[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FA3Z7BS2TH1D29VSC4W9P7":3,"skill-same:01M7FA3Z7BS2TH1D29VSC4W9P7":67},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":48},"01M7FA3Z7BS2TH1D29VSC4W9P7","visual-dialogue-tools",null,"Route image upload, click-mask segmentation, OCR, Husky VQA\u002Fcaptioning, inpainting, replacement, and ControlNet image workflows.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fintern-gpt\u002Fsub-skills\u002Fvisual-dialogue-tools\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: visual-dialogue-tools\ndescription: \"Route image upload, click-mask segmentation, OCR, Husky\n  VQA\u002Fcaptioning, inpainting, replacement, and ControlNet image workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Visual Dialogue Tools\n\nUse this sub-skill when the task is about uploading an image, clicking a region, asking about text or scene content, removing or replacing a masked object, saving a mask for later use, or generating\u002Fediting an image from segmentation, canny, scribble, depth, pose, line, or normal control maps.\n\n## Route elsewhere\n\n- App launch\u002Fload strings, tab gating, certificates, and service-level model loading belong in `..\u002Fapp-deployment\u002FSKILL.md`.\n- ImageBind audio\u002Fthermal generation and DragGAN point editing belong in `..\u002Fcross-modal-generation\u002FSKILL.md`.\n- Video upload, captioning, action recognition, dense captioning, and TikTok-style clip generation belong in `..\u002Fvideo-understanding\u002FSKILL.md`.\n\n## Read first\n\n- Read [references\u002Fcontroller-state.md](references\u002Fcontroller-state.md) for the ConversationBot state model, upload flow, click-mask handling, memory updates, and path recovery rules.\n- Read [references\u002Fimage-tool-reference.md](references\u002Fimage-tool-reference.md) when you need the exact tool names, comma-separated input grammar, checkpoint expectations, or output filename conventions.\n- Read [references\u002Fimage-workflows.md](references\u002Fimage-workflows.md) for end-to-end recipes such as Pick, OCR on a clicked region, remove\u002Freplace, save-mask reuse, and control-map generation.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when a tool is unloaded, a mask is empty, parent-image recovery fails, a checkpoint is missing, OCR returns no text, or the prompt grammar is ambiguous.\n- Run [scripts\u002Fvalidate_mask_inputs.py](scripts\u002Fvalidate_mask_inputs.py) before handing a candidate image\u002Fmask pair to removal, replacement, or OCR workflows; it checks file existence, format, dimensions, non-empty masks, and an optional parent relationship.\n\n## Operating notes\n\n- Treat `state` as the chat transcript and `user_state[0]` as the live session cache.\n- Uploaded images seed both caption and OCR memory; clicked masks are saved under `image\u002F` with a recoverable parent anchor.\n- Use OCR when the user cares about exact characters; use HuskyVQA when the user cares about scene semantics inside a selected region.\n- Removal uses the inpainting path; replacement uses the masked-object replacement path; both expect the image path first and the mask path second.\n- Many models are e-mode aware and move to CPU between calls, so do not assume GPU residency across turns.\n","# Visual Dialogue Tools\n\nUse this sub-skill when the task is about uploading an image, clicking a region, asking about text or scene content, removing or replacing a masked object, saving a mask for later use, or generating\u002Fediting an image from segmentation, canny, scribble, depth, pose, line, or normal control maps.\n\n## Route elsewhere\n\n- App launch\u002Fload strings, tab gating, certificates, and service-level model loading belong in `..\u002Fapp-deployment\u002FSKILL.md`.\n- ImageBind audio\u002Fthermal generation and DragGAN point editing belong in `..\u002Fcross-modal-generation\u002FSKILL.md`.\n- Video upload, captioning, action recognition, dense captioning, and TikTok-style clip generation belong in `..\u002Fvideo-understanding\u002FSKILL.md`.\n\n## Read first\n\n- Read [references\u002Fcontroller-state.md](references\u002Fcontroller-state.md) for the ConversationBot state model, upload flow, click-mask handling, memory updates, and path recovery rules.\n- Read [references\u002Fimage-tool-reference.md](references\u002Fimage-tool-reference.md) when you need the exact tool names, comma-separated input grammar, checkpoint expectations, or output filename conventions.\n- Read [references\u002Fimage-workflows.md](references\u002Fimage-workflows.md) for end-to-end recipes such as Pick, OCR on a clicked region, remove\u002Freplace, save-mask reuse, and control-map generation.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when a tool is unloaded, a mask is empty, parent-image recovery fails, a checkpoint is missing, OCR returns no text, or the prompt grammar is ambiguous.\n- Run [scripts\u002Fvalidate_mask_inputs.py](scripts\u002Fvalidate_mask_inputs.py) before handing a candidate image\u002Fmask pair to removal, replacement, or OCR workflows; it checks file existence, format, dimensions, non-empty masks, and an optional parent relationship.\n\n## Operating notes\n\n- Treat `state` as the chat transcript and `user_state[0]` as the live session cache.\n- Uploaded images seed both caption and OCR memory; clicked masks are saved under `image\u002F` with a recoverable parent anchor.\n- Use OCR when the user cares about exact characters; use HuskyVQA when the user cares about scene semantics inside a selected region.\n- Removal uses the inpainting path; replacement uses the masked-object replacement path; both expect the image path first and the mask path second.\n- Many models are e-mode aware and move to CPU between calls, so do not assume GPU residency across turns.\n",{"name":5,"license":24,"metadata":25,"description":7,"disable-model-invocation":27},"Apache 2.0",{"disco-role":26},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Fintern-gpt\u002Fsub-skills\u002Fvisual-dialogue-tools",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":27},[38,41,44],{"tool":39,"command":40},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill visual-dialogue-tools",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill visual-dialogue-tools",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill visual-dialogue-tools","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fintern-gpt\u002Fsub-skills\u002Fvisual-dialogue-tools\u002FSKILL.md",[49,55,59,63],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fcontroller-state.md","REFERENCE","参考文档",6737,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fintern-gpt\u002Fsub-skills\u002Fvisual-dialogue-tools\u002Freferences\u002Fcontroller-state.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fimage-tool-reference.md",6414,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fintern-gpt\u002Fsub-skills\u002Fvisual-dialogue-tools\u002Freferences\u002Fimage-tool-reference.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fimage-workflows.md",4408,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fintern-gpt\u002Fsub-skills\u002Fvisual-dialogue-tools\u002Freferences\u002Fimage-workflows.md",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Ftroubleshooting.md",4462,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fintern-gpt\u002Fsub-skills\u002Fvisual-dialogue-tools\u002Freferences\u002Ftroubleshooting.md",[68,76,81,88,95,102],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":77,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\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":72,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]