[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7A9CA55DRHK2KBZX91VMDC3":3,"skill-same:01M7A9CA55DRHK2KBZX91VMDC3":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":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":39,"ownerHtmlUrl":40,"ownerBlogUrl":41,"ownerDescription":42,"updatedAt":43,"install":44,"resources":57},"01M7A9CA55DRHK2KBZX91VMDC3","jetson-customize-pcie",null,"Per-controller PCIe enable \u002F disable \u002F lanes \u002F link-speed for a Jetson Thor or Orin custom carrier via ODMDATA + kernel-DT overlay. Do NOT use for UPHY lane allocation or endpoint-mode bring-up.","themusebook\u002Fskills","themusebook","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F349927247?v=4","01M7A5C1RV5S3V5FF6ZACVDNRN","musebook","01M7A5C1SFC3KRZAXNN60XJ7KM",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fjetson-customize-pcie\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: jetson-customize-pcie\ndescription: >-\n  Per-controller PCIe enable \u002F disable \u002F lanes \u002F link-speed for a\n  Jetson Thor or Orin custom carrier via ODMDATA + kernel-DT overlay.\n  Do NOT use for UPHY lane allocation or endpoint-mode bring-up.\nversion: 0.0.1\nlicense: \"Apache-2.0\"\nmetadata:\n  data-classification: public\n  author: \"Jetson Team\"\n  tags:\n    - bsp\n    - phase-2\n    - io\n    - pcie\n  domain: meta\n---\n\n# Customize PCIe (per-controller status \u002F lanes \u002F speed)\n\n## Overview\n\nPCIe on Tegra264 (Thor, `pcie@C0..C5`) and Tegra234 (Orin,\n`pcie@C0..C10`) is split across multiple controllers that share the\nUPHY lane pool with USB3 \u002F MGBE \u002F UFS. Each controller's runtime\nbehavior is determined by **two surfaces, both required**:\n\n| Surface | Target | Authoritative for |\n|---|---|---|\n| ODMDATA `pcie@N_status=…` (+ `pcie@N_max-link-speed`, `pcie@N_pcie-mode`, `pcie@N_clk-scheme`, `pcie-cN-endpoint-enable`) | `\u002Fpcie\u002Fpcie@N` in BPMP DTB | UPHY lane power, refclk gating, controller-side power rails |\n| Kernel-DT overlay on `&pcieN` | `\u002Fbus@0\u002Fpcie@\u003Caddr>` in kernel DTB | Kernel probe, lane width, link speed, RC\u002FEP mode |\n\nSkipping the kernel overlay on a disable lets the kernel probe a\npowered-down PHY (link timeouts in dmesg). Skipping the ODMDATA token\non a disable leaves BPMP holding the PHY hot.\n\n**Agentic, not table-driven** — no controller table, no\n`questions.json`. Every controller, lane width, schematic-routed\nreceptacle, and authoritative DT node address is discovered at runtime\nfrom the docs + DTB + carrier pinmap.\n\nThe output is a **kernel-DT overlay commit only**. Per-controller\n`fragment@N` blocks are appended to the composite custom overlay\n`.dts` per\n[`..\u002F..\u002Freferences\u002Fbsp-customization-kernel-dtb.md`](..\u002F..\u002Freferences\u002Fbsp-customization-kernel-dtb.md)\nand committed to the `bsp_sources\u002F` hardware repo.\n`\u002Fjetson-build-source` compiles the composite to `.dtbo` and owns its\nMakefile + flash-conf registration.\n\n**This skill MUST NOT edit `ODMDATA=\"...\"`.** All ODMDATA tokens\n(`pcie@N_status=…`, `pcie@N_max-link-speed`, `pcie@N_pcie-mode`,\n`pcie@N_clk-scheme`, `pcie-cN-endpoint-enable`, plus the\n`uphyX-config-N` surface tokens and `UPHY_CONFIG=\"\"` clear) are\nemitted by `\u002Fjetson-customize-uphy` in a single atomic commit on the\ncarrier flash-conf fork. The allocation table this skill consumes\nfrom the UPHY sidecar already tells the operator which controllers\nare `okay` \u002F `disabled` \u002F per-lane sized; this skill only translates\nthat table into kernel-DT overlay fragments and verifies that the\noverlay agrees with the ODMDATA already committed by `customize-uphy`\n(consistency check in Step 8 — disagreement is reported, not silently\nfixed).