跳到主内容
智客 ZICQ

技能库 智客分类:文档办公 jetson-link-docs

Jetson Link Docs

装入预下沉 Jetson参考道克(开发者指南,设计指南,pinmux,示意图)进入活性剖面文件块. 在磁盘上装入文件后使用; 不用于下载 .

1103 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

装入预下沉 Jetson参考道克(开发者指南,设计指南,pinmux,示意图)进入活性剖面文件块. 在磁盘上装入文件后使用; 不用于下载 .

何时用

官方 description 未单独写出 Use when。按规范,代理会在用户任务与这段 description 的关键词匹配时激活本技能。

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:jetson-link-docs、Overview、When to invoke、Procedure、Resolve the active target、Load the document-slot schema。

文件分析

文件分析:除 SKILL.md 外,正文引用了 references/platform_template.yaml、references/bsp-platforms-catalogue.md,属于带资源的技能包,这些文件按需再读。

官方 description(原文)

Bind pre-downloaded Jetson reference docs (developer guide, design guide, pinmux, schematics) into the active profile documents block. Use after staging docs on disk; not for downloading.

jetson-link-docsOverviewWhen to invokeProcedureResolve the active targetLoad the document-slot schemaResolve `documents.root_path`Resolve the product tokenScan and auto-matchMatch policy per fieldManual prompts for unmatched fieldsWrite the `documents:` block back to the profile

· 许可:Apache-2.0

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
jetson-link-docs
description
Bind pre-downloaded Jetson reference docs (developer guide, design guide, pinmux, schematics) into the active profile documents block. Use after staging docs on disk; not for downloading.
许可
Apache-2.0
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。
指令中引用的文件 · 2
  • references/platform_template.yaml
  • references/bsp-platforms-catalogue.md

以下路径提取自原文;文件是否齐全请以来源仓库中的完整目录为准。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

该技能引用了附属文件,请从来源获取完整目录;仅复制 SKILL.md 可能缺少依赖。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「jetson-link-docs」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-279242b66f1974c4-Jetson-%E9%93%BE%E6%8E%A5%E6%96%87%E6%A1%A3.html
请存为 .cursor/skills/jetson-link-docs/SKILL.md 或 .claude/skills/jetson-link-docs/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
该技能还带 scripts/、references/、assets/ 等文件,请从 https://github.com/nvidia/skills 取完整目录,不要只建一个 SKILL.md。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/nvidia/skills' --list

