Agent skill

Pivot Analysis Planner

by mohitagw15856 in mohitagw15856/pm-claude-skills

Plan pivot-table analysis that answers the actual question — the question-to-layout mapping (rows, values, filters chosen on purpose), the data-shape check that pivots require, and the drill-down…

MITAuto-check passedDocuments & Office

Install Pivot Analysis Planner

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill pivot-analysis-planner -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills pivot-analysis-planner --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/pivot-analysis-planner .claude/skills/pivot-analysis-planner && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
pivot-analysis-planner
GitHub stars
1.4k
Token cost
~1.2k tokens
SKILL.md length
634 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Plan pivot-table analysis that answers the actual question — the question-to-layout mapping (rows, values, filters chosen on purpose), the data-shape check that pivots require, and the drill-down…

  • Works in 5 steps: Question first, layout second: each… → Tidy data or fix it first: pivots need… → Values need their aggregation chosen,… → …
  • Asked analyze this data with a pivot
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework: The Planning Rules and Output Format, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Pivot Analysis Planner is an agent skill from mohitagw15856/pm-claude-skills. Plan pivot-table analysis that answers the actual question — the question-to-layout mapping (rows, values, filters chosen on purpose), the data-shape check that pivots require, and the drill-down path from summary to so-what. Use when asked analyze this data with a pivot, what's driving the total, break this down by category and month, or my pivot shows nonsense. Produces the question decomposition, the pivot layout(s) with reasons, the data-shape fixes needed first, and the reading guide.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Documents & Office, covering Excel spreadsheets. The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • Asked analyze this data with a pivot
  • Whats driving the total
  • Break this down by category and month
  • My pivot shows nonsense

Example prompts

  • “/pivot-analysis-planner”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Question first, layout second: each pivotable question maps to a layout — "what drove the change" → dimension in rows, period in columns…
  2. Tidy data or fix it first: pivots need one-row-one-record: unmerge cells, delete pre-baked subtotal rows (they double-count), unpivot…
  3. Values need their aggregation chosen, not defaulted: SUM for additive things, COUNT for events, AVERAGE almost never without a…
  4. Filters are the scope contract: what's excluded (test rows, internal accounts, incomplete current month) gets decided and stated in the…
  5. Plan the drill, then the so-what: the summary pivot points somewhere; the plan names the next cut ("if the East drop is real, re-pivot…

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Pivot Analysis Planner loads about 1.2k tokens when it runs. Until then it costs about 129 tokens; SKILL.md has 634 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~129
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 634 words, ~1,239 tokens.

Download SKILL.mdSave it as .claude/skills/pivot-analysis-planner/SKILL.md (or your agent's skills folder).
name
pivot-analysis-planner
description
Plan pivot-table analysis that answers the actual question — the question-to-layout mapping (rows, values, filters chosen on purpose), the data-shape check that pivots require, and the drill-down path from summary to so-what. Use when asked analyze this data with a pivot, what's driving the total, break this down by category and month, or my pivot shows nonsense. Produces the question decomposition, the pivot layout(s) with reasons, the data-shape fixes needed first, and the reading guide.

Pivot Analysis Planner Skill

Pivot tables answer "what's driving X" in seconds — when the layout matches the question and the data is shaped right. Most pivot frustration is one of those two: a layout assembled by dragging until something looks meaningful, or data that isn't tidy (merged cells, subtotal rows baked in, one-column-per-month) feeding a pivot that double-counts. This skill works backwards from the question: decompose it, shape-check the data, choose the layout deliberately, and plan the drill-down — because the first pivot is the start of the analysis, not its output.

