Alicloud Ai Misc Crawl And Skill

Refresh the Model Studio models crawl and regenerate derived summaries and `skills/ai/**` skills. Use when the models list or generated skills must be updated.

Security Scan

The skill's code and instructions match its stated purpose (crawl Alibaba Cloud Model Studio pages and regenerate skill summaries), request no credentials, and perform only local parsing and file generation; the main runtime risk is that it uses npx to fetch a third‑party crawler package on demand.

Purpose & Capability

The name/description, SKILL.md, and the two Python scripts are coherent: they crawl the Alibaba Cloud Model Studio page, extract model IDs and metadata, produce JSON/markdown summaries, and generate a skill coverage report. No unrelated binaries, credentials, or config paths are requested.

Instruction Scope

Instructions are scoped to crawling the listed help.aliyun.com models page, running the two included Python scripts, and writing outputs under output/ and skills/ai/**. They do not access secrets or other system config. One noteworthy instruction: it runs npx @just-every/crawl which executes a third‑party package at runtime and writes the raw crawl to disk; the SKILL.md also asks to include 'region/resource id/time range' in evidence files (be cautious about including sensitive identifiers).

Install Mechanism

There is no install spec (instruction-only), which is low risk, but the runtime use of npx -y @just-every/crawl will download and execute a remote npm package on demand. That is functional for crawling but is a point of transient code execution you may want to audit or pin to a version.

Credentials

The skill declares no required environment variables, no primary credential, and the scripts do not read environment variables or external credentials. This is proportionate to a web-crawl-and-parse task.

Persistence & Privilege

The skill is not always-enabled and does not request elevated or persistent system privileges. It writes outputs under the repository (output/ and skills/ai/**) only. Autonomous invocation is allowed by default but is common and not a separate concern here.

Assessment

This skill appears to do what it claims and does not ask for secrets, but consider the following before running: 1) The workflow uses `npx -y @just-every/crawl` which will fetch and execute a remote npm package each run — audit that package or replace/pin it to a specific trusted version to avoid executing unexpected code. 2) The scripts write files under output/ and skills/ai/**; run in a safe working directory or sandbox to avoid overwriting important files. 3) When saving 'evidence' avoid including sensitive resource identifiers (region IDs, resource IDs, time ranges) unless necessary. 4) If you require higher assurance, review the npm package source for @just-every/crawl or perform the crawl with a vetted tool (curl/wget/custom scraper) and then run the included Python scripts locally.

Category: task

Alibaba Cloud Model Studio Crawl and Skill Generation

Prerequisites

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

Workflow

1. Crawl models page (raw markdown)

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

2. Rebuild summary (models + API/usage links)

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

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

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

Pass criteria: command exits 0 and output/alicloud-ai-misc-crawl-and-skill/validate.txt is generated.

Output And Evidence

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

References

• Source list: references/sources.md