SkillAgentSearch skills...

Spreadsheet & Data Wrangling Master

Complete spreadsheet methodology β€” data cleanup, transformation, analysis, dashboards, automation, and reporting. Works with CSV, Excel, Google Sheets, or any tabular data

Install / Use

npx skills add LeoYeAI/openclaw-master-skills --skill afrexai-spreadsheet-master

Installs into whichever agent you are using.

About this skill
πŸ“„

SKILL.md

Installable skill definition

Quality Score

90/100

Category

Automation

Supported Platforms

Universal

Our assessment of Spreadsheet & Data Wrangling Master

Spreadsheet & Data Wrangling Master scores 90/100 on our quality scale, 1223rd of 2,790 Automation skills we index (top 44%).

Its SKILL.md is 26 KB long, well organised into 49 sections with 20 code examples: a thorough specification that gives an agent plenty to work with.

With 2,149 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
14/20
Freshness
11/15

Maintenance, license and trust

  • The repository was last updated about 4 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
  • Our last check on 2026-10-30 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 98/100, with no cautions. These come from repository metadata, not a code audit β€” read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-30. Automated pattern scan on 2026-09-30. It catches known dangerous patterns, not every risk β€” read a skill before letting an agent act on it.

Spreadsheet & Data Wrangling Master compared with similar skills

All 4 of these similar skills score higher than Spreadsheet & Data Wrangling Master; compare them before choosing.

SkillScoreStarsUpdatedFormat
Spreadsheet & Data Wrangling Master (this skill)by LeoYeAI902.1k4mo agoSKILL.md
Agent-Reachby Panniantong100112.3k8d agoCLAUDE.md
rufloby ruvnet10081.9ktodayCLAUDE.md
Claude-Code-Game-Studiosby Donchitos10039.7k7d agoCLAUDE.md
Scraplingby D4Vinci100103.6k2d agoMCP Server

Frequently asked questions

How do I install Spreadsheet & Data Wrangling Master?
Run npx skills add LeoYeAI/openclaw-master-skills --skill "Spreadsheet & Data Wrangling Master". The install tabs above show the steps for each supported agent.
Which AI agents does Spreadsheet & Data Wrangling Master work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is Spreadsheet & Data Wrangling Master safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 98/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is Spreadsheet & Data Wrangling Master still maintained?
The repository was last updated about 4 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.

name: Spreadsheet & Data Wrangling Master slug: afrexai-spreadsheet-master version: 1.0.0 description: "Complete spreadsheet methodology β€” data cleanup, transformation, analysis, dashboards, automation, and reporting. Works with CSV, Excel, Google Sheets, or any tabular data. Use when the user needs to clean messy data, build reports, create dashboards, automate recurring spreadsheet tasks, or transform data between formats." tags: spreadsheet, excel, csv, data, cleanup, reporting, dashboard, analytics, automation, google-sheets

Spreadsheet & Data Wrangling Master

Turn messy data into clean insights, automated reports, and decision-ready dashboards. Platform-agnostic β€” works with CSV, Excel, Google Sheets, or any tabular format.


Phase 1: Data Intake & Assessment

Before touching any data, assess what you have.

Quick Health Check (score /20)

data_intake:
  source: ""           # file path, URL, API, database, manual entry
  format: ""           # CSV, XLSX, TSV, JSON, clipboard paste
  rows: 0
  columns: 0
  file_size: ""
  encoding: ""         # UTF-8, Latin-1, Windows-1252, etc.
  delimiter: ""        # comma, tab, pipe, semicolon

  health_score:        # rate each 0-4, total /20
    completeness: 0    # 4=<1% missing, 3=<5%, 2=<15%, 1=<30%, 0=>30%
    consistency: 0     # 4=uniform types, 3=minor mixed, 2=significant mixed, 1=chaotic, 0=unusable
    accuracy: 0        # 4=verified, 3=plausible, 2=some outliers, 1=many errors, 0=untrustworthy
    freshness: 0       # 4=real-time, 3=<24h, 2=<7d, 1=<30d, 0=stale/unknown
    structure: 0       # 4=tidy (1 row=1 obs), 3=minor reshaping, 2=pivot needed, 1=multi-header, 0=freeform

  issues_found: []     # list every problem before fixing anything

First 10 Questions to Ask

  1. How many rows and columns?
  2. What does each row represent? (one customer? one transaction? one day?)
  3. Are there header rows? Multiple header rows? Merged cells?
  4. What are the data types? (dates, currencies, percentages, IDs, free text)
  5. How much is missing? Which columns?
  6. Are there duplicates? By which key?
  7. Is there a unique identifier column?
  8. What date format? (MM/DD/YYYY vs DD/MM/YYYY vs YYYY-MM-DD vs mixed)
  9. What currency/number format? (1,000.00 vs 1.000,00 vs 1000)
  10. Where did this data come from and how often is it updated?