What This Skill Produces

  • The question decomposition — the vague ask ("analyze sales") turned into pivotable questions ("which product line drove the Q2 change, and is it price or volume?")
  • The shape check — the data problems that break pivots, found before the pivot finds them
  • The layout plan — rows/columns/values/filters per question, each placement with its reason
  • The reading guide — what the pivot will show, the drill-down path, and the so-what test

Required Inputs

Ask for these if not provided:

  • The question, pushed to specific: "analyze this" becomes 2–3 answerable questions — the decomposition is half the skill, and it needs the user's intent
  • The data's shape — columns and a sample; tidy (one row = one record, one column = one variable) or the fixes list gets written first
  • The comparison that matters — vs last period? vs plan? across segments? Comparisons decide the column dimension and whether calculated fields are needed

Framework: The Planning Rules

  1. Question first, layout second: each pivotable question maps to a layout — "what drove the change" → dimension in rows, period in columns, delta readable across; "where is it concentrated" → dimension in rows, values sorted descending, running % if available. Dragging-until-interesting produces coincidences, not answers.
  2. Tidy data or fix it first: pivots need one-row-one-record: unmerge cells, delete pre-baked subtotal rows (they double-count), unpivot month-columns into a date column (data-cleaning-pass handles the mess). Five minutes of shaping saves an hour of pivot mystery.
  3. Values need their aggregation chosen, not defaulted: SUM for additive things, COUNT for events, AVERAGE almost never without a weight-check (the average-of-averages trap). Every value field's aggregation is a decision with a reason.
  4. Filters are the scope contract: what's excluded (test rows, internal accounts, incomplete current month) gets decided and stated in the output — an unlabeled filtered pivot is how two people present different totals from one dataset.
  5. Plan the drill, then the so-what: the summary pivot points somewhere; the plan names the next cut ("if the East drop is real, re-pivot East by product") and ends at the so-what test — a pivot finding that suggests no action or decision was trivia, and the reading guide says which findings would matter.
Show full SKILL.md (188 more words)Show less

Output Format

Pivot Plan: [dataset] — question: [the real one]

Decomposition

[The ask → 2–3 pivotable questions]

Shape Check

[Tidy? · the fixes needed first, if any]

Layouts

QuestionRowsColumnsValues (aggregation + why)Filters (stated)

Reading Guide

[What each layout will show · the drill path · the so-what test: which findings change a decision]

Quality Checks

  • Every layout traces to a decomposed question
  • The shape check ran before any layout advice
  • Every value field's aggregation has a reason; average-of-averages is guarded
  • Filters/exclusions are stated where the output will be shown
  • The drill-down path and so-what test exist — the pivot is a step, not the deliverable

Anti-Patterns

  • Do not drag until interesting — layouts follow questions or they follow noise
  • Do not pivot over baked-in subtotal rows — the double-count classic
  • Do not average averages — weight or don't
  • Do not present a filtered pivot without its scope note — that's how meetings get two truths
  • Do not stop at the summary — the first pivot locates the question; the drill answers it

Example Trigger Phrases

  • "Analyze this data with a pivot."
  • "What's driving the total?"
  • "Break this down by category and month."
  • "My pivot shows nonsense."

© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/pivot-analysis-planner of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Pivot Analysis Planner next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Pivot Analysis Planner compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pivot Analysis Planner this skillmohitagw15856/pm-claude-skills1.4k—~1.2kAutomated safety check: PassMIT
MarkitdownImCa0/just-laws78114 repos~3.2kAutomated safety check: NotesMIT
Managing Google Workspacetaylorwilsdon/google_workspace_mcp3.3k—~2.9kAutomated safety check: PassMIT
Data Table Managern8n-io/n8n207k—~2.3kAutomated safety check: PassCustom licence
Docx4jplutext/docx4j2.4k—~2.5kAutomated safety check: PassNone
Instrument Data To Allotropeaws-samples/amazon-bedrock-agents-healthcare-lifesciences2742 repos~2.7kAutomated safety check: PassApache-2.0

Similar skills

  • Markitdown

    ImCa0/just-laws

    Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.

