pybind11 Release Preparation
pybind/pybind11
Opens the pybind11 release-preparation pull request: picking the release base, bumping the version in common.h and integrating the changelog, following docs/release.rst.
检查文档质量的工具。当用户提到检查文档质量、审查文档、文档检查、文档审查、lint文档, 或者提供文档URL/PR链接/本地文件路径要求检查时触发。支持通用性检查、教程检查和API文档检查。
$ npx skills add mindspore-ai/docs --skill doc-quality-checker-mindspore -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mindspore-ai/docs doc-quality-checker-mindspore --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mindspore-ai/docs.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/doc-quality-checker-mindspore .claude/skills/doc-quality-checker-mindspore && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "doc-quality-checker-mindspore" agent skill from https://github.com/mindspore-ai/docs/tree/master/skills/doc-quality-checker-mindspore into .claude/skills/doc-quality-checker-mindspore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-quality-checker-mindspore", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mindspore-ai/docs/tree/master/skills/doc-quality-checker-mindsporeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mindspore-ai/docs --skill doc-quality-checker-mindspore -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mindspore-ai/docs doc-quality-checker-mindspore --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mindspore-ai/docs.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/doc-quality-checker-mindspore .agents/skills/doc-quality-checker-mindspore && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "doc-quality-checker-mindspore" agent skill from https://github.com/mindspore-ai/docs/tree/master/skills/doc-quality-checker-mindspore into .agents/skills/doc-quality-checker-mindspore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-quality-checker-mindspore", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mindspore-ai/docs --skill doc-quality-checker-mindspore -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mindspore-ai/docs doc-quality-checker-mindspore --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mindspore-ai/docs.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/doc-quality-checker-mindspore .cursor/skills/doc-quality-checker-mindspore && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "doc-quality-checker-mindspore" agent skill from https://github.com/mindspore-ai/docs/tree/master/skills/doc-quality-checker-mindspore into .cursor/skills/doc-quality-checker-mindspore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-quality-checker-mindspore", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mindspore-ai/docs.git --path skills/doc-quality-checker-mindspore--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mindspore-ai/docs --skill doc-quality-checker-mindspore -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mindspore-ai/docs doc-quality-checker-mindspore --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mindspore-ai/docs.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/doc-quality-checker-mindspore .gemini/skills/doc-quality-checker-mindspore && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "doc-quality-checker-mindspore" agent skill from https://github.com/mindspore-ai/docs/tree/master/skills/doc-quality-checker-mindspore into .gemini/skills/doc-quality-checker-mindspore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-quality-checker-mindspore", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mindspore-ai/docs doc-quality-checker-mindsporeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mindspore-ai/docs --skill doc-quality-checker-mindspore -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mindspore-ai/docs.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/doc-quality-checker-mindspore .github/skills/doc-quality-checker-mindspore && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "doc-quality-checker-mindspore" agent skill from https://github.com/mindspore-ai/docs/tree/master/skills/doc-quality-checker-mindspore into .github/skills/doc-quality-checker-mindspore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-quality-checker-mindspore", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mindspore-ai/docs --skill doc-quality-checker-mindspore -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mindspore-ai/docs doc-quality-checker-mindspore --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mindspore-ai/docs.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/doc-quality-checker-mindspore .opencode/skills/doc-quality-checker-mindspore && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "doc-quality-checker-mindspore" agent skill from https://github.com/mindspore-ai/docs/tree/master/skills/doc-quality-checker-mindspore into .opencode/skills/doc-quality-checker-mindspore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-quality-checker-mindspore", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
doc-quality-checker-mindspore检查文档质量的工具。当用户提到检查文档质量、审查文档、文档检查、文档审查、lint文档, 或者提供文档URL/PR链接/本地文件路径要求检查时触发。支持通用性检查、教程检查和API文档检查。
Doc Quality Checker Mindspore is an agent skill from mindspore-ai/docs. 检查文档质量的工具。当用户提到检查文档质量、审查文档、文档检查、文档审查、lint文档, 或者提供文档URL/PR链接/本地文件路径要求检查时触发。支持通用性检查、教程检查和API文档检查。 输入类型:1) 可访问的HTML页面URL;2) AtomGit PR链接(分析PR中的文档diff); 3) 本地文件夹路径。自动根据内容判断执行 通用+教程 或 通用+API 的检查组合。
Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts (for example `rules/api_cpp_en_rules.md`, `rules/api_cpp_zh_rules.md` and `rules/api_python_consistency_rules.md`).
It sits in Development. It works with C++ and Python. The licence is Apache-2.0.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit b375e48. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 2 files in scripts/ (PowerShell and Shell), which the agent can run.
Shell commands in SKILL.md call:
bashFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
api.atomgit.comAlso links to:
atomgit.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Doc Quality Checker Mindspore loads about 2.1k tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 293 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from mindspore-ai/docs at commit b375e48, republished under its Apache-2.0 licence (© mindspore-ai). 293 words, ~2,119 tokens.
.claude/skills/doc-quality-checker-mindspore/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.解析用户提供的输入,判断输入类型并获取内容:
| 输入类型 | 识别方式 | 获取内容方法 |
|---|---|---|
| HTML页面URL | 以 http:// 或 https:// 开头且非Git链接 | 使用 WebFetch 工具获取页面内容 |
| AtomGit PR链接 | 包含 atomgit.com 的PR URL | 使用 AtomGit API + Token 获取PR内容 |
| 本地文件夹 | 本地路径 | 使用 read 工具读取文件内容 |
对于 AtomGit PR链接:
scripts/fetch_pr.ps1 或 scripts/fetch_pr.sh 获取PR详情和diff内容:scripts/fetch_pr.ps1(Windows)或 scripts/fetch_pr.sh(Linux/Mac)PRIVATE-TOKEN header 认证:--header 'PRIVATE-TOKEN: {token}'https://api.atomgit.com/api/v5/repos/{owner}/{repo}/pulls/{pr_number}脚本用法:
# Windows
.\scripts\fetch_pr.ps1 -Token <token> -Owner <owner> -Repo <repo> -PrNumber <pr_number>
# Linux/Mac
bash scripts/fetch_pr.sh <token> <owner> <repo> <pr_number>Token获取方式:
repo 权限根据输入内容特征自动选择检查组合:
| 特征 | 检查组合 |
|---|---|
| 包含"安装"、"快速开始"、"教程"、"开发指南"等 | 通用性检查 + 教程检查 |
| 包含"API"、"参数"、"返回值"、"函数"等 | 通用性检查 + API文档检查 |
| 包含代码示例、函数签名、参数说明 | 通用性检查 + API文档检查 |
| 包含步骤说明、截图指引、操作流程 | 通用性检查 + 教程检查 |
| 无法判断时默认 | 通用性检查 + 教程检查 |
规则文件为rules/doc_general_rules.md,支持所有格式文件的内容检查。
规则文件为rules/doc_tutorials_rules.md,支持Markdown、reStructuredText、Jupyter Notebook等格式文件的内容检查。
重要:API文档检查必须同时包含以下两部分,缺一不可:
执行格式检查 → 按文档语言类型应用对应规则文件:
rules/api_python_zh_rules.mdrules/api_python_en_rules.mdrules/api_cpp_zh_rules.mdrules/api_cpp_en_rules.md查找对应源文件 → 按方向查找配对文件:
__init__.py 中 from X import 原名 as 别名,所有别名的中文路径一并查找执行一致性检查 → 使用 rules/api_python_consistency_rules.md,按输入类型选择子检查项:
当输入为中文API文档时,需要查找对应的英文源文件:
| 英文源类型 | 后缀 | 说明 |
|---|---|---|
| Python代码 | .py | 包含docstrings的Python代码 |
| C++代码 | .h, .cpp | 包含 /// 注释的C++代码 |
| YAML配置 | .yaml, .yml | MindSpore算子/接口定义文件(Tensor方法等) |
| 英文RST目录 | .rst | API索引/目录文件(如 mindspore.nn.rst) |
典型路径映射(含别名场景):
=== 直接映射 ===
中文RST(Python): docs/api/api_python/mindspore/nn/tanh.rst
英文Python代码: mindspore/python/mindspore/nn/tanh.py
中文RST(Python): docs/api/api_python/mindspore/Tensor/mindspore.Tensor.gather.rst
英文YAML文档: mindspore/ops/op_def/yaml/doc/gather_doc.yaml
中文RST(Python): docs/api/api_python/ops/mindspore.ops.func_strided_slice.rst
英文YAML文档: mindspore/ops/op_def/yaml/doc/strided_slice_doc.yaml
中文RST(Python): docs/api/api_python/mint/mindspore.mint.func_empty.rst
英文YAML文档: mindspore/ops/api_def/function_doc/empty_doc.yaml
中文RST(Python): docs/api/api_python/mindspore.nn.rst
英文RST目录: docs/api/api_python_en/mindspore.nn.rst
中文MD(C++): mindspore/docs/api/cpp_api/classmindspore_1_1Tensor.md
英文C++头文件: mindspore/core/include/mindspore/core/ops/tensor_impl.h
=== 别名追踪映射 ===
中文RST(Python): docs/api/api_python/mint/mindspore.mint.nn.Hardshrink.rst
↓ 解析 mindspore.mint.nn.__init__.py:
from mindspore.nn.layer import HShrink as Hardshrink
↓ 再解析 mindspore.nn.layer.__init__.py 或 activation.py:
class HShrink(Cell) 定义于 mindspore/python/mindspore/nn/layer/activation.py
实际英文Python代码: mindspore/python/mindspore/nn/layer/activation.py (class HShrink)
中文RST(Python): docs/api/api_python/mint/mindspore.mint.nn.functional.linear.rst
↓ 解析 mindspore.mint.nn.functional.py:
from mindspore.ops.functional import dense as linear
↓ dense 是 auto_generate 算子,对应 YAML doc 以原名命名
实际英文YAML文档: mindspore/ops/op_def/yaml/doc/dense_doc.yaml
中文RST(Python): docs/api/api_python/mint/mindspore.mint.nn.functional.fold.rst
↓ 解析 mindspore.mint.nn.functional.py:
from mindspore.ops.auto_generate import fold_ext as fold
↓ 按函数名 fold_ext 搜 doc 找不到,反查 op 定义文件:
col2im_ext_op.yaml 中 name: fold_ext
实际英文YAML文档: mindspore/ops/op_def/yaml/doc/col2im_ext_doc.yamlYAML文档类型说明:
| 类型 | 路径 | 用途 |
|---|---|---|
| function_doc | mindspore/ops/op_def/yaml/doc/ | 函数接口文档 |
| method_doc | mindspore/ops/op_def/yaml/doc/ | 方法接口文档 |
| function_doc(alternative) | mindspore/ops/api_def/function_doc/ | 函数接口文档(备选) |
| method_doc(alternative) | mindspore/ops/api_def/method_doc/ | 方法接口文档(备选) |
查找策略(优先级从高到低):
直接路径推断:根据模块路径映射到对应 Python/YAML 文件
YAML 文档搜索:根据 API 名称搜索 op_def/yaml/doc/ 和 api_def/function_doc/ 等目录
别名导入链追踪:当直接推断和 YAML 搜索均未找到,或找到的内容不足以进行完整一致性检查时,必须追溯 import 别名链。具体做法:
mindspore.mint.nn.Hardshrink)__init__.py(如 mindspore/mint/nn/__init__.py)from X import Y as Z 或 from X import Z 语句,匹配别名 Z 是否等于 API 名称别名 → 真实类/函数名),并继续解析真实导入路径的 __init__.pyclass HShrink 或 def hardshrink)hardshrink_doc.yaml)用于辅助检查YAML op 定义文件反查:当第 3 步得到 auto_generate 函数名后,若按函数名搜 *_doc.yaml 找不到,搜索 op_def/yaml/*_op.yaml 中 name: 字段等于函数名的文件,其文件名前缀即为 doc 文件名:
