[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78CW3X7NW9EXVVTJ40KJESK":3,"skill-same:01M78CW3X7NW9EXVVTJ40KJESK":76},{"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},"01M78CW3X7NW9EXVVTJ40KJESK","jetson-init-image",null,"Extract Jetson Linux + sample-rootfs tarballs and run apply_binaries.sh for the active target, then record bsp_image in the profile. Use after jetson-init-target; not for source-tree setup.","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\u002Fskills\u002Fnvidia\u002Fjetson-init-image\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: jetson-init-image\ndescription: >-\n  Extract Jetson Linux + sample-rootfs tarballs and run\n  apply_binaries.sh for the active target, then record bsp_image in\n  the profile. Use after jetson-init-target; not for source-tree\n  setup.\nversion: 0.0.1\nlicense: \"Apache-2.0\"\nmetadata:\n  data-classification: public\n  author: \"Jetson Team\"\n  tags:\n    - bsp\n    - image\n    - bootstrap\n  domain: meta\n---\n\n# Initialize BSP Image\n\nOutput is only `bsp_image:` in the active profile: derived `version`\nplus `root_path` only when overriding `\u003Cworkspace>\u002FImage`.\n\n## When to invoke\n\n- The user asks to extract, prepare, or initialize the BSP image.\n- A downstream skill reports missing\n  `\u003Cbsp_image.root_path>\u002FLinux_for_Tegra\u002F`.\n- The active profile has no `bsp_image:` block yet.\n\n## Procedure\n\n### Resolve target and image path\n\nResolve the active profile per\n[`..\u002F..\u002Fcontext\u002Ftarget-platform-contract.md`](..\u002F..\u002Fcontext\u002Ftarget-platform-contract.md).\nRefuse if there is no active profile or `reference_devkit:` is missing.\n\n`\u003Cworkspace>` is the parent of the active profile's `target-platform\u002F`\ndirectory. `\u003Cbsp_image.root_path>` defaults to `\u003Cworkspace>\u002FImage`.\n\n| Profile state | Action |\n|---|---|\n| `bsp_image.root_path` exists | Use it without prompting. |\n| `bsp_image:` exists without `root_path` | Use `\u003Cworkspace>\u002FImage`. |\n| No `bsp_image:` block | Ask once: Enter for default, or absolute override path. |\n\nFor an override, validate that the closest existing parent is writable.\nOmit `root_path` when the default is used.\n\n### Determine GPU stack\n\nUse the shared GPU-driver invariant from\n[`..\u002F..\u002Fcontext\u002Ftarget-platform-contract.md`](..\u002F..\u002Fcontext\u002Ftarget-platform-contract.md#derived-platform-facts).\nDerive the expected stack from `reference_devkit.module.id` and the\ncatalogue:\n\n| Chip family | Module IDs | Stack | `apply_binaries.sh` flag |\n|---|---|---|---|\n| T234 \u002F Orin | `p3701`, `p3767` | nvgpu | none |\n| T264 and later \u002F Thor+ | `p3834` | OpenRM | `--openrm` |\n\nRefuse unknown module IDs. The `--openrm` flag is only valid on BSP\nreleases that ship the OpenRM stack; if the active BSP doesn't expose\nthe flag, omit it regardless of what the target wants.\n\n### Reuse or extract\n\nIf `\u003Cbsp_image.root_path>\u002FLinux_for_Tegra\u002F` already exists:\n\n1. Do not extract over it unless the user explicitly requested\n   re-extraction and accepted the overwrite risk.\n2. Derive the on-disk version from `Linux_for_Tegra\u002Fnv_tegra_release`.\n   Ask before replacing a different recorded `bsp_image.version`.\n3. Verify the installed GPU stack against the platform-derived\n   expectation when possible. Detection precedence (first probe that\n   yields a definitive answer wins):\n\n   1. `Linux_for_Tegra\u002Frootfs\u002Fetc\u002Fnv_tegra_release` carries an\n      `INSTALL_TYPE=` token on BSP releases that expose it (newer\n      lines). Read and compare directly.