Source profileQuality 91/100

shawnstack/quickforge/plugins/spreadsheets/skills/spreadsheets/SKILL.md

spreadsheets

Use this skill when the user asks to create, edit, analyze, model, review, visualize, or structure spreadsheet workbooks such as XLSX-oriented files, CSV/TSV tables, trackers, dashboards, financial models, formulas, charts, or data-analysis sheets.

Source repository stars
48
Declared platforms
0
Static risk flags
1
Last source update
2026-08-06
Source checked
2026-08-06

Decision brief

What it does—and where it fits

Use this skill to create or improve spreadsheet-oriented deliverables. A good spreadsheet is organized, auditable, readable, and fit for the user's purpose. For analysis-heavy tasks, correctness matters as much as formatting.

Best for

  • Creating trackers, schedules, budgets, calculators, models, dashboards, reports, or tabular templates.
  • Working with .xlsx, .xls, .csv, .tsv, or Google Sheets-targeted spreadsheet content.
  • Designing formulas, validations, tables, pivots, charts, or workbook structure.

Not for

  • Tasks that require unconfirmed production actions or broad system permissions.
  • Environments where the pinned source and install steps cannot be inspected.

Compatibility matrix

Platform support, with evidence labels

PlatformStatusEvidenceWhat to check
CodexNot declaredNo explicit evidencePortability before use
Claude CodeNot declaredNo explicit evidencePortability before use
CursorNot declaredNo explicit evidencePortability before use
Gemini CLINot declaredNo explicit evidencePortability before use
Open the compatibility checker

Installation

Inspect first. Install second.

The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.

Source-detected install commandSource
npx skills add https://github.com/shawnstack/quickforge --skill "plugins/spreadsheets/skills/spreadsheets"
Safe inspection promptEditorial

Inspect the Agent Skill "spreadsheets" from https://github.com/shawnstack/quickforge/blob/7f946e28d8398ae43aa5c6de6167cec83f12fa82/plugins/spreadsheets/skills/spreadsheets/SKILL.md at commit 7f946e28d8398ae43aa5c6de6167cec83f12fa82. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.

Workflow

What the source asks the agent to do

  1. 01

    Recommended workflow

    1. Identify the user goal, output format, data sources, and level of rigor. 2. Choose workbook/sheet structure before writing formulas or tables. 3. Draft the table/schema/formulas/charts. 4. Validate calculations and edge cases. 5. If writing to disk, use CSV/TSV/Markdown when…

    Identify the user goal, output format, data sources, and level of rigor.Choose workbook/sheet structure before writing formulas or tables.Draft the table/schema/formulas/charts.
  2. 02

    When to use

    Use this skill for requests involving:

    Creating trackers, schedules, budgets, calculators, models, dashboards, reports, or tabular templates.Working with .xlsx, .xls, .csv, .tsv, or Google Sheets-targeted spreadsheet content.Designing formulas, validations, tables, pivots, charts, or workbook structure.
  3. 03

    Spreadsheet principles

    1. Separate purpose, inputs, calculations, and outputs. For non-trivial workbooks, avoid mixing everything on one sheet. 2. Make assumptions visible. Put assumptions near the top or in a dedicated sheet/section. 3. Use clear labels and units. Headers should be unambiguous. 4. Pr…

    Separate purpose, inputs, calculations, and outputs. For non-trivial workbooks, avoid mixing everything on one sheet.Make assumptions visible. Put assumptions near the top or in a dedicated sheet/section.Use clear labels and units. Headers should be unambiguous.
  4. 04

    Recommended workbook structures

    Title and usage note.

    Title and usage note.Main table with clear columns.Status or category values if useful.
  5. 05

    Simple tracker/template

    Title and usage note.

    Title and usage note.Main table with clear columns.Status or category values if useful.

Permission review

Static risk signals and limitations

Reads files

low · line 67

The documentation asks the agent to read local files, directories, or repositories.

Read the relevant file(s) first.

Evidence record

Why each signal appears

EvidenceSourceComputedTestedEditorial
SignalValueEvidence typeMeaning
Quality score91/100ComputedDocumentation, specificity, maintenance, and trust rules
Repository stars48SourceRepository attention, not individual Skill quality
Compatibility0 platformsSourceDeclared in the catalog source record
Usage guideautomated source guideEditorialGenerated or reviewed according to the visible evidence level

Pinned source

Provenance and original SKILL.md

Repository
shawnstack/quickforge
Skill path
plugins/spreadsheets/skills/spreadsheets/SKILL.md
Commit
7f946e28d8398ae43aa5c6de6167cec83f12fa82
License
MIT
Collected
2026-08-06
Default branch
master
View the original SKILL.md

Spreadsheets skill

Use this skill to create or improve spreadsheet-oriented deliverables. A good spreadsheet is organized, auditable, readable, and fit for the user's purpose. For analysis-heavy tasks, correctness matters as much as formatting.

