메뉴
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.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| 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.
Analyze Claude Code prompt cache efficiency and costs. Use when user asks about cache performance, token usage, session costs, how much a session cost, wants to optimize prompt caching, when costs seem high, when context window is filling up, or mentions cache-analyzer/cache hits/token costs/session metrics/cost analysis.
Review code for quality, security, and maintainability. Use when reviewing pull requests, examining code changes, doing QA checks, architecture review, or CTO review. Also trigger for COMPLEX tasks affecting more than 5 files, API contract changes, or data migrations.
Create new skills, modify and improve existing skills, create or update AI rules. Use when creating rules, building skills, adding coding standards, updating .claude/rules/ or .claude/skills/, converting Cursor rules to Claude Code, measuring skill performance, running evals, or optimizing skill descriptions.