audio(text, voice, tier, kind, preview_text, wait, confirm)`：TTS、声音克隆、声音设计、音乐生成。\n- `omnimodal_get_task_result(task_id)`：查询异步任务。\n\n**费用确认是强制规则**：生成工具必须在调用时传 `confirm=true`；否则返回预计费用且不实际调用付费接口。不要绕过确认。\n\n**生成后不要自动识别验证**：用户要求生成图片、视频或音频时，只调用对应生成工具并直接返回结果路径；不要为了“检查生成效果”再自动调用识别工具。只有用户明确要求检查生成结果、或生成结果明显异常时才允许追加识别。\n\n## mode 档位\n\n识别档位统一为：\n\n- `ocr`：仅图片文字提取。\n- `quick`：快速识别，关闭思考，短输出。\n- `standard`：标准提取，默认。\n- `full`：完整提取，不限制输出。\n- `quick_analysis` \u002F `balanced_analysis` \u002F `deep_analysis`：逐步加强的分析档。\n\n档位可通过插件目录 `config\u002Fprofiles.json` 覆盖；本机私有覆盖写在 `config\u002Flocal.json`，不会进入 Git。\n\n## 配置\n\nAPI Key 只写在插件根目录 `.env`：\n\n```powershell\nOMNIMODAL_API_KEY=你的千问或DashScope API Key\nOMNIMODAL_PROVIDER=dashscope\nOMNIMODAL_BASE_URL=https:\u002F\u002Fdashscope.aliyuncs.com\u002Fcompatible-mode\u002Fv1\nOMNIMODAL_IMAGE_MODEL=qwen3.7-flash\nOMNIMODAL_VIDEO_MODEL=qwen3.7-flash\nOMNIMODAL_AUDIO_MODEL_STANDARD=qwen3.5-omni-flash\nOMNIMODAL_AUDIO_MODEL_PRO=qwen3.5-omni-plus\n```\n\n可切换厂商：\n\n- `OMNIMODAL_PROVIDER=zai`：GLM 图片\u002F视频\u002F音频理解、GLM 文生图、GLM 文生视频和 GLM ASR。\n- `OMNIMODAL_PROVIDER=openai_compatible`：识别和 OpenAI Images 风格图片生成；视频\u002F音频生成会返回明确的不支持提示。\n\n模型目录、档位、超时、输出目录等默认值位于 `config\u002Fmodel_catalog.json` 和 `config\u002Fprofiles.json`，均可用 `config\u002Flocal.json` 覆盖。\n\n## Claude 桌面端\n\nClaude 桌面端跨窗口拖入的媒体不落盘。图片复制进剪贴板后调用 `omnimodal_read_clipboard_image`；视频和音频请用户保存为文件后提供明确路径。禁止扫描 `Temp`、按时间戳猜文件，或输出“很可能\u002F可能是你刚粘贴的图片”。\n\n## 命令行兜底\n\n```powershell\nuv run --project \u003C插件根目录> omnimodal-recognize --image \u003C图片路径> --task \"\u003C任务>\" --mode standard\nuv run --project \u003C插件根目录> omnimodal-recognize --video \u003C视频路径> --task \"\u003C任务>\" --mode standard\nuv run --project \u003C插件根目录> omnimodal-recognize --audio \u003C音频路径> --task \"\u003C任务>\" --mode standard\n```\n\n生成服务仅支持 stdio MCP 模式；异步任务超时后返回 `task_id`，可稍后查询。\n","# Omnimodal\n\n主模型使用纯文本模型时，只要任务需要看媒体、听媒体或生成媒体，就自动调用 `omnimodal_*` MCP 工具，不要等用户手动开启，也不要自行假设媒体内容。\n\n## 自动触发\n\n- 用户消息中有图片、视频、音频路径或附件。\n- 任务包含 OCR、截图、UI、设计稿、图表、表格图片、错误弹窗、音频\u002F视频理解。\n- 主任务不是媒体任务，但为了完成它必须知道媒体内容。\n- 用户要求生成图片、视频、语音、音乐、声音克隆或声音设计。\n\n## 识别工具\n\n- 单张图片：`omnimodal_recognize_image(image, task, mode)`。`image` 支持本地路径、`data:` URL 和可解码的 base64。\n- 多张图片：`omnimodal_recognize_images_batch(images, task, mode, max_workers)`。\n- 单个视频：`omnimodal_recognize_video(video, task, mode)`。\n- 批量视频：`omnimodal_recognize_videos_batch(videos, task, mode, max_workers)`。\n- 单个音频：`omnimodal_recognize_audio(audio, task, mode)`，长音频自动走 ASR 转写。\n- 批量音频：`omnimodal_recognize_audios_batch(audios, task, mode, max_workers)`。\n- 剪贴板图片：`omnimodal_read_clipboard_image(task, mode)`。\n- 拖拽媒体：`omnimodal_read_dragged_image` \u002F `omnimodal_read_dragged_video` \u002F `omnimodal_read_dragged_audio`。\n\n网页动态内容先调用 `omnimodal_capture_page(url, actions, viewport, output_dir)`，再把截图路径交给批量识别。Windows 全屏、主屏或指定窗口截图先调用 `omnimodal_list_windows()`，再调用 `omnimodal_capture_windows(mode, window, output_dir)`。\n\n## 生成工具\n\n- `omnimodal_generate_image(prompt, tier, size, n, wait, confirm)`：文生图。\n- `omnimodal_generate_video(prompt, tier, duration, resolution, wait, confirm)`：文生视频。\n- `omnimodal_generate_video_from_image(image, prompt, tier, duration, resolution, wait, confirm)`：图生视频。\n- `omnimodal_edit_video(video, prompt, tier, duration, resolution, reference_image, wait, confirm)`：视频编辑。\n- `omnimodal_generate_audio(text, voice, tier, kind, preview_text, wait, confirm)`：TTS、声音克隆、声音设计、音乐生成。\n- `omnimodal_get_task_result(task_id)`：查询异步任务。\n\n**费用确认是强制规则**：生成工具必须在调用时传 `confirm=true`；否则返回预计费用且不实际调用付费接口。不要绕过确认。\n\n**生成后不要自动识别验证**：用户要求生成图片、视频或音频时，只调用对应生成工具并直接返回结果路径；不要为了“检查生成效果”再自动调用识别工具。只有用户明确要求检查生成结果、或生成结果明显异常时才允许追加识别。\n\n## mode 档位\n\n识别档位统一为：\n\n- `ocr`：仅图片文字提取。\n- `quick`：快速识别，关闭思考，短输出。\n- `standard`：标准提取，默认。\n- `full`：完整提取，不限制输出。\n- `quick_analysis` \u002F `balanced_analysis` \u002F `deep_analysis`：逐步加强的分析档。\n\n档位可通过插件目录 `config\u002Fprofiles.json` 覆盖；本机私有覆盖写在 `config\u002Flocal.json`，不会进入 Git。\n\n## 配置\n\nAPI Key 只写在插件根目录 `.env`：\n\n```powershell\nOMNIMODAL_API_KEY=你的千问或DashScope API Key\nOMNIMODAL_PROVIDER=dashscope\nOMNIMODAL_BASE_URL=https:\u002F\u002Fdashscope.aliyuncs.com\u002Fcompatible-mode\u002Fv1\nOMNIMODAL_IMAGE_MODEL=qwen3.7-flash\nOMNIMODAL_VIDEO_MODEL=qwen3.7-flash\nOMNIMODAL_AUDIO_MODEL_STANDARD=qwen3.5-omni-flash\nOMNIMODAL_AUDIO_MODEL_PRO=qwen3.5-omni-plus\n```\n\n可切换厂商：\n\n- `OMNIMODAL_PROVIDER=zai`：GLM 图片\u002F视频\u002F音频理解、GLM 文生图、GLM 文生视频和 GLM ASR。\n- `OMNIMODAL_PROVIDER=openai_compatible`：识别和 OpenAI Images 风格图片生成；视频\u002F音频生成会返回明确的不支持提示。\n\n模型目录、档位、超时、输出目录等默认值位于 `config\u002Fmodel_catalog.json` 和 `config\u002Fprofiles.json`，均可用 `config\u002Flocal.json` 覆盖。\n\n## Claude 桌面端\n\nClaude 桌面端跨窗口拖入的媒体不落盘。图片复制进剪贴板后调用 `omnimodal_read_clipboard_image`；视频和音频请用户保存为文件后提供明确路径。禁止扫描 `Temp`、按时间戳猜文件，或输出“很可能\u002F可能是你刚粘贴的图片”。\n\n## 命令行兜底\n\n```powershell\nuv run --project \u003C插件根目录> omnimodal-recognize --image \u003C图片路径> --task \"\u003C任务>\" --mode standard\nuv run --project \u003C插件根目录> omnimodal-recognize --video \u003C视频路径> --task \"\u003C任务>\" --mode standard\nuv run --project \u003C插件根目录> omnimodal-recognize --audio \u003C音频路径> --task \"\u003C任务>\" --mode standard\n```\n\n生成服务仅支持 stdio MCP 模式；异步任务超时后返回 `task_id`，可稍后查询。\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002FZXY1240\u002Fread-image\u002Fskills\u002Fomnimodal",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill omnimodal",{"tool":48,"command":49},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill omnimodal",{"tool":51,"command":52},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill omnimodal","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FZXY1240\u002Fread-image\u002Fskills\u002Fomnimodal\u002FSKILL.md",true,[56],{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"agents\u002Fopenai.yaml","REFERENCE","参考文档",159,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FZXY1240\u002Fread-image\u002Fskills\u002Fomnimodal\u002Fagents\u002Fopenai.yaml",[63,73,81,89,97,105],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":68,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":72},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":77,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":72},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":85,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":72},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":93,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":72},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":101,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":72},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":109,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":72},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]