Phase 2: Data Cleaning Decision Tree

Step-by-Step Cleaning Protocol

START
  β”‚
  β”œβ”€ Headers β†’ Normalize (lowercase, snake_case, no spaces/special chars)
  β”‚
  β”œβ”€ Duplicates?
  β”‚   β”œβ”€ Exact duplicates β†’ Remove, keep first
  β”‚   β”œβ”€ Near-duplicates β†’ Flag for review (fuzzy match on name + address)
  β”‚   └─ Intentional duplicates β†’ Leave (e.g., multiple orders same customer)
  β”‚
  β”œβ”€ Missing Values?
  β”‚   β”œβ”€ <5% of column β†’ Fill (mean for numeric, mode for categorical, forward-fill for time series)
  β”‚   β”œβ”€ 5-30% β†’ Flag + fill with "UNKNOWN" or interpolate with justification
  β”‚   β”œβ”€ >30% β†’ Consider dropping column or flagging as unreliable
  β”‚   └─ Entire row missing key fields β†’ Remove with log
  β”‚
  β”œβ”€ Data Types?
  β”‚   β”œβ”€ Dates as text β†’ Parse to date (try multiple formats, log failures)
  β”‚   β”œβ”€ Numbers as text β†’ Strip currency symbols, commas, whitespace, convert
  β”‚   β”œβ”€ IDs/zips with leading zeros β†’ Keep as text (NEVER convert to number)
  β”‚   β”œβ”€ Phone numbers β†’ Text, standardize format
  β”‚   β”œβ”€ Mixed types in column β†’ Split or coerce with error log
  β”‚   └─ Boolean variants β†’ Map (Yes/No/True/False/1/0/Y/N β†’ consistent)
  β”‚
  β”œβ”€ Outliers?
  β”‚   β”œβ”€ Calculate IQR: Q1 - 1.5Γ—IQR to Q3 + 1.5Γ—IQR
  β”‚   β”œβ”€ Business logic check (negative revenue? age 200? date in 2099?)
  β”‚   β”œβ”€ Decide: fix (typo), cap (winsorize), remove, or keep with flag
  β”‚   └─ ALWAYS log which outliers were modified and why
  β”‚
  β”œβ”€ Standardization?
  β”‚   β”œβ”€ Text case β†’ Consistent (Title Case for names, UPPER for codes)
  β”‚   β”œβ”€ Whitespace β†’ Trim leading/trailing, collapse internal
  β”‚   β”œβ”€ Categories β†’ Map variants ("US"/"USA"/"United States" β†’ "US")
  β”‚   β”œβ”€ Dates β†’ ISO 8601 (YYYY-MM-DD) internally
  β”‚   β”œβ”€ Currency β†’ Consistent symbol placement, decimal precision
  β”‚   └─ Phone/email β†’ Validate format
  β”‚
  └─ Structural Issues?
      β”œβ”€ Multi-header rows β†’ Flatten to single header
      β”œβ”€ Merged cells β†’ Unmerge + fill down
      β”œβ”€ Pivot/crosstab β†’ Unpivot to tidy format (1 row = 1 observation)
      β”œβ”€ Multiple tables in one sheet β†’ Split to separate sheets/files
      └─ Metadata rows (totals, notes) β†’ Separate from data rows

Cleaning Log Template

cleaning_log:
  date: "YYYY-MM-DD"
  source_file: ""
  rows_before: 0
  rows_after: 0
  actions:
    - action: "removed exact duplicates"
      rows_affected: 0
      key_columns: ["email"]
    - action: "filled missing values"
      column: "state"
      method: "mode"
      values_filled: 0
    - action: "removed outliers"
      column: "revenue"
      criteria: "negative values"
      rows_removed: 0
    - action: "standardized dates"
      column: "order_date"
      from_format: "MM/DD/YYYY"
      to_format: "YYYY-MM-DD"
      parse_failures: 0
  notes: ""

