Skills for Real Engineers. Straight from my .agents directory.
sn-da-large-file-analysis
Agent skill fromOpenSenseNova/SenseNova-Skills
万行以上 Excel 数据集的高性能分析引擎。提供 openpyxl read_only 流式读取(iter_rows 支持 10 万行以上)、Parquet 转换加速、内存优化、分块处理和大文件写入模式。**遇到以下任一情况就主动使用本 skill**:①数据行数 ≥ 10k(由 sn-da-excel-workflow 的行数评估步骤触发);②用户出现触发词:大文件 / 大数据量 / 性能优化 / 内存不足 / OOM / 百万行 / 十万行 / 流式读取 / Parquet / 分块处理 / large file / big data / streaming read / chunked processing;③直接使用 pd.read_excel() 导致超时或内存溢出;④用户明确要求对大规模数据集进行高性能处理。仅不用于:小于 10k 行的常规 Excel 分析(使用 sn-da-excel-workflow 即可)。
How to install sn-da-large-file-analysis
npx skills add OpenSenseNova/SenseNova-Skills# or add only this skill to Claude Code: copy the folder
skills/sn-da-large-file-analysis/
# into
~/.claude/skills/sn-da-large-file-analysis/ (all projects)
.claude/skills/sn-da-large-file-analysis/ (one project)
1# Large Scale Excel Analysis Skill23## Mandatory Rules45> **When total rows >= 10,000, you MUST use the methods in this skill.**67| Data Scale | Read Strategy | Reason |8|-----------|---------------|--------|9| < 10k rows | `pd.read_excel()` directly | No memory pressure |10| 10k–100k rows | `pd.read_excel()` → convert to Parquet → `pd.read_parquet()` for analysis | Avoid repeated slow reads |11| 100k–1M rows | **openpyxl `read_only` + `iter_rows` streaming** → Parquet | `pd.read_excel()` will OOM or timeout |12| > 1M rows | Streaming read + **multi-sheet split** (Excel max 1,048,576 rows per sheet) | Must chunk |1314**Prohibited:**15- Do NOT use `pd.read_excel()` to fully load 100k+ row files16- Do NOT search for fonts with `fc-list`, `find ... fonts`, or install packages with `pip install`17- Do NOT use `df.iterrows()` on large DataFrames (use `itertuples()` or vectorized ops)18- Do NOT use `df.apply(lambda...)` for operations that can be vectorized1920---2122## Environment Setup2324```python25import pandas as pd26import numpy as np27import os28import gc2930pd.options.mode.copy_on_write = True3132# CJK font setup (fixed paths — do NOT search for fonts)33# ⚠️ Copy this block as-is. Do NOT use fc-list, find, subprocess, or glob to locate fonts.34import matplotlib35import matplotlib.pyplot as plt36import matplotlib.font_manager as fm3738_FONT_PATHS = [39 '/mnt/afs_agents/SimHei.ttf',40 '/mnt/afs_agents/mnt/data/SimHei.ttf',41 os.path.expanduser('~/.fonts/SimHei.ttf'),42…
Excerpt shown under the repository's MIT license.
More skills in SenseNova-Skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
