[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78AMM73GXKS3ZCF9FSNX7F7":3,"skill-same:01M78AMM73GXKS3ZCF9FSNX7F7":86},{"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":33,"commitSha":34,"skillDirectory":35,"forksCount":14,"repositoryHtmlUrl":36,"repositoryHomepageUrl":37,"ownerHtmlUrl":38,"ownerBlogUrl":39,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M78AMM73GXKS3ZCF9FSNX7F7","tao-analyze-changenet-rca",null,"Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with image-evidence-driven investigation. Use when analyzing ChangeNet model failures, investigating poor recall \u002F FAR \u002F PASS-NO_PASS metrics, auditing visual inspection pipeline quality, or running an RCA report for an AOI defect-detection model. Trigger phrases include \"RCA on my ChangeNet model\", \"why is my AOI model failing\", \"audit ChangeNet predictions\", \"investigate FAR regressions\", \"root cause analysis on visual-changenet\".","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-changenet-rca\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: tao-analyze-changenet-rca\ndescription: Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with\n  image-evidence-driven investigation. Use when analyzing ChangeNet model failures, investigating poor recall \u002F FAR \u002F PASS-NO_PASS\n  metrics, auditing visual inspection pipeline quality, or running an RCA report for an AOI defect-detection model.\n  Trigger phrases include \"RCA on my ChangeNet model\", \"why is my AOI model failing\", \"audit ChangeNet predictions\",\n  \"investigate FAR regressions\", \"root cause analysis on visual-changenet\".\nlicense: Apache-2.0\ncompatibility: Requires docker + nvidia-container-toolkit. Workflows declare additional requirements.\nmetadata:\n  author: NVIDIA Corporation\n  version: \"0.1.0\"\nallowed-tools: Read Bash\ntags:\n- application\n- rca\n- changenet\n---\n\n# TAO ChangeNet Classification RCA Skill\n\nYou are an expert investigator for NVIDIA TAO Visual ChangeNet classification experiments. Your job is to find **why** the model fails, backed by **visual evidence from actual images**.\n\nWhen the user provides an experiment result directory and training code directory, perform a deep Root Cause Analysis. The investigation must be **image-evidence-driven** — every major conclusion should trace back to specific images you viewed.\n\n---\n\n## Inputs\n\n1. **Experiment result directory** — contains `train\u002F` and `inference\u002F`\n2. **Training code directory** — the `visual_changenet\u002F` source tree\n3. **Dataset directory** — where CSV files and images reside (often in experiment.yaml)\n4. **Target KPI** — default to **Recall-first** if not specified. Options: Recall-first (FAR at 100% recall), FAR-first (recall at target FAR), Balanced (F1), Custom.\n\n---\n\n## Visual Inspection Primer\n\nThe ChangeNet model compares a **test image** against a **golden image** (known-good reference) to detect differences. When viewing images, check these three things:\n\n1. **Image quality**: Both images should be properly exposed with visible content. Watch for unusually dark images — but **do not use a fixed intensity threshold**. Some illumination types (e.g., SolderLight) produce systemically dark images where mean intensity \u003C 30 is normal. Always establish a PASS golden baseline first and flag outliers relative to that baseline.\n2. **Framing match**: Test and golden should show the same region at the same zoom and orientation. Mismatched framing (e.g., wide-field vs close-up) indicates a golden pipeline error.\n3. **Defect visibility**: Can you see the difference between test and golden? Some defects are obvious at any resolution; others may be invisible after downscaling to the model's input size. Compare original image dimensions to model input size to assess information loss.\n\n---\n\n## Investigation Flow\n\nThe investigation has 5 phases. Phase 1 (numbers) gives you hypotheses. Phase 2 (images) proves or disproves them. Phase 3 (cross-dimensional) finds hidden patterns. Phase 4 (config) explains the mechanism. Phase 5 (counterfactual) quantifies fixes. **Phase 2 is the core — spend the most effort there. Phase 5 is the most actionable — never skip it.**\n\n- **Phase 1 — Score Analysis**: score statistics, tier classification, threshold sweep, per-defect-type table, drop-N threshold-critical analysis, KPI verdict.\n- **Phase 2 — Deep Image Investigation**: threshold-critical sample deep dive (2A), systematic golden audit + failure mode clustering (2B), false positive deep dive (2C), comparative visual analysis (2D), label semantics & visual pattern alignment audit (2E).\n- **Phase 3 — Cross-Dimensional Analysis**: component-type clustering (3A), board-level & positional analysis (3B), training image deep dive (3C), multi-light condition analysis (3D).\n- **Phase 4 — Data & Training Config Analysis**: data sufficiency (4A), training config audit (4B), training metrics (4C), loss function & decision boundary analysis (4D).\n- **Phase 5 — Counterfactual & Actionability**: what-if simulations (5A), minimum viable fix path (5B).\n\nSee `references\u002Finvestigation-phases.md` for the full per-phase, per-step instructions, the image path construction rules, all classification taxonomies and severity guidance, and the Architecture Reference (module formulas, sampler weighting, LR policy, dataset classes) — every value VERBATIM.