Phase 3: Transformation Patterns

12 Essential Transform Operations

| # | Operation | When to Use | Example | |---|-----------|-------------|---------| | 1 | Filter | Subset rows by condition | Orders > $1000, Date after 2024-01-01 | | 2 | Sort | Order by column(s) | Revenue descending, then date ascending | | 3 | Group + Aggregate | Summarize by category | Total revenue by region, avg order by customer | | 4 | Pivot | Rows β†’ columns | Monthly columns from date rows | | 5 | Unpivot/Melt | Columns β†’ rows | Month columns back to date rows | | 6 | Join/Merge | Combine datasets | Customer data + order data on customer_id | | 7 | Deduplicate | Remove redundancy | Keep latest record per customer | | 8 | Derive | Calculate new columns | profit = revenue - cost, age = today - birthdate | | 9 | Split | One column β†’ many | "John Smith" β†’ first_name, last_name | | 10 | Concatenate | Many columns β†’ one | city + state + zip β†’ full_address | | 11 | Lookup/Map | Enrich with reference data | state_code β†’ state_name, product_id β†’ category | | 12 | Window | Running calculations | 7-day moving average, rank within group, running total |

Join Strategy Decision Guide

Which join do you need?
β”‚
β”œβ”€ Need ALL rows from left table β†’ LEFT JOIN
β”‚   (customers who may or may not have orders)
β”‚
β”œβ”€ Need ONLY matching rows β†’ INNER JOIN
β”‚   (only customers WITH orders)
β”‚
β”œβ”€ Need ALL rows from both β†’ FULL OUTER JOIN
β”‚   (reconciliation: find mismatches)
β”‚
β”œβ”€ Need everything NOT in other table β†’ LEFT JOIN + WHERE right IS NULL
β”‚   (customers who NEVER ordered)
β”‚
└─ Need every combination β†’ CROSS JOIN (rare, use carefully)
    (all products Γ— all stores for pricing matrix)

⚠️ ALWAYS check join results:
- Row count: did it explode? (many-to-many join)
- Row count: did it shrink? (keys not matching)
- NULL columns: expected from outer join, unexpected = key mismatch

Formula Reference (Cross-Platform)

| Task | Excel | Google Sheets | Python (pandas) | |------|-------|---------------|-----------------| | Lookup | VLOOKUP, XLOOKUP | VLOOKUP, XLOOKUP | df.merge(), df.map() | | Conditional sum | SUMIFS | SUMIFS | df.groupby().sum() | | Conditional count | COUNTIFS | COUNTIFS | df.groupby().count() | | Text split | TEXTSPLIT, LEFT/MID/RIGHT | SPLIT | df.str.split() | | Date diff | DATEDIF, math | DATEDIF | (df.col2 - df.col1).dt.days | | Running total | SUM($A$1:A1) | SUM($A$1:A1) | df.cumsum() | | Rank | RANK.EQ | RANK | df.rank() | | Percent of total | =A1/SUM($A:$A) | =A1/SUM($A:$A) | df.col / df.col.sum() | | Remove duplicates | Data β†’ Remove Duplicates | Data β†’ Remove Duplicates | df.drop_duplicates() | | Pivot | Pivot Table | Pivot Table | df.pivot_table() |


Phase 4: Analysis Frameworks

Quick Analysis Menu

Pick the analysis that matches the question:

Descriptive (What happened?)

  • Summary statistics: count, mean, median, min, max, std dev, percentiles
  • Frequency distributions: how many of each category?
  • Time trends: daily/weekly/monthly aggregates over time
  • Cross-tabs: category A Γ— category B breakdown

Diagnostic (Why did it happen?)

  • Drill-down: which segment drove the change?
  • Cohort analysis: behavior by signup month
  • Correlation: which variables move together?
  • Variance analysis: actual vs budget/forecast, by category

Predictive (What might happen?)

  • Trend projection: linear/exponential fit + confidence
  • Moving averages: 7/30/90 day smoothing
  • Seasonality: same-period prior year comparison
  • Growth rate: MoM, QoQ, YoY percentage changes

Prescriptive (What should we do?)