\n   2. Otherwise, `find Linux_for_Tegra -name nvgpu.ko`: present →\n      nvgpu, absent → OpenRM.\n   3. If the chip family has only ever shipped one stack (e.g. T234 \u002F\n      Orin is always nvgpu in current BSPs), fall back to the\n      catalogue-derived expectation without disk probing.\n\nIf the installed stack conflicts with the active target, refuse and ask\nthe user to re-extract with the correct stack or fix the target profile.\nOtherwise skip extraction and update the profile.\n\n### Locate tarballs\n\nWhen extraction is needed, search:\n\n1. `\u003Cbsp_image.root_path>\u002F`\n2. `\u003Cworkspace>\u002F`\n3. current working directory\n\nPrompt for absolute paths for anything missing. Required filenames:\n\n- `Jetson_Linux_R\u003Cver>_aarch64.tbz2`\n- `Tegra_Linux_Sample-Root-Filesystem_R\u003Cver>_aarch64.tbz2`\n\nBoth filenames must contain the same `R\u003Cver>` token. Refuse mismatches\nand record `\u003Cver>` as `bsp_image.version`. Do not download tarballs.\n\n### Extract and apply binaries\n\nUse absolute tarball paths; they may live outside\n`\u003Cbsp_image.root_path>`.\n\n```bash\nROOT=\"\u003Cbsp_image.root_path>\"\nBSP_TARBALL=\"\u003Cabsolute path to Jetson_Linux_R\u003Cver>_aarch64.tbz2>\"\nROOTFS_TARBALL=\"\u003Cabsolute path to Tegra_Linux_Sample-Root-Filesystem_R\u003Cver>_aarch64.tbz2>\"\n\nmkdir -p \"$ROOT\"\ntar xjf \"$BSP_TARBALL\" -C \"$ROOT\"\nsudo tar xpjf \"$ROOTFS_TARBALL\" -C \"$ROOT\u002FLinux_for_Tegra\u002Frootfs\"\n\ncd \"$ROOT\u002FLinux_for_Tegra\"\nif [ \"$GPU_STACK\" = \"openrm\" ]; then\n  sudo .\u002Fapply_binaries.sh --openrm\nelse\n  sudo .\u002Fapply_binaries.sh\nfi\n```\n\nSet `GPU_STACK` from the \"Determine GPU stack\" step above. Abort on the first failing command and\nsurface the failed command.\n\n### Update the active profile\n\nPersist the resolved BSP image metadata in the active target profile so\nlater skills can find the BSP without re-prompting. Preserve existing\nblocks, comments, and quoted SKU values; use a round-tripping YAML\nwriter such as `ruamel.yaml`.\n\n```yaml\nbsp_image:\n  root_path: \u003Cabsolute override path>  # omit for \u003Cworkspace>\u002FImage\n  version: \"\u003Cderived version>\"\n```\n\nRules:\n\n- Same version and same root path: no rewrite.\n- Different version: ask before updating.\n- Different recorded `root_path`: refuse automatic rewrite.\n- Always quote `version`.\n\n## Finish\n\nReport the image path, extracted vs reused state, GPU stack, derived\nversion, and profile update status. Then suggest `\u002Fjetson-init-source`.\n\n## Purpose\n\nMaterialize `Linux_for_Tegra\u002F` on disk by extracting the right Jetson\nLinux + sample-rootfs tarballs and running `apply_binaries.sh` with\nthe GPU-stack flag derived from the active target (nvgpu for T234,\nOpenRM for T264+). Then commit the derived BSP version into the\nprofile's `bsp_image:` block.\n\n## Prerequisites\n\n- Active target profile resolved per\n  `..\u002F..\u002Fcontext\u002Ftarget-platform-contract.md`.\n- Jetson Linux BSP tarball and matching sample-rootfs tarball staged\n  on disk (e.g. by `\u002Fjetson-download-bsp` or hand-placed).\n- Write access to the workspace `Image\u002F` root (or the override\n  `bsp_image.root_path`).\n- `sudo` available for `apply_binaries.sh`.\n\n## Limitations\n\n- Writes only the `bsp_image:` block; source tree, documents, and\n  carrier profile are owned by sibling skills.