agentleFS
Sign inStart free
RohiRIKRohiRIK/skills/skills/DataReportBuilder/SKILL.md

DataReportBuilder

Skill1 starsChanged 30 days agoMITView on GitHub

Turn a raw Excel/CSV dataset into a two-layer report — plain-language summary plus untouched raw data. USE WHEN someone shares a spreadsheet wanting a report, analysis, summary, or breakdown.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Always run BuildReport end to end — it scopes the audience first, then builds and validates.

    line 24
  2. Distinctive:

    Never mutate the source data — the report is two layers: a plain-language summary plus the untouched raw data.

    line 56

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Data Report Builder

Turns a raw dataset into a two-layer Excel deliverable with a bun + TypeScript engine (Tools/ReportKit.ts, ExcelJS): a plain-language Summary tab a non-technical reader gets in 30 seconds, optional filterable Action tabs, and the untouched Raw Data tab so a technical reviewer can trust it.

Workflow Routing

WorkflowTriggerFile
BuildReport"report", "analysis", "summary", "breakdown", "present this to…"Workflows/BuildReport.md

Always run BuildReport end to end — it scopes the audience first, then builds and validates.

Quick Reference

  • One-time setup: cd Tools && bun install
  • Engine API (intro/cards/table/steps/actionList/rawData/save): read the header docstring of Tools/ReportKit.ts
  • Runnable template to copy: Tools/Example.ts
  • Validate output: bun Tools/Recalc.ts <file.xlsx>

Examples

Example 1: Compliance review

User: "Here's the device export — can you summarise where we stand for management?"
→ BuildReport: asks audience + decision → green/amber/red cards by readiness
→ Action List sorted "Action needed" first → Raw Data verbatim → recalc → hand off

Example 2: Status tracking

User: "Turn this ticket dump into something I can present to the team."
→ BuildReport: breakdown by owner → number cards + breakdown table → filterable tabs

Example 3: Plain understanding

User: "Just help me understand this spreadsheet."
→ BuildReport: defaults (mixed audience, diplomatic) stated in one line → Summary + Raw Data

Gotchas

  • Never mutate the source data — the report is two layers: a plain-language summary plus the untouched raw data. Altering raw values destroys the audit trail.
  • Validate column types before aggregating; a numeric column read as text silently produces wrong totals.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free