[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78AMYAMK4THM2AB14Q0GYF2":3,"skill-same:01M78AMYAMK4THM2AB14Q0GYF2":81},{"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":36,"commitSha":37,"skillDirectory":38,"forksCount":14,"repositoryHtmlUrl":39,"repositoryHomepageUrl":40,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":43,"updatedAt":44,"install":45,"resources":58},"01M78AMYAMK4THM2AB14Q0GYF2","tao-analyze-gaps-vlm-bcq",null,"Extract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes\u002Fno) predictions. Use when the user asks to \"analyze VLM BCQ gaps\", \"extract VLM false positives and false negatives\", or identify failure cases from a predictions JSON for DEFT root-cause analysis on a binary-classification VLM workflow.","Solizardking\u002Fskillhub-main","Solizardking","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F108096810?v=4","01M786KDB10AYV042N0F9BD5B5","Clawd","01M786NYYXSZK1D05WM8JQPC48",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fnvidia\u002Ftao-analyze-gaps-vlm-bcq\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: tao-analyze-gaps-vlm-bcq\ndescription: Extract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes\u002Fno) predictions.\n  Use when the user asks to \"analyze VLM BCQ gaps\", \"extract VLM false positives and false negatives\", or identify failure\n  cases from a predictions JSON for DEFT root-cause analysis on a binary-classification VLM workflow.\nlicense: Apache-2.0\ncompatibility: Requires docker + nvidia-container-toolkit.\nmetadata:\n  author: NVIDIA Corporation\n  version: \"0.1.0\"\nallowed-tools: Read Bash\ntags:\n- gap-analysis\n- rcca\n- vlm\n- evaluation\n- false-positive\n- false-negative\n---\n\n# VLM Binary Classification Gap Analysis\n\nReads a VLM predictions JSON, compares each model response against ground truth, and writes FP\u002FFN failure cases to a JSONL file with a summary report.\n\n## Purpose\n\nAfter running a VLM on a binary yes\u002Fno evaluation task, the predictions need to be compared against ground truth to identify failure cases. This skill produces a structured list of FP (false positive) and FN (false negative) samples that downstream RCCA stages (e.g., cosmos generation, root cause analysis) consume to drive a DEFT iteration.\n\n## Usage\n\nInvoke the `vlm_bcq` action inside the TAO Toolkit data services container with Hydra-style key=value overrides:\n\n```bash\ngap_analysis vlm_bcq \\\n  predictions_json=\u002Fpath\u002Fto\u002Fresults.json \\\n  results_dir=\u002Fpath\u002Fto\u002Foutput\u002Fgaps\n```\n\nInclude `videos_dir` when `video_id` values in the predictions are relative paths:\n\n```bash\ngap_analysis vlm_bcq \\\n  predictions_json=\u002Fpath\u002Fto\u002Fresults.json \\\n  results_dir=\u002Fpath\u002Fto\u002Foutput\u002Fgaps \\\n  videos_dir=\u002Fpath\u002Fto\u002Fvideos\u002Froot\n```\n\nAfter the run, surface the FP\u002FFN counts from `kpi_gaps_report.txt` and point downstream stages at `kpi_gaps.jsonl`.\n\n## Inputs\n\n- **predictions_json**: Path to predictions JSON file. Must be a JSON array where each item has `video_id`, `response`, and `gt` fields. `response` and `gt` are parsed with word-boundary matching — `'yes'` or `'no'` anywhere in the string is recognized. Samples where both or neither are present are skipped with a warning.\n- **videos_dir** (optional): Base directory for resolving relative `video_id` paths. If omitted, `video_id` values are used as absolute paths.\n\n**Predictions JSON format:**\n```json\n[\n  {\n    \"video_id\": \"\u002Fpath\u002Fto\u002Fvideo.mp4\",\n    \"response\": \"Yes, there is a collision.\",\n    \"gt\": \"B. No\",\n    \"question\": \"Is there a collision?\"\n  }\n]\n```\n\n## Outputs\n\n- **kpi_gaps.jsonl**: One JSON object per line for each FP\u002FFN case. Fields: `video_id` (absolute path), `error_type` (`FP` or `FN`), `question`, `ground_truth`, `response`.\n- **kpi_gaps_report.txt**: Human-readable table with total FP\u002FFN counts.\n\nIf no gaps are found, no files are written and a message is logged.