  • Pareto (80/20): which 20% of X drives 80% of Y?
  • Scenario analysis: best/base/worst case with different assumptions
  • Sensitivity: which input variable has biggest impact?
  • Break-even: at what point does X cover Y?

Insight Formula

Every finding MUST follow this structure:

INSIGHT: [What you found β€” one sentence]
EVIDENCE: [The specific numbers]
SO WHAT: [Why it matters to the business]
ACTION: [What to do about it]
CONFIDENCE: [High/Medium/Low + why]

Example:

INSIGHT: Customer acquisition cost increased 43% in Q3 vs Q2
EVIDENCE: CAC went from $47 to $67, driven by paid search CPC increase (+62%)
SO WHAT: At current LTV of $180, payback period extended from 3.1 to 4.5 months
ACTION: Shift 30% of paid search budget to email/referral channels (CAC $12 and $23 respectively)
CONFIDENCE: High β€” based on complete Stripe + Google Ads data for full quarter

Phase 5: Dashboard & Report Templates

Executive Summary Dashboard (1-page)

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚  EXECUTIVE DASHBOARD β€” [Period]                   β”‚
β”‚                                                    β”‚
β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”β”‚
β”‚  β”‚ Revenue  β”‚ β”‚ Customersβ”‚ β”‚ Margin  β”‚ β”‚  Growth β”‚β”‚
β”‚  β”‚ $XXX,XXX β”‚ β”‚  X,XXX  β”‚ β”‚  XX.X%  β”‚ β”‚ +XX.X%  β”‚β”‚
β”‚  β”‚ β–² +X.X%  β”‚ β”‚ β–² +XXX  β”‚ β”‚ β–Ό -X.X% β”‚ β”‚ vs LY   β”‚β”‚
β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜β”‚
β”‚                                                    β”‚
β”‚  [Trend chart β€” key metric over 12 months]        β”‚
β”‚                                                    β”‚
β”‚  TOP 3 INSIGHTS:                                  β”‚
β”‚  1. [Insight + action]                            β”‚
β”‚  2. [Insight + action]                            β”‚
β”‚  3. [Insight + action]                            β”‚
β”‚                                                    β”‚
β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”        β”‚
β”‚  β”‚ By Segment       β”‚ β”‚ By Channel       β”‚        β”‚
β”‚  β”‚ (table or chart) β”‚ β”‚ (table or chart) β”‚        β”‚
β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜        β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

KPI Formatting Rules

| Element | Rule | Example | |---------|------|---------| | Big numbers | Abbreviate with 1 decimal | $1.2M, 14.3K | | Percentages | 1 decimal, always show direction | β–² +12.3%, β–Ό -4.1% | | Currency | 2 decimals for <$1000, 0 for larger | $47.50, $12,000 | | Dates | Consistent format throughout | Jan 2025, not 01/2025 | | Comparison | Always include baseline | $120K (+15% vs LY) | | RAG status | Use color + text | 🟒 On Track, 🟑 At Risk, πŸ”΄ Behind | | Sparklines | Show direction at a glance | ▁▂▃▅▇ (trending up) |

Chart Selection Guide

What are you showing?
β”‚
β”œβ”€ Change over time β†’ LINE chart (≀5 series) or AREA (stacked composition)
β”‚
β”œβ”€ Comparison across categories β†’ BAR chart (horizontal for long labels)
β”‚
β”œβ”€ Part of whole β†’ PIE (≀5 slices) or STACKED BAR (>5 or over time)
β”‚
β”œβ”€ Distribution β†’ HISTOGRAM or BOX PLOT
β”‚
β”œβ”€ Relationship between 2 variables β†’ SCATTER PLOT
β”‚
β”œβ”€ Geographic β†’ MAP (if location data exists)
β”‚
β”œβ”€ Ranked list β†’ HORIZONTAL BAR sorted descending
β”‚
└─ Single KPI β†’ BIG NUMBER with trend indicator

⚠

Truncated for display β€” read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars2.1k
CategoryAutomation
Updated3mo ago
Forks325

Languages

Python

Trust signals

98/100

From repository metadata: license, adoption, age and documentation. Not a code audit β€” see the Safety scan above for what the skill file itself contains.

1 info
Spreadsheet & Data Wrangling Master β€” Universal Skill: Install & Safety Check | SkillAgent