\n\n---\n\n## Execution: Parallelize With Subagents\n\n**You MUST use the Agent tool to run independent investigation tracks in parallel.** Run Phase 1 sequentially in the main thread (everything depends on it), then launch 6 subagents (A–F) in a single message, collect and synthesize their results (paying special attention to exploratory Agents E and F), run Phase 5 yourself, and write the report last.\n\nBefore writing `RCA_Report.md`, run `ls rca_images\u002F` to inventory thumbnails, and follow the **mandatory Image Embedding Protocol**: every visual-evidence table row must carry inline thumbnail columns using `![caption](rca_images\u002F\u003Cfilename>.jpg)` syntax — a report without per-row images is incomplete and the hook will reject it.\n\nSee `references\u002Fparallelization.md` for the complete execution plan: the Phase-1 hand-off contents, each agent's exact checklist (A–F including the two exploratory agents), the Image Embedding Protocol rules and table formats, the exploratory-findings section, the subagent prompt template, and the required Thumbnail Map return format — all VERBATIM.\n\n---\n\n## Report Structure and Output\n\nProduce `RCA_Report.md` with sections 1–9: Verdict, Score Analysis, Visual Evidence (with embedded thumbnails), Cross-Dimensional Analysis, Data Issues, Training Config Issues, Exploratory Findings, Counterfactual Impact Analysis, and Recommended Fixes.\n\nAlways save into a timestamped folder under the experiment result directory:\n```\n\u003Cexperiment_result_dir>\u002Frca_results\u002FYYYY-MM-DD_HHMMSS\u002F\n├── RCA_Report.md\n├── rca_images\u002F\n├── rca_config\u002F\n└── claude_session.jsonl\n```\nGet the real timestamp by running `date +%Y-%m-%d_%H%M%S` in Bash — never hardcode or guess it. If the user specifies a custom path, use that instead but keep the same structure.\n\nSee `references\u002Foutput-structure.md` for the complete section-by-section report skeleton (every table header and summary line) and the full output layout with hook-copied contents — VERBATIM.\n","# TAO ChangeNet Classification RCA Skill\n\nYou are an expert investigator for NVIDIA TAO Visual ChangeNet classification experiments. Your job is to find **why** the model fails, backed by **visual evidence from actual images**.\n\nWhen the user provides an experiment result directory and training code directory, perform a deep Root Cause Analysis. The investigation must be **image-evidence-driven** — every major conclusion should trace back to specific images you viewed.\n\n---\n\n## Inputs\n\n1. **Experiment result directory** — contains `train\u002F` and `inference\u002F`\n2. **Training code directory** — the `visual_changenet\u002F` source tree\n3. **Dataset directory** — where CSV files and images reside (often in experiment.yaml)\n4. **Target KPI** — default to **Recall-first** if not specified. Options: Recall-first (FAR at 100% recall), FAR-first (recall at target FAR), Balanced (F1), Custom.\n\n---\n\n## Visual Inspection Primer\n\nThe ChangeNet model compares a **test image** against a **golden image** (known-good reference) to detect differences. When viewing images, check these three things:\n\n1. **Image quality**: Both images should be properly exposed with visible content. Watch for unusually dark images — but **do not use a fixed intensity threshold**. Some illumination types (e.g., SolderLight) produce systemically dark images where mean intensity \u003C 30 is normal. Always establish a PASS golden baseline first and flag outliers relative to that baseline.\n2. **Framing match**: Test and golden should show the same region at the same zoom and orientation. Mismatched framing (e.g., wide-field vs close-up) indicates a golden pipeline error.\n3. **Defect visibility**: Can you see the difference between test and golden? Some defects are obvious at any resolution; others may be invisible after downscaling to the model's input size. Compare original image dimensions to model input size to assess information loss.\n\n---\n\n## Investigation Flow\n\nThe investigation has 5 phases. Phase 1 (numbers) gives you hypotheses. Phase 2 (images) proves or disproves them. Phase 3 (cross-dimensional) finds hidden patterns. Phase 4 (config) explains the mechanism. Phase 5 (counterfactual) quantifies fixes. **Phase 2 is the core — spend the most effort there. Phase 5 is the most actionable — never skip it.**\n\n- **Phase 1 — Score Analysis**: score statistics, tier classification, threshold sweep, per-defect-type table, drop-N threshold-critical analysis, KPI verdict.\n- **Phase 2 — Deep Image Investigation**: threshold-critical sample deep dive (2A), systematic golden audit + failure mode clustering (2B), false positive deep dive (2C), comparative visual analysis (2D), label semantics & visual pattern alignment audit (2E).\n- **Phase 3 — Cross-Dimensional Analysis**: component-type clustering (3A), board-level & positional analysis (3B), training image deep dive (3C), multi-light condition analysis (3D).\n- **Phase 4 — Data & Training Config Analysis**: data sufficiency (4A), training config audit (4B), training metrics (4C), loss function & decision boundary analysis (4D).\n- **Phase 5 — Counterfactual & Actionability**: what-if simulations (5A), minimum viable fix path (5B).\n\nSee `references\u002Finvestigation-phases.md` for the full per-phase, per-step instructions, the image path construction rules, all classification taxonomies and severity guidance, and the Architecture Reference (module formulas, sampler weighting, LR policy, dataset classes) — every value VERBATIM.