\n\n## When to invoke\n\n- The user says \"configure PCIe\", \"enable PCIe controller\", \"set PCIe\n  num-lanes\", \"change PCIe link speed\", or asks to flip a\n  `pcie@N_status` token.\n- A specific PCIe slot or M.2 receptacle doesn't enumerate after\n  flash, OR the link trains at the wrong width \u002F speed.\n- `jetson-customize-uphy` ran and re-allocated lanes across PCIe controllers\n  (e.g. switched from `uphy0-config-7` to `uphy0-config-6` enabling\n  PCIe C3); the per-controller side now needs to be brought up.\n- `jetson-customize-mgbe` reports the QSFP path is wired but the kernel\n  doesn't probe its PCIe-side companion (rare; XFI configurations).\n\n**Prerequisites:**\n\n- Active profile with `reference_devkit:` + `custom_carrier:` blocks.\n- `\u003Csource.root_path>\u002FLinux_for_Tegra\u002F.git` exists\n  (`\u002Fjetson-init-source`).\n- `\u002Fjetson-derive-carrier` has run — carrier flash-conf fork is in\n  the overlay tracker.\n- `\u002Fjetson-customize-uphy` has run — its JSON sidecar at\n  `\u003Cworkspace>\u002Ftarget-platform\u002F\u003Cprofile-stem>.jetson-customize-uphy.json`\n  drives the per-controller `enable` decision.\n- Source-of-truth docs registered or supplied at prompt: Adaptation\n  Guide, Module Design Guide, SoC TRM.\n- **When `custom_carrier:` is present, both\n  `documents.custom_carrier_schematic` AND\n  `documents.custom_carrier_pinmux_xls` are REQUIRED.** Refuse the run\n  if either is missing — routing on a custom carrier cannot be guessed.\n  Reference-devkit-only profiles skip this check.\n- `dtc` on PATH.\n\n## Procedure (summary)\n\nFull step-by-step walkthrough lives in\n[`references\u002Fprocedure.md`](references\u002Fprocedure.md). High-level flow:\n\n1. Resolve active target + open source-of-truth documents (incl.\n   `\u003Ccarrier-pinmap>`, `\u003Cref-dtb>`, `\u003Cuphy-state>`). Refuse if\n   `\u003Cuphy-state>` is missing.\n2. Diff PCIe topology — devkit vs custom carrier — by decompiling\n   `\u003Cref-dtb>` and grepping the schematic for `PEX\u003CN>_*` net labels.\n3. `AskUserQuestion` (multiSelect) — which controllers to customize.\n4. Per-controller verification: pinmap + schematic + `pin_verifier.py`\n   for `PE\u003CN>_CLKREQ_L`, `PE\u003CN>_RST_L`, optional `PE\u003CN>_WAKE_L`.\n5. Auto-derive per-controller plan (`enable` from `\u003Cuphy-state>`,\n   `lanes` \u002F `speed` from Adaptation Guide, `mode` hard-pinned to\n   `\"rc\"`) → mandatory confirm-or-customize gate.\n6. Append per-controller `fragment@N` blocks (marker\n   `\u002F* custom-bsp: pcie:pcie@\u003Caddr> *\u002F`) to the composite custom\n   overlay `.dts` in `bsp_sources\u002F`. Pre-flight `dtc` + `fdtoverlay`.\n   Commit via the workflow's preview gate.\n   **Do not edit `ODMDATA`** — `\u002Fjetson-customize-uphy` already emitted\n   `pcie@N_status=…`, `pcie@N_max-link-speed`, `pcie@N_pcie-mode`,\n   `pcie@N_clk-scheme`, and `pcie-cN-endpoint-enable` in its single\n   atomic ODMDATA commit. This skill only translates the per-controller\n   plan into kernel-DT overlay fragments.\n7. (Step folded into Step 6 — overlay-only emission.)\n8. Cross-check ODMDATA vs overlay consistency. On a contradictory\n   row, **stop and ask the user how to recover the two commits.\n   Never run `git reset --hard` autonomously.**\n9. Write run-state JSON sidecar at\n   `\u003Cworkspace>\u002Ftarget-platform\u002F\u003Cprofile-stem>.jetson-customize-pcie.json`\n   + summary, then drive the downstream next-step chain via sequential\n   `AskUserQuestion` prompts per `references\u002Fprocedure.md` Step 9.