npx skills add 'https://github.com/nvidia/skills' --skill 'jetson-link-docs'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版
--- name: jetson-link-docs description: >- Bind pre-downloaded Jetson reference docs (developer guide, design guide, pinmux, schematics) into the active profile documents block. Use after staging docs on disk; not for downloading. version: 0.0.1 license: "Apache-2.0" metadata: data-classification: public author: "Jetson Team" tags: - target-platform - documents - setup domain: meta --- # jetson-link-docs ## Overview This skill **writes** the `documents:` block of the active Jetson / IGX target-platform profile YAML so downstream skills (`/jetson-generate-kb`, `/jetson-customize-pinmux`, camera / pcie / uphy, etc.) can resolve doc paths by name. It walks the user through every document slot in the profile schema, tries to auto-bind each slot to a file under `/` via case-insensitive glob matching, and writes the resulting paths back into the active profile. Scope is **registering pointers only** — this skill does **not** fetch or download. The files must already exist on disk under `/`. ## When to invoke - After `/jetson-init-target` finishes and the user has documents on disk to register. - The user wants to add, change, or remove document references on an existing profile. - A downstream skill (e.g. `jetson-generate-kb`) reports "no documents recorded" and the user wants to fix that. ## Procedure ### Resolve the active target Resolve the active profile + `` per the contract in [`../../context/target-platform-contract.md`](../../context/target-platform-contract.md). Cache the loaded profile in memory — this skill mutates it in the "Write the `documents:` block back to the profile" step. ### Load the document-slot schema Load [`../../references/platform_template.yaml`](../../references/platform_template.yaml). Parse the `documents:` block. Each per-document field is marked ``. Use the marker description as prompt text verbatim. Match markers with the regex `^<(REQUIRED|OPTIONAL|DERIVED):\s*(.*)>$` after YAML parsing strips surrounding quotes. Skip `custom_carrier_schematic` and `custom_carrier_pinmux_xls` entirely when the active profile has no `custom_carrier:` block — both are meaningless without one. This filter applies through the "Scan and auto-match" and "Manual prompts for unmatched fields" steps. ### Resolve `documents.root_path` Default: `/Documents`. If the profile already records `documents.root_path`, use it. Otherwise, if `/Documents/` exists, use it (the field is **omitted** from the written profile — downstream skills fall back to the workspace default). If neither is available, prompt the user for an absolute path, or accept Enter / `cancel` to skip the auto-scan. A user-provided path that doesn't exist is treated as skipped (warn, don't refuse — the field is OPTIONAL); manual prompts in the "Manual prompts for unmatched fields" step still run. ### Resolve the product token Read the **Product Token** column from [`../../references/bsp-platforms-catalogue.md`](../../references/bsp-platforms-catalogue.md) for the row matching `reference_devkit.name`. The token is a case-insensitive glob fragment (e.g. `*orin*nano*`, `*agx*thor*`) consumed by the fallback patterns in the "Scan and auto-match" step. If `reference_devkit.name` has no row in the catalogue, log a warning and proceed without a product-token fallback — the "Scan and auto-match" step still works with strictly SKU-keyed matching. For custom carriers, derive `` from `custom_carrier.name` using this recipe: lowercase, replace each space with `*`, wrap in `*` on both ends. E.g. "Acme Vision X1" → `*acme*vision*x1*`. ### Scan and auto-match Skip this step entirely if `documents.root_path` did not resolve in the "Resolve `documents.root_path`" step (no scan target → no auto-suggest; fall through to manual prompts in the "Manual prompts for unmatched fields" step). Scan the directory once (one level deep) and try to auto-match each remaining `` field using the case-insensitive globs below. Use the lower-case `module.id` / `carrier.id` / `custom_carrier.id` strings from the profile in the SKU column. | Field | SKU glob (primary) | Product-token glob (fallback) | |---|---|---| | `bsp_developer_guide` | `*developer*guide*.pdf`, `*BSP*guide*.pdf` | _(no fallback — pattern is product-agnostic)_ | | `soc_tech_ref_manual` | `*TRM*.pdf`, `*tech*ref*manual*.pdf` | _(no fallback — same)_ | | `module_data_sheet` | `**data*sheet*.pdf`, `**datasheet*.pdf` | `data*sheet*.pdf`, `datasheet*.pdf` | | `module_design_guide` | `**design*guide*.pdf`, `**PDG*.pdf` | `design*guide*.pdf`, `PDG*.pdf` | | `module_thermal_design_guide` | `**thermal*.pdf` (covers "Thermal Design Guide" / "TDG") | `thermal*.pdf` | | `module_schematic` | `**schem*.pdf` | `schem*.pdf` | | `carrier_board_spec` | `**board*spec*.pdf`, `**spec*.pdf` | `carrier*spec*.pdf` | | `carrier_schematic` | `**schem*.pdf` | `carrier*schem*.pdf` | | `custom_carrier_schematic` | `**schem*.pdf` (only if custom carrier) | `schem*.pdf` (only if custom carrier) | | `ref_devkit_pinmux_xls` | `**pinmux*.xls*` (matches `.xls`, `.xlsx`, `.xlsm`) | `pinmux*.xls*` | | `custom_carrier_pinmux_xls` | `**pinmux*.xls*` (only if custom carrier) | `pinmux*.xls*` (only if custom carrier) | `` is the catalogue-resolved product token; `` is derived from `custom_carrier.name` per the "Resolve the product token" step. Tokens already include leading/trailing `*`, so the table does not repeat them. ### Match policy per field For each field that has auto-match results: - Take the **union** of hits across the SKU glob and the product- token glob, then **deduplicate by absolute path** — a file matched by both globs counts once. - **Exactly 1 unique hit** → show the path and prompt `use this? (yes/no, default yes)`. On `yes`, record it and **skip** the manual prompt for that field. On `no`, fall through to the manual prompt in the "Manual prompts for unmatched fields" step. - **0 hits** → skip auto-suggest entirely for that field; fall through to the "Manual prompts for unmatched fields" step. - **2+ unique hits** → present them as a numbered list in the "Manual prompts for unmatched fields" step so the user can pick by number rather than typing a path; include a `skip / NA` option. Never silently bind a multi-hit candidate. - **Never silently bind** without user confirmation — wrong-schematic / wrong-pinmux bindings are real and costly. If `documents.root_path` is folder-organised one level deeper than flat (NVIDIA archives often are: `Schematics/`, `Design-Guides/`, `Pinmux/`, etc.), the file globs may return zero hits even when the right documents exist. v0.2 only scans one level deep — when 0 hits is suspicious (`documents.root_path` exists but no fields auto-bound), surface the limitation to the user and offer to fall through to manual prompts. ### Manual prompts for unmatched fields For every field that wasn't auto-bound (and wasn't filtered out in the "Load the document-slot schema" step), prompt using the marker description from the "Load the document-slot schema" step as prompt text, in document order. Accept Enter and `NA` interchangeably as "skip this field". When the "Match policy per field" step produced 2+ candidate hits for a field, present them as a numbered list with a `skip / NA` option rather than asking for a free-text path. Validate that user-provided paths exist on disk (warn if not, but do not refuse — the user may be recording a planned path). URLs (values starting with `http://`, `https://`, or `ftp://`) are accepted verbatim and not validated. ### Write the `documents:` block back to the profile Edit `target-platform/.yaml` in place. Preserve all other top-level blocks (`reference_devkit:`, `custom_carrier:`, `bsp_image:`, `source:`) and their comments verbatim. Write only the fields the user provided — omit skipped / `NA` fields entirely (no `NA` placeholders, no empty keys). Edge behavior: when every field was skipped (including `documents.root_path`), drop the `documents:` block entirely from the profile — never write `documents: {}` or a block of `NA` values. When only `documents.root_path` was provided (no per-document binding), record it alone — the path has value as a hint for future re-runs. On re-run with an existing `documents:` block, merge: existing bindings are preserved unless the user picks a new file or `NA`; newly bound fields are added. ### Confirm Print a summary: - Profile path written. - `documents.root_path` — resolved value (or "default — omitted"). - Auto-bound fields: count + per-field one-line list. - Manually entered fields: count + list. - Skipped fields: count. - A reminder that `jetson-generate-kb` re-reads `documents.*` and should be re-run if a KB exists. If a downstream skill triggered this run, tell the user to re-issue their original request; do not silently re-trigger it. ## Gotchas - **Active profile must exist.