메뉴
Comprehensive guide for conducting rigorous data analysis, from question definition to actionable recommendations
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
Schedule reminders and recurring tasks.
Two-layer memory system with grep-based recall.
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
Business process analysis and improvement. Use when mapping, analyzing, or optimizing processes.
Requirements gathering and documentation. Use when eliciting, documenting, or validating requirements.
| name | Data Analysis |
| description | Comprehensive guide for conducting rigorous data analysis, from question definition to actionable recommendations |
| emoji | 📊 |
| tags | ["analysis","statistics","methodology","reporting"] |
Daily Metrics:
SELECT
DATE(created_at) as date,
COUNT(*) as events,
COUNT(DISTINCT user_id) as unique_users
FROM events
WHERE created_at >= CURRENT_DATE - INTERVAL '30 days'
GROUP BY DATE(created_at)
ORDER BY date DESC;
Cohort Analysis:
WITH cohorts AS (
SELECT
user_id,
DATE_TRUNC('month', MIN(created_at)) as cohort_month
FROM users
GROUP BY user_id
)
SELECT
c.cohort_month,
DATE_TRUNC('month', e.created_at) as event_month,
COUNT(DISTINCT e.user_id) as active_users
FROM cohorts c
JOIN events e ON c.user_id = e.user_id
GROUP BY c.cohort_month, DATE_TRUNC('month', e.created_at)
ORDER BY c.cohort_month, event_month;
Running Totals:
SELECT
date,
revenue,
SUM(revenue) OVER (ORDER BY date) as running_total
FROM daily_revenue
ORDER BY date;
Ranking:
SELECT
product_id,
revenue,
RANK() OVER (ORDER BY revenue DESC) as revenue_rank
FROM product_revenue;
Period-over-Period Comparison:
SELECT
date,
revenue,
LAG(revenue, 7) OVER (ORDER BY date) as revenue_7d_ago,
revenue - LAG(revenue, 7) OVER (ORDER BY date) as change_7d
FROM daily_revenue
ORDER BY date;
Multi-Step Analysis:
WITH filtered_data AS (
SELECT *
FROM events
WHERE created_at >= CURRENT_DATE - INTERVAL '30 days'
AND status = 'completed'
),
aggregated AS (
SELECT
DATE(created_at) as date,
COUNT(*) as count
FROM filtered_data
GROUP BY DATE(created_at)
)
SELECT
date,
count,
AVG(count) OVER (ORDER BY date ROWS BETWEEN 6 PRECEDING AND CURRENT ROW) as rolling_7d_avg
FROM aggregated
ORDER BY date;
Two Groups (Independent):
Two Groups (Paired):
Multiple Groups:
Two Categories:
Multiple Categories:
Linear Relationship:
Multiple Predictors:
Non-Linear Relationship:
When assumptions fail:
Primary Metric:
Secondary Metrics: