菜单
Download a dataset from a URL and inspect its actual contents — schema, column types, shape, sample rows, and null counts. Supports CSV, Parquet, Excel, JSON, and JSONL. Use this to look inside a dataset, not just its landing page.
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
Conduct a structured discovery interview to produce a precise, confirmed ProblemBrief.
Delegate complex, multi-file coding tasks to an autonomous coding agent that can iterate and self-correct. Uses Claude Code if ANTHROPIC_API_KEY is set, otherwise falls back to Gemini via generate_code + execute.
Produce a comprehensive, detail-preserving research report from all phase findings and agent evidence.
Execute arbitrary Python code in an isolated subprocess. Use for data transformation, statistical analysis, geospatial processing, knowledge graph modeling, ontology engineering, RDF serialization, data visualization, document parsing, and any computation task. Always print() results to capture them.
Download a PDF from a URL and extract its full text — ideal for research papers, reports, and documentation. Returns page count and extracted text.
Navigate to and extract content from specific web URLs. Good for reading data portals, documentation, and landing pages.
| description | Download a dataset from a URL and inspect its actual contents — schema, column types, shape, sample rows, and null counts. Supports CSV, Parquet, Excel, JSON, and JSONL. Use this to look inside a dataset, not just its landing page. |
| name | dataset_inspection |
| source | built-in |
| tags | ["data","datasets","inspection","schema","tabular"] |
| tools | ["url_fetch"] |
Apply when the work item requires assessing whether a specific dataset is fit for purpose — what columns it has, what values are present, how complete it is, and whether its coverage matches the task requirements. Use after web_search or web_browse has identified a candidate dataset URL. Do not speculate about a dataset's contents — inspect the actual file.
Produce a dataset assessment card in the proof field containing: dataset name, source URL, licence, format, dimensions (rows × columns), key columns and their types, coverage (geography, time range, resolution), fitness verdict (suitable / partially suitable / not suitable) with rationale, and quality concerns if any.