例: col2im_ext_op.yaml 中 name: fold_ext
→ doc 文件为 col2im_ext_doc.yaml用户指定路径
汇总所有检查结果,按照"输出格式"生成 Markdown 报告保存到本地,在"基本信息"中列出本次使用的规则文件,告知用户路径。
report_{场景}.md(如 report_PR_1234.md),文件已存在则覆盖## PR #1234、## 本地文件: xxx.rst)生成Markdown格式的检查报告。
# 文档质量检查报告
## 基本信息
| 项目 | 内容 |
|------|------|
| 检查时间 | [时间戳] |
| 输入类型 | [HTML页面/PR链接/本地文件] |
| 输入来源 | [具体URL或路径] |
| 检查组合 | [通用+教程/通用+API] |
| 使用规则 | [本次使用的规则文件列表,如 `api_python_zh_rules.md`、`api_python_en_rules.md`] |
## 检查结果概览
| 问题等级 | 数量 |
|----------|------|
| 严重问题 | X |
| 一般问题 | X |
| 建议优化 | X |
| **总计** | **X** |
## 详细问题列表
- 以下仅给出输出格式参考,编号以规则文件中列举的实际编号为准。
- 本章节的问题分类不需要给出具体的规则文件来源。
### 通用性问题
| 编号 | 问题标题 | 优先级 | 位置 | 问题描述 | 建议修复 |
|------|----------|--------|------|----------|----------|
| G-L-01 | 单词拼写问题 | 严重 | 第X行 | XX单词拼写错误 | XX单词应改为XX |
| G-U-01 | 使用被动语态 | 一般 | 第X行 | XXX这句话使用了被动语态 | 建议将这句话改为XXX |
### 教程相关问题(如适用)
| 编号 | 问题标题 | 优先级 | 位置 | 问题描述 | 建议修复 |
|------|----------|--------|------|----------|----------|
| T-C-04 | 运行结果为 | 建议 | 第X行 | 运行结果中出现WARNING信息 | 建议删除运行结果中的WARNING信息 |
### API文档问题(如适用)
| 编号 | 问题标题 | 优先级 | 位置 | 问题描述 | 建议修复 |
|------|----------|--------|------|----------|----------|
| I-PY-R-01 | 缺失Summary描述 | 严重 | 第X行 | 函数/类缺少描述接口功能的Summary | 添加Summary描述 |
| I-PY-A-01 | 参数类型错误 | 严重 | 第X行 | 参数类型格式不正确 | 使用 `arg (int): description` 格式 |
| I-CPP-F-01 | 文件命名错误 | 严重 | 文件名 | class文件命名不符合规范 | 使用 `class{namespace}_{classname}.md` 格式 |
| I-YA-P-01 | 位置参数缺少类型 | 一般 | 第X行 | 缺少参数类型说明 | 使用 `input (Tensor): 描述` 格式 |
| I-PY-EF-02 | 示例缺少续行符 | 一般 | 第X行 | 多行代码缺少 `...` 续行符 | 类/函数定义后使用 `...` 续行 |
| I-YA-M-01 | 公式格式错误 | 建议 | 第X行 | 行公式未缩进 | 使用 `.. math::` + 缩进格式 |
### 一致性问题(如适用)
| 编号 | 问题类型 | 优先级 | 位置 | 中文文档 | 英文源码 | 建议修复 |
|------|----------|--------|------|----------|----------|----------|
| I-CN-D-03 | 参数名不一致 | 严重 | 中文RST第X行 / 英文源第Y行 | `**input_data**` | `input_data` | 确保参数名完全一致 |
| I-CN-A-03 | 参数类型不一致 | 严重 | 中文RST第X行 / 英文源第Y行 | `(Tensor)` | `(int)` | 确保参数类型一致 |
| I-CN-S-01 | 描述语义差异 | 一般 | 中文RST第X行 / 英文源第Y行 | 中文描述... | 英文描述... | 保持描述语义一致 |
| I-CN-T-02 | 返回值类型不一致 | 一般 | 中文RST第X行 / 英文源第Y行 | 返回:Tensor | Returns: int | 确保返回值类型一致 |
| I-PR-M-01 | 中文新增无英文对应 | 建议 | PR #123 | 新增 `xxx.rst` 文档 | 需在对应文件中添加注释 |
## 改进建议
1. [🔴高] 建议...
2. [🟠中] 建议...
3. [🟢低] 建议...© mindspore-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 9 other files (scripts) in skills/doc-quality-checker-mindspore of mindspore-ai/docs.