\n   Never substitute a printed \"Next step: …\" line for the prompts.\n\n## Limitations\n\n- **Mode hard-pinned to RC.** Endpoint mode is only emitted when the\n  operator passes `mode_override=\"ep\"` in Step 5c.\n- **`enable` is derived, not asked.** UPHY-allocated controllers are\n  mandatorily `okay`; non-allocated are mandatorily `disabled`.\n- **No upstream BSP edits.** Output lands in `Linux_for_Tegra\u002F` +\n  `bsp_sources\u002F` only.\n- **Pre-flight overlay merge is a sanity check**, not the production\n  build. `\u002Fjetson-build-source` is authoritative.\n- **Flash-conf overlay registration is out of scope.** Owned by\n  `\u002Fjetson-build-source` Step 5.0a.\n\n## Troubleshooting\n\n- **`\u003Cuphy-state>` missing** → run `\u002Fjetson-customize-uphy` first.\n- **Slot doesn't enumerate after flash** → check `dmesg | grep pcie`;\n  re-verify ODMDATA `pcie@\u003CN>_status=okay` and the overlay fragment\n  agree (Step 8 table in\n  [`references\u002Fprocedure.md`](references\u002Fprocedure.md)).\n- **Link trains at wrong width** → confirm UPHY config in\n  `\u003Cuphy-state>` allocates the expected lane count; the kernel\n  fragment's `num-lanes` must match.\n- **`compatible` mismatch** → fix the composite root, not the\n  fragment. UEFI plugin-manager silently skips on mismatch.\n- **Contradictory ODMDATA-vs-overlay row** → ask the user; do not\n  auto-`git reset --hard`. See gotchas.\n- **Common pitfalls** — see\n  [`references\u002Fgotchas.md`](references\u002Fgotchas.md) (RC pinning, node-\n  address sourcing, stock-disabled controllers, intra-file handoff\n  with `jetson-customize-uphy`).\n\n## References\n\n- [`references\u002Fprocedure.md`](references\u002Fprocedure.md) — full nine-\n  step procedure (topology diff, plan derivation, overlay append,\n  ODMDATA cross-check, sidecar).\n- [`references\u002Fgotchas.md`](references\u002Fgotchas.md) — failure modes\n  + invariants (RC pinning, address sourcing, BPMP handoff).\n- [`..\u002F..\u002Fscripts\u002Fpin_verifier.py`](..\u002F..\u002Fscripts\u002Fpin_verifier.py)\n  — shared HSIO pin verifier (Step 4).\n- [`..\u002F..\u002Freferences\u002Fplatform_template.yaml`](..\u002F..\u002Freferences\u002Fplatform_template.yaml)\n  — `documents:` block consumed by Step 1.\n- [`..\u002F..\u002Fcontext\u002Fbsp-customization-workflow.md`](..\u002F..\u002Fcontext\u002Fbsp-customization-workflow.md#workflow-invariants)\n  — overlay edit protocol + commit message preview gate.\n- [`..\u002F..\u002Freferences\u002Fbsp-customization-kernel-dtb.md`](..\u002F..\u002Freferences\u002Fbsp-customization-kernel-dtb.md)\n  — composite overlay filename \u002F skeleton \u002F append protocol.\n- [`..\u002Fjetson-customize-uphy\u002FSKILL.md`](..\u002Fjetson-customize-uphy\u002FSKILL.md)\n  — sibling skill that owns UPHY lane allocation; its sidecar drives\n  the per-controller `enable` decision.\n- [`..\u002Fjetson-customize-pinmux\u002FSKILL.md`](..\u002Fjetson-customize-pinmux\u002FSKILL.md)\n  — sibling skill invoked by Step 4 (with operator confirmation) to\n  fix HSIO pin SFIO mismatches.\n- [`..\u002Fjetson-customize-mgbe\u002FSKILL.md`](..\u002Fjetson-customize-mgbe\u002FSKILL.md)\n  — sibling for MGBE controllers; shares the two-surface (ODMDATA\n  + overlay) pattern.\n- [`..\u002Fjetson-derive-carrier\u002FSKILL.md`](..\u002Fjetson-derive-carrier\u002FSKILL.md)\n  — must run first; produces the carrier flash-conf fork edited in\n  Step 6.\n- [`..\u002Fjetson-init-source\u002FSKILL.md`](..