[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78XD5FE5YDDAVSCSP3TZWDW":3,"skill-same:01M78XD5FE5YDDAVSCSP3TZWDW":67},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M78XD5FE5YDDAVSCSP3TZWDW","multimodal-i-o",null,"Use GenAI Processors audio, video, PDF, web, file, and speech connectors.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgenai-processors\u002Fsub-skills\u002Fmultimodal-i-o\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: multimodal-i-o\ndescription: \"Use GenAI Processors audio, video, PDF, web, file, and speech connectors.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# Multimodal I\u002FO\n\nUse this sub-skill when the task is about getting content into or out of a\nprocessor pipeline: microphones, speakers, cameras, screens, PDFs, URLs,\nGitHub, Google Drive, files, speech recognition, speech synthesis, VAD, and\nrealtime media flow.\n\n## Read when\n\n- The task names `PyAudioIn`, `PyAudioOut`, `VideoIn`, `AudioToWav`, `Vad`,\n  `SpeechToText`, `TextToSpeech`, `PDFExtract`, `UrlFetch`, `GithubProcessor`,\n  `Drive`, `RateLimitAudio`, `EventDetection`, `add_timestamps`, `to_timestamp`, or `Window`.\n- The task is about MIME types, audio sample rates, video frames, PDFs, URLs,\n  files, or Google Workspace documents.\n- The task needs a realtime audio\u002Fvideo pipeline before or after a model\n  wrapper.\n- The task needs optional dependency or device troubleshooting.\n\n## Boundaries\n\nThis sub-skill owns connectors and media\u002Fdocument processing. It does not own\nmodel selection or function-calling strategy; use `..\u002Fmodel-backends\u002F` for\nthat. It does not own complete app\u002Fdemo layout; use `..\u002Fexamples-and-apps\u002F` for\nfull CLIs and AI Studio applets.\n\n## Workflow checklist\n\n1. Identify source modality: terminal text, audio, camera\u002Fscreen frames, file\n   glob, PDF bytes, URL, GitHub URL, Drive doc\u002Fsheet\u002Fslide, or tool output.\n2. Confirm MIME type and substream expectations before composing with model\n   processors.\n3. Verify optional imports with `scripts\u002Fsmoke_io.py` before using devices or\n   credentials.\n4. For audio\u002Fvideo, check device permissions and prefer headphones unless using\n   browser echo cancellation.\n5. For Google Speech\u002FTTS or Drive, validate credentials and project\u002Fservice\n   setup before running full pipelines.\n6. For URLs\u002FGitHub\u002FPDFs, separate safe parser\u002Fimport smoke from network or file\n   reads.\n7. When combining with live\u002Frealtime models, cross-check trigger and substream\n   behavior in `..\u002Fmodel-backends\u002F`.\n\n## References and scripts\n\n- `references\u002Fapi-reference.md` lists connector classes and processor roles.\n- `references\u002Fworkflows.md` provides audio, video, PDF, URL, Drive\u002FGitHub, and\n  realtime media patterns.\n- `references\u002Ftroubleshooting.md` covers PortAudio, device permissions,\n  Google Cloud auth, PDF rendering, OpenCV\u002FAV, and web fetch failures.\n- `scripts\u002Fsmoke_io.py` imports optional I\u002FO modules without opening devices,\n  making network requests, or requiring credentials.\n\n## Native evidence anchors\n\nEvidence comes from source modules under `genai_processors\u002Fcore\u002F`, docs under\n`documentation\u002Fdocs\u002Fdevelopment\u002F` and `documentation\u002Fdocs\u002Fconcepts\u002Frealtime.md`,\nand tests including `audio_test.py`, `rate_limit_audio_test.py`,\n`speech_to_text_test.py`, `text_to_speech_test.py`, `vad_test.py`,\n`video_test.py`, `pdf_test.py`, `web_test.py`, `github_test.py`,\n`drive_test.py`, `filesystem_test.py`, `event_detection_test.py`,\n`timestamp_test.py`, and `window_test.py`.\n\n## Usability checkpoints\n\nA good answer using this sub-skill should:\n\n- Name exact optional packages and environment variables before runnable code.\n- Avoid opening microphones, speakers, cameras, browsers, or remote services in\n  a smoke check.\n- Preserve non-text parts until a downstream processor intentionally converts\n  them.\n- Include concrete MIME types and substream names when they affect routing.\n- Route model-specific or applet-specific follow-up work to the proper sibling\n  sub-skill.\n","# Multimodal I\u002FO\n\nUse this sub-skill when the task is about getting content into or out of a\nprocessor pipeline: microphones, speakers, cameras, screens, PDFs, URLs,\nGitHub, Google Drive, files, speech recognition, speech synthesis, VAD, and\nrealtime media flow.