\n\n---\n\n## Execution: Parallelize With Subagents\n\n**You MUST use the Agent tool to run independent investigation tracks in parallel.** Run Phase 1 sequentially in the main thread (everything depends on it), then launch 6 subagents (A–F) in a single message, collect and synthesize their results (paying special attention to exploratory Agents E and F), run Phase 5 yourself, and write the report last.\n\nBefore writing `RCA_Report.md`, run `ls rca_images\u002F` to inventory thumbnails, and follow the **mandatory Image Embedding Protocol**: every visual-evidence table row must carry inline thumbnail columns using `![caption](rca_images\u002F\u003Cfilename>.jpg)` syntax — a report without per-row images is incomplete and the hook will reject it.\n\nSee `references\u002Fparallelization.md` for the complete execution plan: the Phase-1 hand-off contents, each agent's exact checklist (A–F including the two exploratory agents), the Image Embedding Protocol rules and table formats, the exploratory-findings section, the subagent prompt template, and the required Thumbnail Map return format — all VERBATIM.\n\n---\n\n## Report Structure and Output\n\nProduce `RCA_Report.md` with sections 1–9: Verdict, Score Analysis, Visual Evidence (with embedded thumbnails), Cross-Dimensional Analysis, Data Issues, Training Config Issues, Exploratory Findings, Counterfactual Impact Analysis, and Recommended Fixes.\n\nAlways save into a timestamped folder under the experiment result directory:\n```\n\u003Cexperiment_result_dir>\u002Frca_results\u002FYYYY-MM-DD_HHMMSS\u002F\n├── RCA_Report.md\n├── rca_images\u002F\n├── rca_config\u002F\n└── claude_session.jsonl\n```\nGet the real timestamp by running `date +%Y-%m-%d_%H%M%S` in Bash — never hardcode or guess it. If the user specifies a custom path, use that instead but keep the same structure.\n\nSee `references\u002Foutput-structure.md` for the complete section-by-section report skeleton (every table header and summary line) and the full output layout with hook-copied contents — VERBATIM.\n",{"name":5,"tags":24,"license":15,"metadata":28,"description":7,"allowed-tools":31,"compatibility":32},[25,26,27],"application","rca","changenet",{"author":29,"version":30},"NVIDIA Corporation","0.1.0","Read Bash","Requires docker + nvidia-container-toolkit. Workflows declare additional requirements.","main","be3de0244dc1a57e323d8160787ebb40fb64930e","public\u002Fapi\u002Fskills\u002Fnvidia\u002Ftao-analyze-changenet-rca","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":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add Solizardking\u002Fskillhub-main --skill tao-analyze-changenet-rca",{"tool":48,"command":49},"bunx","bunx skills add Solizardking\u002Fskillhub-main --skill tao-analyze-changenet-rca",{"tool":51,"command":52},"pnpm","pnpm dlx skills add Solizardking\u002Fskillhub-main --skill tao-analyze-changenet-rca","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fnvidia\u002Ftao-analyze-changenet-rca\u002FSKILL.md",true,[56,62,66,70,74,78,82],{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"BENCHMARK.md","REFERENCE","参考文档",4140,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fnvidia\u002Ftao-analyze-changenet-rca\u002FBENCHMARK.md",{"path":63,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":64,"sourceHtmlUrl":65},"metadata.json",769,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fnvidia\u002Ftao-analyze-changenet-rca\u002Fmetadata.json",{"path":67,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Finvestigation-phases.md",17039,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fnvidia\u002Ftao-analyze-changenet-rca\u002Freferences\u002Finvestigation-phases.md",{"path":71,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Foutput-structure.md",6092,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fnvidia\u002Ftao-analyze-changenet-rca\u002Freferences\u002Foutput-structure.md",{"path":75,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fparallelization.md",8795,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fnvidia\u002Ftao-analyze-changenet-rca\u002Freferences\u002Fparallelization.md",{"path":79,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":80,"sourceHtmlUrl":81},"skill-card.md",3901,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fnvidia\u002Ftao-analyze-changenet-rca\u002Fskill-card.md",{"path":83,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":84,"sourceHtmlUrl":85},"verification.json",2282,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fnvidia\u002Ftao-analyze-changenet-rca\u002Fverification.json",[87,95,102,109,116,124],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"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":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"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":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"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":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"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":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":91,"licenseFileUrl":120,"sourceHtmlUrl":121,"categories":122,"keywords":123,"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":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"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",[],[]]