** This skill writes back to whichever profile is active. If no profile is active, refuse and route to `jetson-set-target` / `jetson-init-target`. - **Product-token globs are intentionally broad.** A token like `*orin*nano*` matches both Orin-Nano-specific docs and combined Orin-NX/Nano docs (e.g. `Jetson-Orin-NX-Nano-Design-Guide_…`). That is usually correct for module-side docs (NVIDIA ships combined manuals), but verify on schematic / pinmux / spec fields where wrong-product binding is costly. - **Update `bsp-platforms-catalogue.md` when adding new product rows.** The **Product Token** column is consumed by the "Resolve the product token" step; a missing token degrades the auto-scan to SKU-only matching (the skill warns and continues, but doc-rich `documents.root_path` scans will degrade silently from "5 auto-binds" to "fewer auto- binds"). - **Use a round-tripping YAML loader.** the "Write the `documents:` block back to the profile" step mutates an existing YAML file. Plain `yaml.safe_load` + `yaml.safe_dump` loses comments, block ordering, and quoting style — use `ruamel.yaml` or equivalent so hand-edited fields and comments survive. - **Re-runnable.** Re-running merges new bindings; existing bindings are preserved unless the user explicitly changes them. Safe to invoke as part of a profile refresh. ## Prerequisites - Active target profile resolved per `../../context/target-platform-contract.md`. - Documents available either under the recorded `documents.root_path`, under default `/Documents/`, or as user-provided paths / URLs during manual prompts. A missing root only disables auto-scan; it is not a hard prerequisite. - `ruamel.yaml` or another round-tripping YAML writer for the profile edit step. ## Limitations - Registers pointers only; never downloads, copies, or renames files. - Per-document field set is fixed to the schema in `../../references/platform_template.yaml` — no ad-hoc keys. - Glob matching is filename-only; bad filenames in `documents.root_path` will under-bind and require manual selection. ## Troubleshooting - **`documents.root_path` missing** — auto-scan is skipped. Provide an absolute root path, enter individual document paths / URLs manually, or skip the fields you do not want to bind. - **Multiple files match a single slot** — the skill stops and prompts; pick or rename the file. Example: two `Jetson-Linux-Developer-Guide*.pdf` files → keep the active version, rename the stale one. - **Profile comments lost after write** — a non-round-tripping YAML writer was used; switch to `ruamel.yaml` and rerun against a fresh pristine copy. - **Validation fails because a binding points outside `documents.root_path`** — `documents.*` are relative paths only; move the file under the root and retry. ## References - [`../../context/target-platform-contract.md`](../../context/target-platform-contract.md) — target-platform contract; this skill consumes and mutates the active profile. - [`../../references/bsp-platforms-catalogue.md`](../../references/bsp-platforms-catalogue.md) — source of the **Product Token** column for the "Resolve the product token" step. - [`../../references/platform_template.yaml`](../../references/platform_template.yaml) — schema for the `documents:` block (source of truth for prompts and field list). - [`../jetson-init-target/SKILL.md`](../jetson-init-target/SKILL.md) — sibling skill that authors target identity (`reference_devkit:`, optional `custom_carrier:`). - [`../jetson-init-image/SKILL.md`](../jetson-init-image/SKILL.md) — sibling skill that authors `bsp_image:`. - [`../jetson-init-source/SKILL.md`](../jetson-init-source/SKILL.md) — sibling skill: clones shared repos and handles `source.root_path` overrides. - [`../jetson-generate-kb/SKILL.md`](../jetson-generate-kb/SKILL.md) — sibling skill: consumes the `documents:` block this skill writes.

相关技能

文档办公

Ontology

为结构化的代理内存和可堆肥技能所打入的知识图. 在创建/征服实体(Person, project, Task, Evention, Document)时使用,链接相关对象,强制约束,规划多步动作作为图变,或技能需要共享状态时使用. 触发到"记住","我知道什么","链接X到Y",…

文档办公

Nano Pdf

使用纳米-pdf CLI编辑带有自然语言指令的PDF.

文档办公

Word / DOCX

创建,检查,并编辑有可靠样式的Microsoft Word文档和DOCX文件,编号,跟踪更改,表格,章节,并进行相容性检查. 当 (1) 任务涉及 Word 或 ".docx " 时使用; (2) 文件包括跟踪的更改,评论,字段,表格,模板,或页面布局限制; (3) 文档必须在不…

文档办公

Api Gateway

通过 Maton 网关调用第三方 API, 它为用户已经连接的应用程序注入证书 。 当用户命名一个连接的应用程序和其中的具体行动时使用此技能——读取一个邮箱,查询一个CMM,归档一个问题,更新一个电子表格,通过一个连接的搜索或刮取提供者运行一个查询. 每一次通话都到用户连接的应用…