data-analyst

Name: data-analyst
Author: szsip239

101stars14forks

How to install data-analyst?

szsip239/teamclaw/data-analyst

$npx -y skills add szsip239/teamclaw --skill data-analyst

Installs into the current project.

Summary

Data visualization, report generation, SQL queries, and spreadsheet automation. Transform your AI agent into a data-savvy analyst that turns raw data into actionable insights.

Files · 1

View on GitHub

SKILL.md

1	# Data Analyst Skill 📊
2
3	Turn your AI agent into a data analysis powerhouse.
4
5	Query databases, analyze spreadsheets, create visualizations, and generate insights that drive decisions.
6
7	---
8
9	## What This Skill Does
10
11	✅ SQL Queries — Write and execute queries against databases
12	✅ Spreadsheet Analysis — Process CSV, Excel, Google Sheets data
13	✅ Data Visualization — Create charts, graphs, and dashboards
14	✅ Report Generation — Automated reports with insights
15	✅ Data Cleaning — Handle missing data, outliers, formatting
16	✅ Statistical Analysis — Descriptive stats, trends, correlations
17
18	---
19
20	## Quick Start
21
22	1. Configure your data sources in `TOOLS.md`:
23	```markdown
24	### Data Sources
25	- Primary DB: [Connection string or description]
26	- Spreadsheets: [Google Sheets URL / local path]
27	- Data warehouse: [BigQuery/Snowflake/etc.]
28	```
29
30	2. Set up your workspace:
31	```bash
32	./scripts/data-init.sh
33	```
34
35	3. Start analyzing!
36
37	---
38
39	## SQL Query Patterns
40
41	### Common Query Templates
42
43	Basic Data Exploration
44	```sql
45	-- Row count
46	SELECT COUNT(*) FROM table_name;
47
48	-- Sample data
49	SELECT * FROM table_name LIMIT 10;
50
51	-- Column statistics
52	SELECT
53	column_name,
54	COUNT(*) as count,
55	COUNT(DISTINCT column_name) as unique_values,
56	MIN(column_name) as min_val,
57	MAX(column_name) as max_val
58	FROM table_name
59	GROUP BY column_name;
60	```
61
62	Time-Based Analysis
63	```sql
64	-- Daily aggregation
65	SELECT
66	DATE(created_at) as date,
67	COUNT(*) as daily_count,
68	SUM(amount) as daily_total
69	FROM transactions
70	GROUP BY DATE(created_at)
71	ORDER BY date DESC;
72
73	-- Month-over-month comparison
74	SELECT
75	DATE_TRUNC('month', created_at) as month,
76	COUNT(*) as count,
77	LAG(COUNT(*)) OVER (ORDER BY DATE_TRUNC('month', created_at)) as prev_month,
78	(COUNT() - LAG(COUNT()) OVER (ORDER BY DATE_TRUNC('month', created_at))) /
79	NULLIF(LAG(COUNT()) OVER (ORDER BY DATE_TRUNC('month', created_at)), 0) 100 as growth_pct
80	FROM transactions
81	GROUP BY DATE_TRUNC('month', created_at)
82	ORDER BY month;
83	```
84
85	Cohort Analysis
86	```sql
87	-- User cohort by signup month
88	SELECT
89	DATE_TRUNC('month', u.created_at) as cohort_month,
90	DATE_TRUNC('month', o.created_at) as activity_month,
91	COUNT(DISTINCT u.id) as users
92	FROM users u
93	LEFT JOIN orders o ON u.id = o.user_id
94	GROUP BY cohort_month, activity_month
95	ORDER BY cohort_month, activity_month;
96	```
97
98	Funnel Analysis
99	```sql
100	-- Conversion funnel
101	WITH funnel AS (
102	SELECT
103	COUNT(DISTINCT CASE WHEN event = 'page_view' THEN user_id END) as views,
104	COUNT(DISTINCT CASE WHEN event = 'signup' THEN user_id END) as signups,
105	COUNT(DISTINCT CASE WHEN event = 'purchase' THEN user_id END) as purchases
106	FROM events
107	WHERE date >= CURRENT_DATE - INTERVAL '30 days'
108	)
109	SELECT
110	views,
111	signups,
112	ROUND(signups * 100.0 / NULLIF(views, 0), 2) as signup_rate,
113	purchases,
114	ROUND(purchases * 100.0 / NULLIF(signups, 0), 2) as purchase_rate
115	FROM funnel;
116	```
117
118	---
119
120	## Data Cleaning
121
122	### Common Data Quality Issues
123
124	\| Issue \| Detection \| Solution \|
125	\|-------\|-----------\|----------\|
126	\| Missing values \| `IS NULL` or empty string \| Impute, drop, or flag \|
127	\| Duplicates \| `GROUP BY` with `HAVING COUNT(*) > 1` \| Deduplicate with rules \|
128	\| Outliers \| Z-score > 3 or IQR method \| Investigate, cap, or exclude \|
129	\| Inconsistent formats \| Sample and pattern match \| Standardize with transforms \|
130	\| Invalid values \| Range checks, referential integrity \| Validate and correct \|
131
132	### Data Cleaning SQL Patterns
133
134	```sql
135	-- Find duplicates
136	SELECT email, COUNT(*)
137	FROM users
138	GROUP BY email
139	HAVING COUNT(*) > 1;
140
141	-- Find nulls
142	SELECT
143	COUNT(*) as total,
144	SUM(CASE WHEN email IS NULL THEN 1 ELSE 0 END) as null_emails,
145	SUM(CASE WHEN name IS NULL THEN 1 ELSE 0 END) as null_names
146	FROM users;
147
148	-- Standardize text
149	UPDATE products
150	SET category = LOWER(TRIM(category));
151
152	-- Remove outliers (IQR method)
153	WITH stats AS (
154	SELECT
155	PERCENTILE_CONT(0.25) WITHIN GROUP (ORDER BY value) as q1,
156	PERCENTILE_CONT(0.75) WITHIN GROUP (ORDER BY value) as q3
157	FROM data
158	)
159	SELECT * FROM data, stats
160	WHERE value BETWEEN q1 - 1.5(q3-q1) AND q3 + 1.5(q3-q1);
161	```
162
163	### Data Cleaning Checklist
164
165	```markdown
166	# Data Quality Audit: [Dataset]
167
168	## Row-Level Checks
169	- [ ] Total row count: [X]
170	- [ ] Duplicate rows: [X]
171	- [ ] Rows with any null: [X]
172
173	## Column-Level Checks
174	\| Column \| Type \| Nulls \| Unique \| Min \| Max \| Issues \|
175	\|--------\|------\|-------\|--------\|-----\|-----\|--------\|
176	\| [col] \| [type] \| [n] \| [n] \| [v] \| [v] \| [notes] \|
177
178	## Data Lineage
179	- Source: [Where data came from]
180	- Last updated: [Date]
181	- Known issues: [List]
182
183	## Cleaning Actions Taken
184	1. [Action and reason]
185	2. [Action and reason]
186	```
187
188	---
189
190	## Spreadsheet Analysis
191
192	### CSV/

