← 返回 Skills 市场

Aliyun Modelstudio Crawl And Skill

Name: Aliyun Modelstudio Crawl And Skill
Author: cinience

作者 cinience · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

100

总下载

当前安装

版本数

在 OpenClaw 中安装

/install aliyun-modelstudio-crawl-and-skill

功能描述

Use when refreshing the Model Studio models crawl and regenerate derived summaries and `skills/ai/**` skills. Use when the models list or generated skills mu...

使用说明 (SKILL.md)

Category: task

Alibaba Cloud Model Studio Crawl and Skill Generation

Prerequisites

Node.js (for npx)
Python 3
Network access to the models page

Workflow

Crawl models page (raw markdown)

npx -y @just-every/crawl \"https://help.aliyun.com/zh/model-studio/models\" > alicloud-model-studio-models.md

Rebuild summary (models + API/usage links)

python3 skills/ai/misc/aliyun-modelstudio-crawl-and-skill/scripts/refresh_models_summary.py

Regenerate skills (creates/updates skills/ai/**)

python3 skills/ai/misc/aliyun-modelstudio-crawl-and-skill/scripts/refresh_alicloud_skills.py

Outputs

alicloud-model-studio-models.md: raw crawl output
output/alicloud-model-studio-models-summary.md: cleaned summary
output/alicloud-model-studio-models.json: structured model list
output/alicloud-model-studio-skill-scan.md: skill coverage report
skills/ai/**: generated skills

Notes

Do not invent model IDs or API endpoints; only use links present on the models page.
After regeneration, update README.md, README.en.md, and README.zh-TW.md if skills list changed.

Validation

mkdir -p output/aliyun-modelstudio-crawl-and-skill
for f in skills/ai/misc/aliyun-modelstudio-crawl-and-skill/scripts/*.py; do
  python3 -m py_compile "$f"
done
echo "py_compile_ok" > output/aliyun-modelstudio-crawl-and-skill/validate.txt

Pass criteria: command exits 0 and output/aliyun-modelstudio-crawl-and-skill/validate.txt is generated.

Output And Evidence

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

References

Source list: references/sources.md

安全使用建议

This skill appears to do what it says (crawl the Aliyun Model Studio page and generate summaries and suggested skills), but review a few things before running it: - Path mismatch: SKILL.md runs scripts at skills/ai/misc/.../scripts/*.py but the repository has scripts/refresh_*.py at top-level scripts/. Confirm the expected location or adjust commands to point to the included files; otherwise the workflow may fail or the scripts may compute wrong ROOT paths. - npx risk: The workflow uses `npx -y @just-every/crawl` which transiently downloads and executes an npm package. npx executes arbitrary code from the npm registry; inspect the @just-every/crawl package source (and pin a specific version) or replace it with a known-safe fetch mechanism (curl/wget, or a locally vetted crawler) if you want to reduce risk. - Run in a sandbox: Because the crawl step executes third-party code and the scripts write files, run this workflow in an isolated environment (container or VM) until you are comfortable with the behavior and outputs. - Inspect outputs: The Python scripts write JSON/markdown under output/ and may include model IDs and URLs. Ensure you do not unintentionally publish sensitive identifiers. The instructions request recording region/resource IDs — avoid including secrets/credentials. Given the inconsistencies and the use of npx, this is suspicious rather than clearly benign. If the maintainer can confirm the intended file layout and justify using the specific @just-every/crawl package (or provide a pinned, vetted alternative), the assessment could be upgraded.

功能分析

Type: OpenClaw Skill Name: aliyun-modelstudio-crawl-and-skill Version: 1.0.0 The skill bundle is designed to crawl Alibaba Cloud Model Studio documentation and generate structured summaries and skill coverage reports. The workflow uses standard tools like `npx` for crawling and Python scripts (scripts/refresh_models_summary.py and scripts/refresh_alicloud_skills.py) for data processing, with no evidence of data exfiltration, malicious execution, or prompt injection.

能力评估

ℹ Purpose & Capability

The name/description match the included Python scripts which parse a crawl and produce summaries and skill suggestions. However, SKILL.md lists Node.js/npx as a prerequisite while the skill metadata declares no required binaries; the SKILL.md command paths reference scripts under skills/ai/misc/... but the shipped files live at scripts/*.py. These mismatches mean the runtime layout the instructions expect may not match how the skill is installed or executed.

⚠ Instruction Scope

Instructions tell the agent to run an npx command that downloads and executes @just-every/crawl against https://help.aliyun.com and then run bundled Python scripts that read/write files. The crawling step contacts an external site (expected) but uses npx which will fetch and execute code from npm (arbitrary code execution). The SKILL.md also asks to save evidence including 'region/resource id/time range' which could encourage including environment-specific identifiers in outputs; while not secrets by name, this increases what gets written to disk and possibly shared.

ℹ Install Mechanism

There is no install spec (instruction-only), which reduces installer risk. However, the workflow relies on npx -y @just-every/crawl (transiently pulling an npm package and executing it). Relying on npx to run a remote package is a moderate install/execution risk unless the package and version are audited or pinned. The Python scripts are local and simple text processing (no external downloads).

✓ Credentials

The skill declares no required environment variables or credentials, and the Python scripts do not read secrets or env vars. The only external access is network to the public help.aliyun.com site. Asking to record 'region/resource id/time range' in evidence is informational and not a request for secrets.

✓ Persistence & Privilege

always is false and the skill does not request persistent or system-wide privileges. It writes outputs into an output/ subdirectory and generated skills under skills/ai/** per instructions — this is expected for a content-generation workflow and not an escalation of privilege.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install aliyun-modelstudio-crawl-and-skill
安装完成后，直接呼叫该 Skill 的名称或使用 /aliyun-modelstudio-crawl-and-skill 触发
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-modelstudio-crawl-and-skill. - Automates crawling of Alibaba Cloud Model Studio models and regeneration of skills in `skills/ai/**`. - Outputs structured model lists, cleaned summaries, skill coverage reports, and generated skills. - Includes validation scripts and reproducibility guidelines. - Supports updating documentation files if the skills list changes.

元数据

Slug aliyun-modelstudio-crawl-and-skill

版本 1.0.0

许可证 MIT-0

累计安装 1

当前安装数 1

历史版本数 1

常见问题