← 返回 Skills 市场
cinience

Aliyun Platform Docs Review

作者 cinience · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
86
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install aliyun-platform-docs-review
功能描述
Use when reviewing latest Alibaba Cloud product docs and OpenAPI docs by product name, then output detailed prioritized improvement suggestions with evidence...
使用说明 (SKILL.md)

Alibaba Cloud Product Docs + API Docs Reviewer

Use this skill when the user gives a product name and asks for an end-to-end documentation/API quality review.

What this skill does

  1. Resolve product from latest OpenAPI metadata.
  2. Fetch latest API docs for default version.
  3. Discover product/help-doc links from official product page.
  4. Produce a structured review report with:
  • score
  • evidence
  • prioritized suggestions (P0/P1/P2)

Workflow

Run the bundled script:

python skills/platform/docs/aliyun-platform-docs-review/scripts/review_product_docs_and_api.py --product "\x3Cproduct name or product code>"

Example:

python skills/platform/docs/aliyun-platform-docs-review/scripts/review_product_docs_and_api.py --product "ECS"

Output policy

All generated artifacts must be written under:

output/aliyun-platform-docs-review/

For each run, the script creates:

  • review_evidence.json
  • review_report.md

Reporting guidance

When answering the user:

  1. State resolved product + version first.
  2. Summarize the score and the top 3 issues.
  3. List P0/P1/P2 recommendations with concrete actions.
  4. Provide source links used in the report.

Validation

mkdir -p output/aliyun-platform-docs-review
for f in skills/platform/docs/aliyun-platform-docs-review/scripts/*.py; do
  python3 -m py_compile "$f"
done
echo "py_compile_ok" > output/aliyun-platform-docs-review/validate.txt

Pass criteria: command exits 0 and output/aliyun-platform-docs-review/validate.txt is generated.

Output And Evidence

  • Save artifacts, command outputs, and API response summaries under output/aliyun-platform-docs-review/.
  • Include key parameters (region/resource id/time range) in evidence files for reproducibility.

Prerequisites

  • Configure least-privilege Alibaba Cloud credentials before execution.
  • Prefer environment variables: ALICLOUD_ACCESS_KEY_ID, ALICLOUD_ACCESS_KEY_SECRET, optional ALICLOUD_REGION_ID.
  • If region is unclear, ask the user before running mutating operations.

References

  • Review rubric: references/review-rubric.md
安全使用建议
This skill appears to perform public web/API scraping of Alibaba Cloud docs and produce a report, which matches its description. However, SKILL.md asks you to set Alibaba Cloud credentials and to include region/resource IDs in evidence, while the manifest declares no env vars and the visible script doesn't use credentials — that mismatch is concerning. Before installing or running: - Ask the skill author/maintainer to explain why credentials are needed and update the manifest if they truly are required. - Review the rest of the script (the truncated portion) to confirm there is no code that uses or exfiltrates credentials or other secrets. - Do not provide production credentials; if credentials are truly needed, provide a tightly-scoped read-only key in a sandbox account or use a throwaway test key. - Run the script in an isolated environment (no access to sensitive networks) and inspect output/ files to ensure they don't inadvertently include secrets or sensitive resource identifiers. - If you cannot get a satisfactory explanation for the credential requirement, treat the credential request as unnecessary and avoid supplying secrets.
功能分析
Type: OpenClaw Skill Name: aliyun-platform-docs-review Version: 1.0.0 The skill is designed to automate the quality audit of Alibaba Cloud product and API documentation. The core logic in `scripts/review_product_docs_and_api.py` fetches public metadata and documentation pages from official domains (api.aliyun.com and www.aliyun.com) to generate a structured improvement report. There is no evidence of data exfiltration, credential theft, or malicious execution; the script uses standard libraries and performs only read-only operations on public endpoints.
能力评估
Purpose & Capability
Name/description claim a docs + API reviewer for Alibaba Cloud and the included script implements web/API fetches and analysis of public metadata — that aligns. However SKILL.md asks the user to “Configure least-privilege Alibaba Cloud credentials” (ALICLOUD_ACCESS_KEY_ID, ALICLOUD_ACCESS_KEY_SECRET, optional region) even though the skill manifest declares no required env vars and the visible script does not reference environment credentials. This inconsistency is disproportionate to the stated purpose.
Instruction Scope
The SKILL.md instructs the agent to collect and save evidence under output/..., and to include key parameters (region/resource id/time range) for reproducibility. Asking to capture region/resource IDs may cause collection of identifiers that could be sensitive. The script (as provided) fetches public endpoints (api.aliyun.com, www.aliyun.com, help.aliyun.com) which is expected, but the instructions also advise configuring cloud credentials and to ask before running mutating operations — the script appears read-only in the shown portion, so these extra instructions constitute scope creep and possible overreach.
Install Mechanism
No install spec; this is an instruction-only skill with a bundled Python script. No downloads or external installers are executed by the skill manifest itself, which is low-risk from an install-mechanism perspective.
Credentials
Manifest lists no required env vars, but SKILL.md explicitly recommends providing Alibaba Cloud credentials via ALICLOUD_ACCESS_KEY_ID / ALICLOUD_ACCESS_KEY_SECRET and possibly region. The provided script does HTTP(S) requests and parsing of public pages and shows no use of credentials in the visible code. Requesting credentials (and asking evidence to include region/resource ids) without code-level justification is disproportionate and could enable accidental disclosure of secrets if users follow guidance.
Persistence & Privilege
always is false, no service installation, and the skill writes only to a local output/ directory per SKILL.md. It does not request persistent agent-level privileges or modify other skills. This is low-privilege.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install aliyun-platform-docs-review
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /aliyun-platform-docs-review 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release of aliyun-platform-docs-review skill. - Enables end-to-end review of Alibaba Cloud product and OpenAPI documentation by product name. - Generates a structured quality report with scores, evidence, and prioritized improvement suggestions (P0/P1/P2). - Supports output of review artifacts and evidence to a dedicated directory for transparency and reproducibility. - Includes clear workflow, reporting guidance, and validation steps for users.
元数据
Slug aliyun-platform-docs-review
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Aliyun Platform Docs Review 是什么?

Use when reviewing latest Alibaba Cloud product docs and OpenAPI docs by product name, then output detailed prioritized improvement suggestions with evidence... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 86 次。

如何安装 Aliyun Platform Docs Review?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install aliyun-platform-docs-review」即可一键安装,无需额外配置。

Aliyun Platform Docs Review 是免费的吗?

是的,Aliyun Platform Docs Review 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Aliyun Platform Docs Review 支持哪些平台?

Aliyun Platform Docs Review 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Aliyun Platform Docs Review?

由 cinience(@cinience)开发并维护,当前版本 v1.0.0。

💬 留言讨论