Open the folder on GitHubat commit b375e48
Doc Quality Checker Mindspore next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Doc Quality Checker Mindspore this skillmindspore-ai/docs | 167 | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| pybind11 Release Preparationpybind/pybind11 | 18k | — | ~1.7k | Automated safety check: Pass | Custom licence | |
| Paddle Eager GraphPaddlePaddle/Paddle | 24k | — | ~562 | Automated safety check: Pass | Apache-2.0 | |
| pybind11 Release Publicationpybind/pybind11 | 18k | — | ~2.5k | Automated safety check: Pass | Custom licence | |
| ExecuTorch Build Guidepytorch/executorch | 5.1k | — | ~2.3k | Automated safety check: Notes | Custom licence | |
| Ros2 Engineering Skillsdbwls99706/ros2-engineering-skills | 217 | — | ~3k | Automated safety check: Pass | Apache-2.0 |
pybind/pybind11
Opens the pybind11 release-preparation pull request: picking the release base, bumping the version in common.h and integrating the changelog, following docs/release.rst.
PaddlePaddle/Paddle
A skill your agent uses when navigating Paddle eager-mode (dynamic graph) source code, tracing forward/backward execution, debugging autograd issues, understanding PyLayer, or investigating…
pybind/pybind11
Walks a maintainer through publishing a pybind11 release after the preparation PR merges, with preflight checks, confirmations before each push and a GitHub release.
pytorch/executorch
Builds ExecuTorch from source: the Python package, C++ runtime, model runners, Android and iOS cross-compilation and backend-specific builds, with environment checks.
dbwls99706/ros2-engineering-skills
ROS 2 engineering: rclcpp/rclpy, colcon/ament, launch, QoS/DDS, tf2/URDF, ros2control, Nav2, MoveIt 2, sensors, runtime/artifact provenance, and hardware safety.
BlueAndi/Pixelix
A skill your agent uses when writing, reviewing, or refactoring C/C++ firmware code in this repository (src/, lib/, test/) — creating or editing .h/.hpp/.cpp files, applying MISRA-oriented and…
mindspore-ai/docs
Generate documentation for Python APIs, functions, classes, and modules — including English docstrings and Chinese RST docs.
mindspore-ai/docs
MindSpore 文档发布新分支时,链接更替与组件清洗技能,用于清理组件和替换链接. An agent skill from mindspore-ai/docs.
Categories
检查文档质量的工具。当用户提到检查文档质量、审查文档、文档检查、文档审查、lint文档, 或者提供文档URL/PR链接/本地文件路径要求检查时触发。支持通用性检查、教程检查和API文档检查。. Doc Quality Checker Mindspore is an agent skill from mindspore-ai/docs.
Doc Quality Checker Mindspore fits situations like: development work in your project.
Run `npx skills add mindspore-ai/docs --skill doc-quality-checker-mindspore -a claude-code`. Or copy the skill folder (skills/doc-quality-checker-mindspore in mindspore-ai/docs) into .claude/skills/doc-quality-checker-mindspore in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mindspore-ai/docs --skill doc-quality-checker-mindspore -a codex`. Or copy the skill folder (skills/doc-quality-checker-mindspore in mindspore-ai/docs) into .agents/skills/doc-quality-checker-mindspore in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mindspore-ai/docs --skill doc-quality-checker-mindspore -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/doc-quality-checker-mindspore, .gemini/skills/doc-quality-checker-mindspore, .github/skills/doc-quality-checker-mindspore and .opencode/skills/doc-quality-checker-mindspore in your project.
Going by SKILL.md and its folder, Doc Quality Checker Mindspore needs PowerShell and a shell for the scripts in its folder and the command-line tools its instructions call (bash). Our summary lists: Python 3; A Bash shell; PowerShell.
SKILL.md names 2 domains. In commands or code: api.atomgit.com; the agent is likely to contact it when it follows the instructions. As links in the text: atomgit.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Doc Quality Checker Mindspore is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.1k tokens (SKILL.md is roughly 8.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Doc Quality Checker Mindspore: pybind11 Release Preparation (pybind/pybind11, 18k stars), Paddle Eager Graph (PaddlePaddle/Paddle, 24k stars), pybind11 Release Publication (pybind/pybind11, 18k stars) and ExecuTorch Build Guide (pytorch/executorch, 5.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
mindspore-ai (a GitHub organization) maintains it in mindspore-ai/docs, which has 167 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 10, 2026.
Source: mindspore-ai/docs on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.