\n- Refuses to overwrite an existing `Linux_for_Tegra\u002F` without explicit\n  user direction.\n- Does not download tarballs; rely on `\u002Fjetson-download-bsp` or\n  hand-stage the inputs.\n\n## Troubleshooting\n\n- **`apply_binaries.sh` exits non-zero** — re-read its console output;\n  most failures are missing `sudo`, missing rootfs tarball, or wrong\n  GPU stack flag for the SoC generation.\n- **`nv_tegra_release` absent after extract** — extraction stopped\n  early; verify tarball integrity and rerun.\n- **Recorded `version` disagrees with the tarball filename** — the\n  tarball was renamed; trust the value parsed from\n  `Linux_for_Tegra\u002Fnv_tegra_release` over filenames.\n- **Different recorded `root_path` already in profile** — refuse and\n  ask the user to confirm before overwriting.\n\n## References\n\n- [`..\u002F..\u002Fcontext\u002Ftarget-platform-contract.md`](..\u002F..\u002Fcontext\u002Ftarget-platform-contract.md)\n- [`..\u002F..\u002Freferences\u002Fbsp-platforms-catalogue.md`](..\u002F..\u002Freferences\u002Fbsp-platforms-catalogue.md)\n- [`..\u002F..\u002Freferences\u002Fplatform_template.yaml`](..\u002F..\u002Freferences\u002Fplatform_template.yaml)\n- [`..\u002Fjetson-init-target\u002FSKILL.md`](..\u002Fjetson-init-target\u002FSKILL.md)\n- [`..\u002Fjetson-init-source\u002FSKILL.md`](..\u002Fjetson-init-source\u002FSKILL.md)\n- [`..\u002Fjetson-flash-image\u002FSKILL.md`](..\u002Fjetson-flash-image\u002FSKILL.md)\n","# Initialize BSP Image\n\nOutput is only `bsp_image:` in the active profile: derived `version`\nplus `root_path` only when overriding `\u003Cworkspace>\u002FImage`.\n\n## When to invoke\n\n- The user asks to extract, prepare, or initialize the BSP image.\n- A downstream skill reports missing\n  `\u003Cbsp_image.root_path>\u002FLinux_for_Tegra\u002F`.\n- The active profile has no `bsp_image:` block yet.\n\n## Procedure\n\n### Resolve target and image path\n\nResolve the active profile per\n[`..\u002F..\u002Fcontext\u002Ftarget-platform-contract.md`](..\u002F..\u002Fcontext\u002Ftarget-platform-contract.md).\nRefuse if there is no active profile or `reference_devkit:` is missing.\n\n`\u003Cworkspace>` is the parent of the active profile's `target-platform\u002F`\ndirectory. `\u003Cbsp_image.root_path>` defaults to `\u003Cworkspace>\u002FImage`.\n\n| Profile state | Action |\n|---|---|\n| `bsp_image.root_path` exists | Use it without prompting. |\n| `bsp_image:` exists without `root_path` | Use `\u003Cworkspace>\u002FImage`. |\n| No `bsp_image:` block | Ask once: Enter for default, or absolute override path. |\n\nFor an override, validate that the closest existing parent is writable.\nOmit `root_path` when the default is used.\n\n### Determine GPU stack\n\nUse the shared GPU-driver invariant from\n[`..\u002F..\u002Fcontext\u002Ftarget-platform-contract.md`](..\u002F..\u002Fcontext\u002Ftarget-platform-contract.md#derived-platform-facts).\nDerive the expected stack from `reference_devkit.module.id` and the\ncatalogue:\n\n| Chip family | Module IDs | Stack | `apply_binaries.sh` flag |\n|---|---|---|---|\n| T234 \u002F Orin | `p3701`, `p3767` | nvgpu | none |\n| T264 and later \u002F Thor+ | `p3834` | OpenRM | `--openrm` |\n\nRefuse unknown module IDs. The `--openrm` flag is only valid on BSP\nreleases that ship the OpenRM stack; if the active BSP doesn't expose\nthe flag, omit it regardless of what the target wants.\n\n### Reuse or extract\n\nIf `\u003Cbsp_image.root_path>\u002FLinux_for_Tegra\u002F` already exists:\n\n1. Do not extract over it unless the user explicitly requested\n   re-extraction and accepted the overwrite risk.\n2. Derive the on-disk version from `Linux_for_Tegra\u002Fnv_tegra_release`.\n   Ask before replacing a different recorded `bsp_image.version`.\n3. Verify the installed GPU stack against the platform-derived\n   expectation when possible. Detection precedence (first probe that\n   yields a definitive answer wins):\n\n   1. `Linux_for_Tegra\u002Frootfs\u002Fetc\u002Fnv_tegra_release` carries an\n      `INSTALL_TYPE=` token on BSP releases that expose it (newer\n      lines). Read and compare directly.\n   2. Otherwise, `find Linux_for_Tegra -name nvgpu.ko`: present →\n      nvgpu, absent → OpenRM.\n   3. If the chip family has only ever shipped one stack (e.g. T234 \u002F\n      Orin is always nvgpu in current BSPs), fall back to the\n      catalogue-derived expectation without disk probing.\n\nIf the installed stack conflicts with the active target, refuse and ask\nthe user to re-extract with the correct stack or fix the target profile.\nOtherwise skip extraction and update the profile.\n\n### Locate tarballs\n\nWhen extraction is needed, search:\n\n1. `\u003Cbsp_image.root_path>\u002F`\n2. `\u003Cworkspace>\u002F`\n3. current working directory\n\nPrompt for absolute paths for anything missing. Required filenames:\n\n- `Jetson_Linux_R\u003Cver>_aarch64.tbz2`\n- `Tegra_Linux_Sample-Root-Filesystem_R\u003Cver>_aarch64.tbz2`\n\nBoth filenames must contain the same `R\u003Cver>` token. Refuse mismatches\nand record `\u003Cver>` as `bsp_image.version`. Do not download tarballs.\n\n### Extract and apply binaries\n\nUse absolute tarball paths; they may live outside\n`\u003Cbsp_image.root_path>`.\n\n```bash\nROOT=\"\u003Cbsp_image.root_path>\"\nBSP_TARBALL=\"\u003Cabsolute path to Jetson_Linux_R\u003Cver>_aarch64.tbz2>\"\nROOTFS_TARBALL=\"\u003Cabsolute path to Tegra_Linux_Sample-Root-Filesystem_R\u003Cver>_aarch64.tbz2>\"\n\nmkdir -p \"$ROOT\"\ntar xjf \"$BSP_TARBALL\" -C \"$ROOT\"\nsudo tar xpjf \"$ROOTFS_TARBALL\" -C \"$ROOT\u002FLinux_for_Tegra\u002Frootfs\"\n\ncd \"$ROOT\u002FLinux_for_Tegra\"\nif [ \"$GPU_STACK\" = \"openrm\" ]; then\n  sudo .\u002Fapply_binaries.sh --openrm\nelse\n  sudo .\u002Fapply_binaries.sh\nfi\n```\n\nSet `GPU_STACK` from the \"Determine GPU stack\" step above. Abort on the first failing command and\nsurface the failed command.\n\n### Update the active profile\n\nPersist the resolved BSP image metadata in the active target profile so\nlater skills can find the BSP without re-prompting. Preserve existing\nblocks, comments, and quoted SKU values; use a round-tripping YAML\nwriter such as `ruamel.yaml`.\n\n```yaml\nbsp_image:\n  root_path: \u003Cabsolute override path>  # omit for \u003Cworkspace>\u002FImage\n  version: \"\u003Cderived version>\"\n```\n\nRules:\n\n- Same version and same root path: no rewrite.\n- Different version: ask before updating.\n- Different recorded `root_path`: refuse automatic rewrite.\n- Always quote `version`.\n\n## Finish\n\nReport the image path, extracted vs reused state, GPU stack, derived\nversion, and profile update status. Then suggest `\u002Fjetson-init-source`.\n\n## Purpose\n\nMaterialize `Linux_for_Tegra\u002F` on disk by extracting the right Jetson\nLinux + sample-rootfs tarballs and running `apply_binaries.sh` with\nthe GPU-stack flag derived from the active target (nvgpu for T234,\nOpenRM for T264+). Then commit the derived BSP version into the\nprofile's `bsp_image:` block.\n\n## Prerequisites\n\n- Active target profile resolved per\n  `..\u002F..\u002Fcontext\u002Ftarget-platform-contract.md`.\n- Jetson Linux BSP tarball and matching sample-rootfs tarball staged\n  on disk (e.g. by `\u002Fjetson-download-bsp` or hand-placed).\n- Write access to the workspace `Image\u002F` root (or the override\n  `bsp_image.root_path`).\n- `sudo` available for `apply_binaries.sh`.\n\n## Limitations\n\n- Writes only the `bsp_image:` block; source tree, documents, and\n  carrier profile are owned by sibling skills.\n- Refuses to overwrite an existing `Linux_for_Tegra\u002F` without explicit\n  user direction.\n- Does not download tarballs; rely on `\u002Fjetson-download-bsp` or\n  hand-stage the inputs.\n\n## Troubleshooting\n\n- **`apply_binaries.sh` exits non-zero** — re-read its console output;\n  most failures are missing `sudo`, missing rootfs tarball, or wrong\n  GPU stack flag for the SoC generation.\n- **`nv_tegra_release` absent after extract** — extraction stopped\n  early; verify tarball integrity and rerun.\n- **Recorded `version` disagrees with the tarball filename** — the\n  tarball was renamed; trust the value parsed from\n  `Linux_for_Tegra\u002Fnv_tegra_release` over filenames.\n- **Different recorded `root_path` already in profile** — refuse and\n  ask the user to confirm before overwriting.\n\n## References\n\n- [`..\u002F..\u002Fcontext\u002Ftarget-platform-contract.md`](..\u002F..\u002Fcontext\u002Ftarget-platform-contract.md)\n- [`..\u002F..\u002Freferences\u002Fbsp-platforms-catalogue.md`](..\u002F..\u002Freferences\u002Fbsp-platforms-catalogue.md)\n- [`..\u002F..\u002Freferences\u002Fplatform_template.yaml`](..\u002F..\u002Freferences\u002Fplatform_template.yaml)\n- [`..\u002Fjetson-init-target\u002FSKILL.md`](..\u002Fjetson-init-target\u002FSKILL.md)\n- [`..\u002Fjetson-init-source\u002FSKILL.md`](..\u002Fjetson-init-source\u002FSKILL.md)\n- [`..\u002Fjetson-flash-image\u002FSKILL.md`](..\u002Fjetson-flash-image\u002FSKILL.md)\n",{"name":5,"license":15,"version":24,"metadata":25,"description":7},"0.0.1",{"tags":26,"author":30,"domain":31,"data-classification":32},[27,28,29],"bsp","image","bootstrap","Jetson Team","meta","public","main","be3de0244dc1a57e323d8160787ebb40fb64930e","skills\u002Fnvidia\u002Fjetson-init-image","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 jetson-init-image",{"tool":48,"command":49},"bunx","bunx skills add Solizardking\u002Fskillhub-main --skill jetson-init-image",{"tool":51,"command":52},"pnpm","pnpm dlx skills add Solizardking\u002Fskillhub-main --skill jetson-init-image","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fjetson-init-image\u002FSKILL.md",true,[56,62,66,70],{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"BENCHMARK.md","REFERENCE","参考文档",3812,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fjetson-init-image\u002FBENCHMARK.md",{"path":63,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":64,"sourceHtmlUrl":65},"evals\u002Fevals.json",3989,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fjetson-init-image\u002Fevals\u002Fevals.json",{"path":67,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":68,"sourceHtmlUrl":69},"skill-card.md",4087,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fjetson-init-image\u002Fskill-card.md",{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"skill.oms.sig","OTHER","其他",4589,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fjetson-init-image\u002Fskill.oms.sig",[77,85,92,99,106,114],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":110,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"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",[],[]]