メニュー
Clean and transform tabular data (CSV/JSON). Performs deduplication, null-row removal, string trimming, and column normalization. Useful for ETL tasks that don't need pandas — uses only Python standard library.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | data-processing-pipeline |
| description | Clean and transform tabular data (CSV/JSON). Performs deduplication, null-row removal, string trimming, and column normalization. Useful for ETL tasks that don't need pandas — uses only Python standard library. |
Use this skill when you need to clean a CSV or JSON-array file without spinning up a full pandas workflow. It handles the common 80%: dedupe, drop nulls, normalize.
input_path (required, str) — path to a .csv or .json file.output_path (required, str) — where to write the cleaned data.operations (optional, list[str]) — any of dedupe, drop_empty_rows, trim_strings, normalize_columns. Default: all four.output_format (optional, str) — csv or json. Default: same as input.{
"output_path": "/path/to/cleaned.csv",
"rows_in": 1000,
"rows_out": 875,
"operations_applied": ["dedupe", "drop_empty_rows", "trim_strings", "normalize_columns"],
"duplicates_removed": 100,
"empty_rows_removed": 25
}
| Name | Behavior |
|---|---|
dedupe | Remove exact-duplicate rows (all columns equal). |
drop_empty_rows | Drop rows where every value is empty/whitespace-only. |
trim_strings | .strip() on every string value. |
normalize_columns | Column names → lowercase, spaces/dashes → underscores. |
JSON input must be a top-level array of objects; non-conforming JSON raises ValueError.
Multi-model adversarial code review for agent outputs. Use when reviewing core logic changes, 5+ files, 200+ lines, or when user says "对抗审查/adversarial review/cross-model review". The reviewer agent inspects coder outputs through a cross-validation lens to catch single-model blind spots.
Change impact scan for Python projects. When modifying function signatures, interfaces, data models, config structs, or shared modules, automatically grep all call sites and dependent files to prevent incomplete changes. Outputs a structured markdown impact report.
Pitfall recording and evolution tracking. When AI makes a mistake or user corrects output, record a PIT entry. Same-type PITs reaching 2+ trigger rule extraction; 4+ trigger skill crystallization. Use when user says "踩坑/pitfall/PIT/记录错误/犯错日志/evolve mistake/踩坑记录".
Use when developing, modifying, refactoring, or reviewing the task-orchestrator multi-agent orchestration engine. Covers design principles, architecture decisions, and development guardrails derived from the Multi-Agent Harness design reference. Triggered by changes to src/openagents_orchestration/, adding new orchestration features, or questions about orchestrator design.
Run a static code review over a target directory. Scans Python/JS/TS files for common issues (long functions, TODOs, missing docstrings, unused imports, security smells) and produces a structured markdown report.
Generate API documentation (markdown) from a Python module by AST parsing. Extracts module docstrings, function signatures, class hierarchies, and type hints. Pure Python, no LLM dependency.