    781 GitHub starsUsed in 14 repos~3.2k tokens
    Documents & OfficeAuto-check: notes
  • Managing Google Workspace

    taylorwilsdon/google_workspace_mcp

    Manages Google Workspace operations across 12 services (Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms, Tasks, Contacts, Chat, Apps Script, Custom Search).

    3.3k GitHub stars~2.9k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Official

    Load before calling data-tables or parse-file. An agent skill from n8n-io/n8n.

    207k GitHub stars~2.3k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Docx4j

    plutext/docx4j

    A skill your agent uses when writing Java code that creates, reads or edits Word (.docx), PowerPoint (.pptx) or Excel (.xlsx) files with docx4j — including generating documents, editing existing…

    2.4k GitHub stars~2.5k tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • Instrument Data To Allotrope

    aws-samples/amazon-bedrock-agents-healthcare-lifesciences

    Official

    Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV.

    274 GitHub starsUsed in 2 repos~2.7k tokens
    Documents & OfficeAuto-check passed
  • Cyber Ppt

    crazyykhllc-bit/CyberPPT

    当用户需要把 DOCX、PDF、TXT、XLSX、研究报告、业务材料或原始数据转成高密度、可编辑、咨询风格 PPTX 时使用;也适用于需要 SCR 论证、视觉风格探索、详细图表和渲染质检的 PPT。

    1.8k GitHub stars~10k tokensUpdated 2 mo ago
    Documents & OfficeAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo
  • Car Tco

    mohitagw15856/pm-claude-skills

    Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…

    1.4k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Fire Number

    mohitagw15856/pm-claude-skills

    Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.

    1.4k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

Questions about Pivot Analysis Planner

What does Pivot Analysis Planner do?

Plan pivot-table analysis that answers the actual question — the question-to-layout mapping (rows, values, filters chosen on purpose), the data-shape check that pivots require, and the drill-down…. Pivot Analysis Planner is an agent skill from mohitagw15856/pm-claude-skills. Plan pivot-table analysis that answers the actual question — the question-to-layout mapping (rows, values, filters chosen on purpose), the data-shape check that pivots require, and the drill-down path from summary to so-what.

When should I use Pivot Analysis Planner?

Pivot Analysis Planner fits situations like: asked analyze this data with a pivot; whats driving the total; break this down by category and month; my pivot shows nonsense.

How do I install Pivot Analysis Planner in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill pivot-analysis-planner -a claude-code`. Or copy the skill folder (skills/pivot-analysis-planner in mohitagw15856/pm-claude-skills) into .claude/skills/pivot-analysis-planner in your project. Claude Code loads it when a task matches its description.

How do I install Pivot Analysis Planner in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill pivot-analysis-planner -a codex`. Or copy the skill folder (skills/pivot-analysis-planner in mohitagw15856/pm-claude-skills) into .agents/skills/pivot-analysis-planner in your project. Codex loads it when a task matches its description.

Can I use Pivot Analysis Planner in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mohitagw15856/pm-claude-skills --skill pivot-analysis-planner -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pivot-analysis-planner, .gemini/skills/pivot-analysis-planner, .github/skills/pivot-analysis-planner and .opencode/skills/pivot-analysis-planner in your project.

What does Pivot Analysis Planner need to run?

SKILL.md names no scripts, command-line tools or credentials: Pivot Analysis Planner is instructions for the agent only.

Does Pivot Analysis Planner access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Pivot Analysis Planner safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Pivot Analysis Planner use?

Pivot Analysis Planner is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pivot Analysis Planner use?

About 1.2k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Pivot Analysis Planner?

Skills that share tags, products or a category with Pivot Analysis Planner: Markitdown (ImCa0/just-laws, 781 stars), Managing Google Workspace (taylorwilsdon/google_workspace_mcp, 3.3k stars), Data Table Manager (n8n-io/n8n, 207k stars) and Docx4j (plutext/docx4j, 2.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pivot Analysis Planner?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.

Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.