People who liked this also viewed

6 picks

Type

azure-kustoQuery and analyze data in Azure Data Explorer (Kusto/ADX) using KQL for log analytics, telemetry, and time series analysis. WHEN: KQL queries, Kusto database queries, Azure Data Explorer, ADX clustersSkillsJul 2026470k1.3k
lark-base飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、workflow、角色权限；遇到 Base/多维表格/bitable 或 /base/ 链接时使用。文件导入转 lark-drive，认证/授权转 lark-shared。SkillsJul 2026382k16k
lark-calendar飞书日历：管理日历日程和会议室。查看/搜索日程、创建/更新日程、管理参会人、查询忙闲和推荐时段、预定会议室。当用户需要查看日程安排、创建/修改会议、查询/预定会议室时使用。不负责：查询过去的视频会议记录（走 lark-vc）、待办任务（走 lark-task）。SkillsJul 2026380k16k
shadcnManages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. AppliSkillsJul 2026246k120k
xlsxUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.SkillsJul 2026139k163k
firebase-data-connectAgent Skills for FirebaseSkillsJul 2026108k387

data-analyst

101stars14forks

View on GitHub

How to install data-analyst?

szsip239/teamclaw/data-analyst

$npx -y skills add szsip239/teamclaw --skill data-analyst

Installs into the current project.

Summary

Data visualization, report generation, SQL queries, and spreadsheet automation. Transform your AI agent into a data-savvy analyst that turns raw data into actionable insights.

Files · 1

View on GitHub

SKILL.md

1	# Data Analyst Skill 📊
2
3	Turn your AI agent into a data analysis powerhouse.
4
5	Query databases, analyze spreadsheets, create visualizations, and generate insights that drive decisions.
6
7	---
8
9	## What This Skill Does
10
11	✅ SQL Queries — Write and execute queries against databases
12	✅ Spreadsheet Analysis — Process CSV, Excel, Google Sheets data
13	✅ Data Visualization — Create charts, graphs, and dashboards
14	✅ Report Generation — Automated reports with insights
15	✅ Data Cleaning — Handle missing data, outliers, formatting
16	✅ Statistical Analysis — Descriptive stats, trends, correlations
17
18	---
19
20	## Quick Start
21
22	1. Configure your data sources in `TOOLS.md`:
23	```markdown
24	### Data Sources
25	- Primary DB: [Connection string or description]
26	- Spreadsheets: [Google Sheets URL / local path]
27	- Data warehouse: [BigQuery/Snowflake/etc.]
28	```
29
30	2. Set up your workspace:
31	```bash
32	./scripts/data-init.sh
33	```
34
35	3. Start analyzing!
36
37	---
38
39	## SQL Query Patterns
40
41	### Common Query Templates
42
43	Basic Data Exploration
44	```sql
45	-- Row count
46	SELECT COUNT(*) FROM table_name;
47
48	-- Sample data
49	SELECT * FROM table_name LIMIT 10;
50
51	-- Column statistics
52	SELECT
53	column_name,
54	COUNT(*) as count,
55	COUNT(DISTINCT column_name) as unique_values,
56	MIN(column_name) as min_val,
57	MAX(column_name) as max_val
58	FROM table_name
59	GROUP BY column_name;
60	```
61
62	Time-Based Analysis
63	```sql
64	-- Daily aggregation
65	SELECT
66	DATE(created_at) as date,
67	COUNT(*) as daily_count,
68	SUM(amount) as daily_total
69	FROM transactions
70	GROUP BY DATE(created_at)
71	ORDER BY date DESC;
72
73	-- Month-over-month comparison
74	SELECT
75	DATE_TRUNC('month', created_at) as month,
76	COUNT(*) as count,
77	LAG(COUNT(*)) OVER (ORDER BY DATE_TRUNC('month', created_at)) as prev_month,
78	(COUNT() - LAG(COUNT()) OVER (ORDER BY DATE_TRUNC('month', created_at))) /
79	NULLIF(LAG(COUNT()) OVER (ORDER BY DATE_TRUNC('month', created_at)), 0) 100 as growth_pct
80	FROM transactions
81	GROUP BY DATE_TRUNC('month', created_at)
82	ORDER BY month;
83	```
84
85	Cohort Analysis
86	```sql
87	-- User cohort by signup month
88	SELECT
89	DATE_TRUNC('month', u.created_at) as cohort_month,
90	DATE_TRUNC('month', o.created_at) as activity_month,
91	COUNT(DISTINCT u.id) as users
92	FROM users u
93	LEFT JOIN orders o ON u.id = o.user_id
94	GROUP BY cohort_month, activity_month
95	ORDER BY cohort_month, activity_month;
96	```
97
98	Funnel Analysis
99	```sql
100	-- Conversion funnel
101	WITH funnel AS (
102	SELECT
103	COUNT(DISTINCT CASE WHEN event = 'page_view' THEN user_id END) as views,
104	COUNT(DISTINCT CASE WHEN event = 'signup' THEN user_id END) as signups,
105	COUNT(DISTINCT CASE WHEN event = 'purchase' THEN user_id END) as purchases
106	FROM events
107	WHERE date >= CURRENT_DATE - INTERVAL '30 days'
108	)
109	SELECT
110	views,
111	signups,
112	ROUND(signups * 100.0 / NULLIF(views, 0), 2) as signup_rate,
113	purchases,
114	ROUND(purchases * 100.0 / NULLIF(signups, 0), 2) as purchase_rate
115	FROM funnel;
116	```
117
118	---
119
120	## Data Cleaning
121
122	### Common Data Quality Issues
123
124	\| Issue \| Detection \| Solution \|
125	\|-------\|-----------\|----------\|
126	\| Missing values \| `IS NULL` or empty string \| Impute, drop, or flag \|
127	\| Duplicates \| `GROUP BY` with `HAVING COUNT(*) > 1` \| Deduplicate with rules \|
128	\| Outliers \| Z-score > 3 or IQR method \| Investigate, cap, or exclude \|
129	\| Inconsistent formats \| Sample and pattern match \| Standardize with transforms \|
130	\| Invalid values \| Range checks, referential integrity \| Validate and correct \|
131
132	### Data Cleaning SQL Patterns
133
134	```sql
135	-- Find duplicates
136	SELECT email, COUNT(*)
137	FROM users
138	GROUP BY email
139	HAVING COUNT(*) > 1;
140
141	-- Find nulls
142	SELECT
143	COUNT(*) as total,
144	SUM(CASE WHEN email IS NULL THEN 1 ELSE 0 END) as null_emails,
145	SUM(CASE WHEN name IS NULL THEN 1 ELSE 0 END) as null_names
146	FROM users;
147
148	-- Standardize text
149	UPDATE products
150	SET category = LOWER(TRIM(category));
151
152	-- Remove outliers (IQR method)
153	WITH stats AS (
154	SELECT
155	PERCENTILE_CONT(0.25) WITHIN GROUP (ORDER BY value) as q1,
156	PERCENTILE_CONT(0.75) WITHIN GROUP (ORDER BY value) as q3
157	FROM data
158	)
159	SELECT * FROM data, stats
160	WHERE value BETWEEN q1 - 1.5(q3-q1) AND q3 + 1.5(q3-q1);
161	```
162
163	### Data Cleaning Checklist
164
165	```markdown
166	# Data Quality Audit: [Dataset]
167
168	## Row-Level Checks
169	- [ ] Total row count: [X]
170	- [ ] Duplicate rows: [X]
171	- [ ] Rows with any null: [X]
172
173	## Column-Level Checks
174	\| Column \| Type \| Nulls \| Unique \| Min \| Max \| Issues \|
175	\|--------\|------\|-------\|--------\|-----\|-----\|--------\|
176	\| [col] \| [type] \| [n] \| [n] \| [v] \| [v] \| [notes] \|
177
178	## Data Lineage
179	- Source: [Where data came from]
180	- Last updated: [Date]
181	- Known issues: [List]
182
183	## Cleaning Actions Taken
184	1. [Action and reason]
185	2. [Action and reason]
186	```
187
188	---
189
190	## Spreadsheet Analysis
191
192	### CSV/

People who liked this also viewed

6 picks

Type