\u002Fjetson-init-source\u002FSKILL.md)\n  — produces the overlay tracker + bsp_sources repo this skill\n  commits into.\n","# Customize PCIe (per-controller status \u002F lanes \u002F speed)\n\n## Overview\n\nPCIe on Tegra264 (Thor, `pcie@C0..C5`) and Tegra234 (Orin,\n`pcie@C0..C10`) is split across multiple controllers that share the\nUPHY lane pool with USB3 \u002F MGBE \u002F UFS. Each controller's runtime\nbehavior is determined by **two surfaces, both required**:\n\n| Surface | Target | Authoritative for |\n|---|---|---|\n| ODMDATA `pcie@N_status=…` (+ `pcie@N_max-link-speed`, `pcie@N_pcie-mode`, `pcie@N_clk-scheme`, `pcie-cN-endpoint-enable`) | `\u002Fpcie\u002Fpcie@N` in BPMP DTB | UPHY lane power, refclk gating, controller-side power rails |\n| Kernel-DT overlay on `&pcieN` | `\u002Fbus@0\u002Fpcie@\u003Caddr>` in kernel DTB | Kernel probe, lane width, link speed, RC\u002FEP mode |\n\nSkipping the kernel overlay on a disable lets the kernel probe a\npowered-down PHY (link timeouts in dmesg). Skipping the ODMDATA token\non a disable leaves BPMP holding the PHY hot.\n\n**Agentic, not table-driven** — no controller table, no\n`questions.json`. Every controller, lane width, schematic-routed\nreceptacle, and authoritative DT node address is discovered at runtime\nfrom the docs + DTB + carrier pinmap.\n\nThe output is a **kernel-DT overlay commit only**. Per-controller\n`fragment@N` blocks are appended to the composite custom overlay\n`.dts` per\n[`..\u002F..\u002Freferences\u002Fbsp-customization-kernel-dtb.md`](..\u002F..\u002Freferences\u002Fbsp-customization-kernel-dtb.md)\nand committed to the `bsp_sources\u002F` hardware repo.\n`\u002Fjetson-build-source` compiles the composite to `.dtbo` and owns its\nMakefile + flash-conf registration.\n\n**This skill MUST NOT edit `ODMDATA=\"...\"`.** All ODMDATA tokens\n(`pcie@N_status=…`, `pcie@N_max-link-speed`, `pcie@N_pcie-mode`,\n`pcie@N_clk-scheme`, `pcie-cN-endpoint-enable`, plus the\n`uphyX-config-N` surface tokens and `UPHY_CONFIG=\"\"` clear) are\nemitted by `\u002Fjetson-customize-uphy` in a single atomic commit on the\ncarrier flash-conf fork. The allocation table this skill consumes\nfrom the UPHY sidecar already tells the operator which controllers\nare `okay` \u002F `disabled` \u002F per-lane sized; this skill only translates\nthat table into kernel-DT overlay fragments and verifies that the\noverlay agrees with the ODMDATA already committed by `customize-uphy`\n(consistency check in Step 8 — disagreement is reported, not silently\nfixed).\n\n## When to invoke\n\n- The user says \"configure PCIe\", \"enable PCIe controller\", \"set PCIe\n  num-lanes\", \"change PCIe link speed\", or asks to flip a\n  `pcie@N_status` token.\n- A specific PCIe slot or M.2 receptacle doesn't enumerate after\n  flash, OR the link trains at the wrong width \u002F speed.\n- `jetson-customize-uphy` ran and re-allocated lanes across PCIe controllers\n  (e.g. switched from `uphy0-config-7` to `uphy0-config-6` enabling\n  PCIe C3); the per-controller side now needs to be brought up.\n- `jetson-customize-mgbe` reports the QSFP path is wired but the kernel\n  doesn't probe its PCIe-side companion (rare; XFI configurations).\n\n**Prerequisites:**\n\n- Active profile with `reference_devkit:` + `custom_carrier:` blocks.\n- `\u003Csource.root_path>\u002FLinux_for_Tegra\u002F.git` exists\n  (`\u002Fjetson-init-source`).\n- `\u002Fjetson-derive-carrier` has run — carrier flash-conf fork is in\n  the overlay tracker.\n- `\u002Fjetson-customize-uphy` has run — its JSON sidecar at\n  `\u003Cworkspace>\u002Ftarget-platform\u002F\u003Cprofile-stem>.jetson-customize-uphy.json`\n  drives the per-controller `enable` decision.\n- Source-of-truth docs registered or supplied at prompt: Adaptation\n  Guide, Module Design Guide, SoC TRM.\n- **When `custom_carrier:` is present, both\n  `documents.custom_carrier_schematic` AND\n  `documents.custom_carrier_pinmux_xls` are REQUIRED.** Refuse the run\n  if either is missing — routing on a custom carrier cannot be guessed.\n  Reference-devkit-only profiles skip this check.\n- `dtc` on PATH.\n\n## Procedure (summary)\n\nFull step-by-step walkthrough lives in\n[`references\u002Fprocedure.md`](references\u002Fprocedure.md). High-level flow:\n\n1. Resolve active target + open source-of-truth documents (incl.\n   `\u003Ccarrier-pinmap>`, `\u003Cref-dtb>`, `\u003Cuphy-state>`). Refuse if\n   `\u003Cuphy-state>` is missing.\n2. Diff PCIe topology — devkit vs custom carrier — by decompiling\n   `\u003Cref-dtb>` and grepping the schematic for `PEX\u003CN>_*` net labels.\n3. `AskUserQuestion` (multiSelect) — which controllers to customize.\n4. Per-controller verification: pinmap + schematic + `pin_verifier.py`\n   for `PE\u003CN>_CLKREQ_L`, `PE\u003CN>_RST_L`, optional `PE\u003CN>_WAKE_L`.\n5. Auto-derive per-controller plan (`enable` from `\u003Cuphy-state>`,\n   `lanes` \u002F `speed` from Adaptation Guide, `mode` hard-pinned to\n   `\"rc\"`) → mandatory confirm-or-customize gate.\n6. Append per-controller `fragment@N` blocks (marker\n   `\u002F* custom-bsp: pcie:pcie@\u003Caddr> *\u002F`) to the composite custom\n   overlay `.dts` in `bsp_sources\u002F`. Pre-flight `dtc` + `fdtoverlay`.\n   Commit via the workflow's preview gate.\n   **Do not edit `ODMDATA`** — `\u002Fjetson-customize-uphy` already emitted\n   `pcie@N_status=…`, `pcie@N_max-link-speed`, `pcie@N_pcie-mode`,\n   `pcie@N_clk-scheme`, and `pcie-cN-endpoint-enable` in its single\n   atomic ODMDATA commit. This skill only translates the per-controller\n   plan into kernel-DT overlay fragments.\n7. (Step folded into Step 6 — overlay-only emission.)\n8. Cross-check ODMDATA vs overlay consistency. On a contradictory\n   row, **stop and ask the user how to recover the two commits.\n   Never run `git reset --hard` autonomously.**\n9. Write run-state JSON sidecar at\n   `\u003Cworkspace>\u002Ftarget-platform\u002F\u003Cprofile-stem>.jetson-customize-pcie.json`\n   + summary, then drive the downstream next-step chain via sequential\n   `AskUserQuestion` prompts per `references\u002Fprocedure.md` Step 9.\n   Never substitute a printed \"Next step: …\" line for the prompts.\n\n## Limitations\n\n- **Mode hard-pinned to RC.** Endpoint mode is only emitted when the\n  operator passes `mode_override=\"ep\"` in Step 5c.\n- **`enable` is derived, not asked.** UPHY-allocated controllers are\n  mandatorily `okay`; non-allocated are mandatorily `disabled`.\n- **No upstream BSP edits.** Output lands in `Linux_for_Tegra\u002F` +\n  `bsp_sources\u002F` only.\n- **Pre-flight overlay merge is a sanity check**, not the production\n  build. `\u002Fjetson-build-source` is authoritative.\n- **Flash-conf overlay registration is out of scope.** Owned by\n  `\u002Fjetson-build-source` Step 5.0a.\n\n## Troubleshooting\n\n- **`\u003Cuphy-state>` missing** → run `\u002Fjetson-customize-uphy` first.\n- **Slot doesn't enumerate after flash** → check `dmesg | grep pcie`;\n  re-verify ODMDATA `pcie@\u003CN>_status=okay` and the overlay fragment\n  agree (Step 8 table in\n  [`references\u002Fprocedure.md`](references\u002Fprocedure.md)).