菜单
Extract structured data from websites with robots awareness, request throttling, selector-based parsing, and reproducible output. Use when collecting data from public pages, monitoring page changes, or converting HTML content into JSON/CSV datasets.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Create and extend command-line automation tools with clear argument contracts, safe defaults, dry-run support, and validation. Use when building project utilities, operational scripts, developer productivity commands, or repeatable terminal workflows.
Build and maintain authenticated API integrations with predictable request/response handling, retries, pagination, and error classification. Use when implementing REST/JSON API calls, syncing external systems, troubleshooting API failures, or creating reusable API client scripts.
Process tabular datasets with repeatable cleaning, schema checks, type normalization, and quality reporting. Use when transforming CSV/TSV exports, preparing analytics-ready data, validating required columns, or building deterministic ETL-style scripts.
Process files in bulk with deterministic naming, format conversion, filtering, and safe write patterns. Use when renaming large file sets, generating transformed copies, organizing directories, or applying repeatable file-level operations.
| name | web-scraping-template |
| description | Extract structured data from websites with robots awareness, request throttling, selector-based parsing, and reproducible output. Use when collecting data from public pages, monitoring page changes, or converting HTML content into JSON/CSV datasets. |
Use this template to build polite and maintainable scraping skills.
references/scraping-playbook.md.assets/selectors-template.yaml and define extraction selectors.scripts/scrape_static.py against one URL first.scripts/scrape_static.py for static pages without browser automation.references/scraping-playbook.md for policy and reliability rules.assets/selectors-template.yaml.