\n\n## Key Parameters\n\n| Parameter | Required | Description |\n|-----------|----------|-------------|\n| predictions_json | Yes | Path to predictions JSON file |\n| results_dir | Yes | Output directory; created if it does not exist |\n| videos_dir | No | Base directory for resolving relative `video_id` paths |\n\n## Error Patterns\n\n| Error | Cause | Fix |\n|-------|-------|-----|\n| `FileNotFoundError` | `predictions_json` does not exist | Check the path |\n| `ValueError: must be a JSON array` | Predictions file is not a list | Wrap predictions in `[...]` |\n| `ValueError: missing 'gt'\u002F'response'\u002F'video_id'` | A prediction item is missing a required field | Inspect and fix the predictions JSON |\n| Samples silently skipped | `response` or `gt` contains both or neither 'yes'\u002F'no' | Check logs for warnings; inspect those samples |\n","# VLM Binary Classification Gap Analysis\n\nReads a VLM predictions JSON, compares each model response against ground truth, and writes FP\u002FFN failure cases to a JSONL file with a summary report.\n\n## Purpose\n\nAfter running a VLM on a binary yes\u002Fno evaluation task, the predictions need to be compared against ground truth to identify failure cases. This skill produces a structured list of FP (false positive) and FN (false negative) samples that downstream RCCA stages (e.g., cosmos generation, root cause analysis) consume to drive a DEFT iteration.\n\n## Usage\n\nInvoke the `vlm_bcq` action inside the TAO Toolkit data services container with Hydra-style key=value overrides:\n\n```bash\ngap_analysis vlm_bcq \\\n  predictions_json=\u002Fpath\u002Fto\u002Fresults.json \\\n  results_dir=\u002Fpath\u002Fto\u002Foutput\u002Fgaps\n```\n\nInclude `videos_dir` when `video_id` values in the predictions are relative paths:\n\n```bash\ngap_analysis vlm_bcq \\\n  predictions_json=\u002Fpath\u002Fto\u002Fresults.json \\\n  results_dir=\u002Fpath\u002Fto\u002Foutput\u002Fgaps \\\n  videos_dir=\u002Fpath\u002Fto\u002Fvideos\u002Froot\n```\n\nAfter the run, surface the FP\u002FFN counts from `kpi_gaps_report.txt` and point downstream stages at `kpi_gaps.jsonl`.\n\n## Inputs\n\n- **predictions_json**: Path to predictions JSON file. Must be a JSON array where each item has `video_id`, `response`, and `gt` fields. `response` and `gt` are parsed with word-boundary matching — `'yes'` or `'no'` anywhere in the string is recognized. Samples where both or neither are present are skipped with a warning.\n- **videos_dir** (optional): Base directory for resolving relative `video_id` paths. If omitted, `video_id` values are used as absolute paths.\n\n**Predictions JSON format:**\n```json\n[\n  {\n    \"video_id\": \"\u002Fpath\u002Fto\u002Fvideo.mp4\",\n    \"response\": \"Yes, there is a collision.\",\n    \"gt\": \"B. No\",\n    \"question\": \"Is there a collision?\"\n  }\n]\n```\n\n## Outputs\n\n- **kpi_gaps.jsonl**: One JSON object per line for each FP\u002FFN case. Fields: `video_id` (absolute path), `error_type` (`FP` or `FN`), `question`, `ground_truth`, `response`.\n- **kpi_gaps_report.txt**: Human-readable table with total FP\u002FFN counts.\n\nIf no gaps are found, no files are written and a message is logged.\n\n## Key Parameters\n\n| Parameter | Required | Description |\n|-----------|----------|-------------|\n| predictions_json | Yes | Path to predictions JSON file |\n| results_dir | Yes | Output directory; created if it does not exist |\n| videos_dir | No | Base directory for resolving relative `video_id` paths |\n\n## Error Patterns\n\n| Error | Cause | Fix |\n|-------|-------|-----|\n| `FileNotFoundError` | `predictions_json` does not exist | Check the path |\n| `ValueError: must be a JSON array` | Predictions file is not a list | Wrap predictions in `[...]` |\n| `ValueError: missing 'gt'\u002F'response'\u002F'video_id'` | A prediction item is missing a required field | Inspect and fix the predictions JSON |\n| Samples silently skipped | `response` or `gt` contains both or neither 'yes'\u002F'no' | Check logs for warnings; inspect those samples |\n",{"name":5,"tags":24,"license":15,"metadata":31,"description":7,"allowed-tools":34,"compatibility":35},[25,26,27,28,29,30],"gap-analysis","rcca","vlm","evaluation","false-positive","false-negative",{"author":32,"version":33},"NVIDIA Corporation","0.1.0","Read Bash","Requires docker + nvidia-container-toolkit.","main","be3de0244dc1a57e323d8160787ebb40fb64930e","public\u002Fapi\u002Fskills\u002Fnvidia\u002Ftao-analyze-gaps-vlm-bcq","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main","https:\u002F\u002Fskills.x402.wtf","https:\u002F\u002Fgithub.com\u002FSolizardking","https:\u002F\u002Fmusebook.trade","Got