\n- **Link trains at wrong width** → confirm UPHY config in\n  `\u003Cuphy-state>` allocates the expected lane count; the kernel\n  fragment's `num-lanes` must match.\n- **`compatible` mismatch** → fix the composite root, not the\n  fragment. UEFI plugin-manager silently skips on mismatch.\n- **Contradictory ODMDATA-vs-overlay row** → ask the user; do not\n  auto-`git reset --hard`. See gotchas.\n- **Common pitfalls** — see\n  [`references\u002Fgotchas.md`](references\u002Fgotchas.md) (RC pinning, node-\n  address sourcing, stock-disabled controllers, intra-file handoff\n  with `jetson-customize-uphy`).\n\n## References\n\n- [`references\u002Fprocedure.md`](references\u002Fprocedure.md) — full nine-\n  step procedure (topology diff, plan derivation, overlay append,\n  ODMDATA cross-check, sidecar).\n- [`references\u002Fgotchas.md`](references\u002Fgotchas.md) — failure modes\n  + invariants (RC pinning, address sourcing, BPMP handoff).\n- [`..\u002F..\u002Fscripts\u002Fpin_verifier.py`](..\u002F..\u002Fscripts\u002Fpin_verifier.py)\n  — shared HSIO pin verifier (Step 4).\n- [`..\u002F..\u002Freferences\u002Fplatform_template.yaml`](..\u002F..\u002Freferences\u002Fplatform_template.yaml)\n  — `documents:` block consumed by Step 1.\n- [`..\u002F..\u002Fcontext\u002Fbsp-customization-workflow.md`](..\u002F..\u002Fcontext\u002Fbsp-customization-workflow.md#workflow-invariants)\n  — overlay edit protocol + commit message preview gate.\n- [`..\u002F..\u002Freferences\u002Fbsp-customization-kernel-dtb.md`](..\u002F..\u002Freferences\u002Fbsp-customization-kernel-dtb.md)\n  — composite overlay filename \u002F skeleton \u002F append protocol.\n- [`..\u002Fjetson-customize-uphy\u002FSKILL.md`](..\u002Fjetson-customize-uphy\u002FSKILL.md)\n  — sibling skill that owns UPHY lane allocation; its sidecar drives\n  the per-controller `enable` decision.\n- [`..\u002Fjetson-customize-pinmux\u002FSKILL.md`](..\u002Fjetson-customize-pinmux\u002FSKILL.md)\n  — sibling skill invoked by Step 4 (with operator confirmation) to\n  fix HSIO pin SFIO mismatches.\n- [`..\u002Fjetson-customize-mgbe\u002FSKILL.md`](..\u002Fjetson-customize-mgbe\u002FSKILL.md)\n  — sibling for MGBE controllers; shares the two-surface (ODMDATA\n  + overlay) pattern.\n- [`..\u002Fjetson-derive-carrier\u002FSKILL.md`](..\u002Fjetson-derive-carrier\u002FSKILL.md)\n  — must run first; produces the carrier flash-conf fork edited in\n  Step 6.\n- [`..\u002Fjetson-init-source\u002FSKILL.md`](..\u002Fjetson-init-source\u002FSKILL.md)\n  — produces the overlay tracker + bsp_sources repo this skill\n  commits into.\n",{"name":5,"license":15,"version":24,"metadata":25,"description":7},"0.0.1",{"tags":26,"author":31,"domain":32,"data-classification":33},[27,28,29,30],"bsp","phase-2","io","pcie","Jetson Team","meta","public","main","1c523aba5cdf867a79f078847075492d7778092a","skills\u002Fnvidia\u002Fjetson-customize-pcie",1,"https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills","https:\u002F\u002Fskills.x402.wtf","https:\u002F\u002Fgithub.com\u002Fthemusebook","https:\u002F\u002Fmusebook.trade","The official Github of musebook","2026-11-02 23:42:26",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add themusebook\u002Fskills --skill jetson-customize-pcie",{"tool":50,"command":51},"bunx","bunx skills add themusebook\u002Fskills --skill jetson-customize-pcie",{"tool":53,"command":54},"pnpm","pnpm dlx skills add themusebook\u002Fskills --skill