菜单
Analyze data, investigate datasets, work with CSV/parquet/pandas/dataframes. Use when analyzing data, exploring datasets, running experiments, or when user mentions data, analysis, parquet, csv, pandas, dataframe, statistics, investigation.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/dmitryprg-ai/cursor-develop-autorules --skill research命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | research |
| description | Analyze data, investigate datasets, work with CSV/parquet/pandas/dataframes. Use when analyzing data, exploring datasets, running experiments, or when user mentions data, analysis, parquet, csv, pandas, dataframe, statistics, investigation. |
Principle: DATA FIRST, CODE SECOND.
Choose analysis method based on project stack:
-- Schema inspection
SELECT column_name, data_type, is_nullable
FROM information_schema.columns WHERE table_name = 'target';
-- Data profiling
SELECT count(*), count(DISTINCT column_name),
count(*) FILTER (WHERE column_name IS NULL) as nulls
FROM target;
-- Distribution
SELECT column_name, count(*) FROM target GROUP BY 1 ORDER BY 2 DESC LIMIT 20;
// Shape and types
console.log(`Records: ${data.length}`);
console.log(`Keys: ${Object.keys(data[0] || {})}`);
// Profiling
const nullCount = data.filter(item => item.field == null).length;
const uniqueCount = new Set(data.map(item => item.field)).size;
const duplicates = data.length - uniqueCount;
print(f"Shape: {df.shape}")
print(f"dtypes:\n{df.dtypes}")
print(f"head:\n{df.head()}")
print(f"nunique:\n{df.nunique()}")
print(f"nulls:\n{df.isnull().sum()}")
| Risk | SQL Check | TypeScript Check | Python Check |
|---|---|---|---|
| Missing data | count(*) FILTER (WHERE col IS NULL) | data.filter(x => x.col == null).length | df.isnull().sum() |
| Duplicates | count(*) - count(DISTINCT col) | data.length - new Set(data.map(x => x.col)).size | df.duplicated().sum() |
| Wrong types | SELECT pg_typeof(col) | typeof item.field | df.dtypes |
| Outliers | percentile_cont(0.99) | Sort + inspect extremes | df.describe() |
# EXPERIMENT: [Description]
# HYPOTHESIS: [What we expect]
# METHOD: [SQL query / TypeScript code / Python code]
# RESULT: [actual output]
# EXPECTED: [what we expected]
# STATUS: PASS / FAIL
Rules:
Test API endpoints with proper authorization including Basic Auth and session cookies. Use when testing curl requests, checking API responses, getting 401 Unauthorized, session expired errors, or verifying endpoint behavior after changes.
Implement accumulated improvements from improvements-backlog into AI rules and skills. Use when backlog has 5+ items, weekly rule update cycle, 2+ high priority improvements exist, before important releases, when same error repeated 3+ times, when user says implement improvements/process backlog/update rules from errors.
Fix bugs, errors, exceptions, and unexpected behavior. Use when debugging, fixing errors, handling crashes, or when user mentions bug, error, broken, not working, crash, exception, 500 error, Application error, white screen, TypeError, undefined is not a function, or unexpected behavior.
基于 SOC 职业分类