This QuickForge adaptation intentionally does not depend on Codex cache paths, Codex workspace dependencies, or @oai/artifact-tool. Prefer spreadsheet plans, CSV/TSV outputs, formulas, workbook specs, or Markdown tables first. If the user explicitly needs XLSX generation or editing, explain the available local workflow and ask before using shell commands or external tools.

When to use

Use this skill for requests involving:

  • Creating trackers, schedules, budgets, calculators, models, dashboards, reports, or tabular templates.
  • Working with .xlsx, .xls, .csv, .tsv, or Google Sheets-targeted spreadsheet content.
  • Designing formulas, validations, tables, pivots, charts, or workbook structure.
  • Analyzing spreadsheet data or answering questions about provided tabular files.
  • Reviewing or improving workbook layout, formulas, assumptions, or data quality.

Spreadsheet principles

  1. Separate purpose, inputs, calculations, and outputs. For non-trivial workbooks, avoid mixing everything on one sheet.
  2. Make assumptions visible. Put assumptions near the top or in a dedicated sheet/section.
  3. Use clear labels and units. Headers should be unambiguous.
  4. Prefer auditable formulas. Explain formulas and avoid hidden magic.
  5. Design for maintenance. Tables should be easy to extend.
  6. Validate important outputs. Include checks for reconciliations, totals, or formula consistency when relevant.
  7. Use charts only when they add insight. Every chart should have a takeaway.

Recommended workbook structures

Simple tracker/template

  • Title and usage note.
  • Main table with clear columns.
  • Status or category values if useful.
  • Summary section only if it helps.

Analysis workbook

  • Executive summary or dashboard.
  • Source data.
  • Assumptions.
  • Calculations/model.
  • Outputs/charts.
  • Checks, if correctness depends on formulas or reconciliations.

Financial or operations model

  • Summary/dashboard.
  • Inputs/assumptions.
  • Historical/source data.
  • Model/calculations.
  • Scenarios/sensitivity.
  • Checks.

Recommended workflow

New spreadsheet-oriented deliverable

  1. Identify the user goal, output format, data sources, and level of rigor.
  2. Choose workbook/sheet structure before writing formulas or tables.
  3. Draft the table/schema/formulas/charts.
  4. Validate calculations and edge cases.
  5. If writing to disk, use CSV/TSV/Markdown when sufficient; ask before attempting XLSX generation.

Editing or analyzing existing spreadsheet data

  1. Read the relevant file(s) first.
  2. Determine whether the user wants an answer, a file edit, or a new artifact.
  3. Preserve existing formulas and patterns unless asked to refactor.
  4. For formula changes, explain changed logic.
  5. For data analysis, call out data quality risks and assumptions.

Formula guidance

  • Prefer formulas that are understandable to spreadsheet users.
  • Use consistent row/column references.
  • Document non-obvious formulas.
  • Avoid volatile functions unless needed.
  • For financial models, keep assumptions editable and outputs linked.

Chart guidance

When specifying charts, include:

  • Chart type.
  • Source data range or fields.
  • X/Y axes.
  • Series.
  • Main takeaway.
  • Any annotations or formatting guidance.

Do not create charts with invented data. If data is missing, ask for it or propose placeholders.

XLSX / Google Sheets-oriented requests

QuickForge currently provides this as a spreadsheet-planning/workflow skill, not a bundled spreadsheet runtime. For XLSX or Google Sheets deliverables:

  • First create a precise workbook spec, CSV/TSV data, or formulas.
  • If XLSX creation/editing is required, ask before running shell commands.
  • Do not assume Excel, LibreOffice, Python libraries, Node packages, or Google APIs are available.
  • Do not install dependencies unless the user explicitly asks and approves.

Final response guidance

When delivering spreadsheet content inline, make it easy to copy into a sheet. When files are created or edited, include:

  • The file path.
  • The sheet/table structure.
  • Key formulas or assumptions.
  • Validation performed or remaining risks.

Alternatives

Compare before choosing

Computed 8738,680

AstrBotDevs/AstrBot

spreadsheets

Create, read, edit, analyze, convert, chart, and validate spreadsheet files including XLSX, XLSM, XLS, CSV, and TSV. Use when a spreadsheet is a primary input or deliverable, or when tabular data must remain editable and auditable in workbook form.

Computed 8869

PaulRBerg/agent-skills

spreadsheets

Use when CSV, TSV, or Excel (.xlsx) is the primary input/output: inspect, transform, validate, convert, recalc formulas, or create/fix spreadsheets. Do not trigger when tabular data is incidental.

Computed 9832,785

K-Dense-AI/scientific-agent-skills

dask

Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.

Computed 97148

JasonColapietro/suede-creator-skills

suede-instagram-growth

Suede-owned Instagram growth operating system for account-specific audits, Reels, carousels, Stories, conversion mapping, calendars, and daily candidate-production loops. Use when the user names Instagram, IG, Reels, Stories, asks to analyze recent posts, grow a handle, run a daily workflow, create or repurpose Instagram content, or distinguish views from follows, leads, and sales. NOT FOR: multi-platform organic strategy (use suede-social), full video rendering or editing (use suede-video), pai