jetson-customize-pcie","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fjetson-customize-pcie\u002FSKILL.md",true,[58,64,68,72,76,80],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"BENCHMARK.md","REFERENCE","参考文档",3832,"https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fjetson-customize-pcie\u002FBENCHMARK.md",{"path":65,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":66,"sourceHtmlUrl":67},"evals\u002Fevals.json",7057,"https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fjetson-customize-pcie\u002Fevals\u002Fevals.json",{"path":69,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fgotchas.md",2349,"https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fjetson-customize-pcie\u002Freferences\u002Fgotchas.md",{"path":73,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fprocedure.md",15200,"https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fjetson-customize-pcie\u002Freferences\u002Fprocedure.md",{"path":77,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":78,"sourceHtmlUrl":79},"skill-card.md",3760,"https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fjetson-customize-pcie\u002Fskill-card.md",{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"skill.oms.sig","OTHER","其他",5061,"https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fjetson-customize-pcie\u002Fskill.oms.sig",[87,96,103,110,117,124],{"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":92,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M7AB34SPKVSDRRG009PM1CZH","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","MIT","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-clipper\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-clipper\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M7AB18BH6N7KR7939HRNWVMQ","viem-integration","Integrate EVM blockchains using viem. Use when user says \"read blockchain data\", \"send transaction\", \"interact with smart contract\", \"connect to Ethereum\", \"use viem\", \"use wagmi\", \"wallet integration\", \"viem setup\", or mentions blockchain\u002FEVM development with TypeScript.","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fviem-integration\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":19},"01M7AB12GHGP48WCNXDQQ9222H","v4-security-foundations","Security-first Uniswap v4 hook development. Use when user mentions \"v4 hooks\", \"hook security\", \"PoolManager\", \"beforeSwap\", \"afterSwap\", or asks about V4 hook best practices, vulnerabilities, or audit requirements.","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fv4-security-foundations\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":19},"01M7AB0XM3PSR7V3Q2ZRR0Q0FB","v4-sdk-integration","App-layer SDK guide for building swap and liquidity experiences directly with the Uniswap v4 SDK. Use when user asks about \"v4 sdk\", \"uniswap v4\", \"v4 swap\", \"v4 liquidity\", \"PoolManager\", \"V4Planner\", \"StateView\", \"PositionManager\", \"pool state\", \"v4 position\", \"uniswap sdk\", or when building swap\u002Fliquidity UX directly with SDKs rather than via the Trading API.","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fv4-sdk-integration\u002FSKILL.md",[],[],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":19},"01M7AB0SGA93ASA588DJW4P9WT","v4-hook-generator","Generate Uniswap v4 hook contracts via OpenZeppelin MCP. Use when building custom swap logic, async swaps, hook-owned liquidity, custom curves, dynamic fees, MEV protection, limit orders, or oracle hooks.","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fv4-hook-generator\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},"01M7AAZYH75H4CS03WSW2EZ8DM","testing","For testing with Light Protocol programs and clients on localnet, devnet, and mainnet validation.","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftesting\u002FSKILL.md",[],[]]