a mile high and never came down","2026-10-08 23:20:13",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add Solizardking\u002Fskillhub-main --skill tao-analyze-gaps-vlm-bcq",{"tool":51,"command":52},"bunx","bunx skills add Solizardking\u002Fskillhub-main --skill tao-analyze-gaps-vlm-bcq",{"tool":54,"command":55},"pnpm","pnpm dlx skills add Solizardking\u002Fskillhub-main --skill tao-analyze-gaps-vlm-bcq","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fnvidia\u002Ftao-analyze-gaps-vlm-bcq\u002FSKILL.md",true,[59,65,69,73,77],{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"BENCHMARK.md","REFERENCE","参考文档",3841,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fnvidia\u002Ftao-analyze-gaps-vlm-bcq\u002FBENCHMARK.md",{"path":66,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":67,"sourceHtmlUrl":68},"metadata.json",560,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fnvidia\u002Ftao-analyze-gaps-vlm-bcq\u002Fmetadata.json",{"path":70,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fskill_info.yaml",569,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fnvidia\u002Ftao-analyze-gaps-vlm-bcq\u002Freferences\u002Fskill_info.yaml",{"path":74,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":75,"sourceHtmlUrl":76},"skill-card.md",3692,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fnvidia\u002Ftao-analyze-gaps-vlm-bcq\u002Fskill-card.md",{"path":78,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":79,"sourceHtmlUrl":80},"verification.json",1719,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fnvidia\u002Ftao-analyze-gaps-vlm-bcq\u002Fverification.json",[82,90,97,104,111,119],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M78E0TGCAMNPS207BA3G07S7","zkrouter","Self-hosted OpenAI-compatible LLM router — smart tier-based routing, ZK-stamped routing decisions, mode overrides, free OpenRouter at install via the Birth bot. Save 60-80% on inference costs by routing to the cheapest capable model across 12+ OpenRouter models.","MIT","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzkrouter\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M78E0R1Z8BDT6EDTHY17MTNB","zk","For custom ZK Solana programs and privacy-preserving applications to prevent double spending. Guide to integrate rent-free nullifier PDAs for double-spend prevention.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzk\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":86,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M78E0P3ZTZ1YWF8MD5MM23QE","zk-omni-messaging","Zero-knowledge omnichain messaging between Robinhood Chain and Solana using CheshireZkOmniMessenger (msgType 4) with nullifier anti-replay and the zk-omni-relayer service.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzk-omni-messaging\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M78E0JXZ2PNB1896VXAGDBWD","zerion-wallet-data","Use when the user asks to check a wallet's portfolio, token balances, DeFi positions, PnL, transaction history, or NFTs. Provides interpreted on-chain data across 40+ EVM chains and Solana via x402 pay-per-request or API key — no raw RPC decoding needed.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzerion-wallet-data\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":115,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":19},"01M78E0G14FH9GRRTQYMKD5E59","youtube-clipper","YouTube 视频智能剪辑工具。下载视频和字幕，AI 分析生成精细章节（几分钟级别）， 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频，并生成总结文案。 使用场景：当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词：视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-clipper\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-clipper\u002FSKILL.md",[],[],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":19},"01M78E0C2ZYA99CFFDNB7ZMK5S","yield-optimization","Multi-chain yield optimization via yield.xyz (StakeKit). Discover 2,988+ yield opportunities across 75+ blockchains, build deposit\u002Fwithdrawal transactions with shell scripts, and sign them with a MoonPay wallet. Use when the user wants to earn yield, find the best lending or staking rate, enter\u002Fexit a position, or check portfolio balances.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fyield-optimization\u002FSKILL.md",[],[]]