\n\n## Read when\n\n- The task names `PyAudioIn`, `PyAudioOut`, `VideoIn`, `AudioToWav`, `Vad`,\n  `SpeechToText`, `TextToSpeech`, `PDFExtract`, `UrlFetch`, `GithubProcessor`,\n  `Drive`, `RateLimitAudio`, `EventDetection`, `add_timestamps`, `to_timestamp`, or `Window`.\n- The task is about MIME types, audio sample rates, video frames, PDFs, URLs,\n  files, or Google Workspace documents.\n- The task needs a realtime audio\u002Fvideo pipeline before or after a model\n  wrapper.\n- The task needs optional dependency or device troubleshooting.\n\n## Boundaries\n\nThis sub-skill owns connectors and media\u002Fdocument processing. It does not own\nmodel selection or function-calling strategy; use `..\u002Fmodel-backends\u002F` for\nthat. It does not own complete app\u002Fdemo layout; use `..\u002Fexamples-and-apps\u002F` for\nfull CLIs and AI Studio applets.\n\n## Workflow checklist\n\n1. Identify source modality: terminal text, audio, camera\u002Fscreen frames, file\n   glob, PDF bytes, URL, GitHub URL, Drive doc\u002Fsheet\u002Fslide, or tool output.\n2. Confirm MIME type and substream expectations before composing with model\n   processors.\n3. Verify optional imports with `scripts\u002Fsmoke_io.py` before using devices or\n   credentials.\n4. For audio\u002Fvideo, check device permissions and prefer headphones unless using\n   browser echo cancellation.\n5. For Google Speech\u002FTTS or Drive, validate credentials and project\u002Fservice\n   setup before running full pipelines.\n6. For URLs\u002FGitHub\u002FPDFs, separate safe parser\u002Fimport smoke from network or file\n   reads.\n7. When combining with live\u002Frealtime models, cross-check trigger and substream\n   behavior in `..\u002Fmodel-backends\u002F`.\n\n## References and scripts\n\n- `references\u002Fapi-reference.md` lists connector classes and processor roles.\n- `references\u002Fworkflows.md` provides audio, video, PDF, URL, Drive\u002FGitHub, and\n  realtime media patterns.\n- `references\u002Ftroubleshooting.md` covers PortAudio, device permissions,\n  Google Cloud auth, PDF rendering, OpenCV\u002FAV, and web fetch failures.\n- `scripts\u002Fsmoke_io.py` imports optional I\u002FO modules without opening devices,\n  making network requests, or requiring credentials.\n\n## Native evidence anchors\n\nEvidence comes from source modules under `genai_processors\u002Fcore\u002F`, docs under\n`documentation\u002Fdocs\u002Fdevelopment\u002F` and `documentation\u002Fdocs\u002Fconcepts\u002Frealtime.md`,\nand tests including `audio_test.py`, `rate_limit_audio_test.py`,\n`speech_to_text_test.py`, `text_to_speech_test.py`, `vad_test.py`,\n`video_test.py`, `pdf_test.py`, `web_test.py`, `github_test.py`,\n`drive_test.py`, `filesystem_test.py`, `event_detection_test.py`,\n`timestamp_test.py`, and `window_test.py`.\n\n## Usability checkpoints\n\nA good answer using this sub-skill should:\n\n- Name exact optional packages and environment variables before runnable code.\n- Avoid opening microphones, speakers, cameras, browsers, or remote services in\n  a smoke check.\n- Preserve non-text parts until a downstream processor intentionally converts\n  them.\n- Include concrete MIME types and substream names when they affect routing.\n- Route model-specific or applet-specific follow-up work to the proper sibling\n  sub-skill.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fgenai-processors\u002Fsub-skills\u002Fmultimodal-i-o",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill multimodal-i-o",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill multimodal-i-o",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill multimodal-i-o","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgenai-processors\u002Fsub-skills\u002Fmultimodal-i-o\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",3452,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgenai-processors\u002Fsub-skills\u002Fmultimodal-i-o\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",2864,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgenai-processors\u002Fsub-skills\u002Fmultimodal-i-o\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fworkflows.md",2908,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgenai-processors\u002Fsub-skills\u002Fmultimodal-i-o\u002Freferences\u002Fworkflows.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fsmoke_io.py","SCRIPT","脚本",1348,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgenai-processors\u002Fsub-skills\u002Fmultimodal-i-o\u002Fscripts\u002Fsmoke_io.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]