anbeime/skill / skills/data-flow-skill/data-flow-skill
data-flow-skill
Verified面向数据分析任务的一站式 Agent Skill,覆盖数据类型检测、数据理解、预处理、统计分析、可视化图表生成、正式报告和幻灯片输出。适用于课程作业、论文实验、业务分析、SEO/GEO 数据报告和可追溯数据分析工作流。
scripts/analysis/analyzer_preprocessing.py
View on GitHub"""Preprocessing recommendation helpers."""
from __future__ import annotations
from dataclasses import asdict, dataclass
from typing import Any
@dataclass(slots=True)
class PreprocessingAction:
action_name: str
target_fields: list[str]
reason: str
result: str
def build_preprocessing_log(
should_run: bool,
actions: list[PreprocessingAction] | None = None,
raw_snapshot_path: str = "",
processed_snapshot_path: str = "",
) -> dict[str, Any]:
return {
"should_run_preprocessing": should_run,
"raw_snapshot_path": raw_snapshot_path,
"processed_snapshot_path": processed_snapshot_path,
"actions": [asdict(action) for action in (actions or [])],
}
def generate_preprocessing_recommendations(
data_profile: dict[str, Any],
preprocessing_preference: str,
) -> list[PreprocessingAction]:
actions: list[PreprocessingAction] = []
if preprocessing_preference == "no preprocessing":
return actions
high_missing_fields = data_profile.get("data_profile", {}).get("high_missing_fields", [])
if high_missing_fields:
actions.append(
PreprocessingAction(
action_name="Review missing-value treatment",
target_fields=list(high_missing_fields),
reason="High-missing fields may distort statistics and figures.",
result="Wait for user confirmation before dropping or imputing values.",
)
)
constant_columns = data_profile.get("data_profile", {}).get("constant_columns", [])
if constant_columns:
actions.append(
PreprocessingAction(
action_name="Remove constant columns",
target_fields=list(constant_columns),
reason="Constant columns do not provide useful analytical signal.",
result="Recommended for removal.",
)
)
return actions
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 466k | Updated | Claude CodeCodex | Verified | Install |
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 466k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |