agentleFS
BenaliHQBenaliHQ/paxus-skills/skills/monthly-dashboard/SKILL.md

monthly-dashboard

Skill4 starsChanged 16 days agoNo licenceView on GitHub

Build the one-page monthly financial dashboard for any Paxus CFO, advisory, or bookkeeping client — non-profit or for-profit. For non-profits it fronts the monthly board financials package (CFO / non-profit clients); for for-profit clients it is the client's own monthly dashboard (Wheel of Service businesses, advisory clients, and similar). Pulls monthly financials from the client's shared Drive (gws CLI in Claude Code; the connected Drive folder in Cowork), reads the client's context bundle (when there is one) to understand the audience, computes bespoke KPIs against confirmed benchmarks, offers the controller up to three headliner, chart, and client action-step options (each with a "why this one") to pick from or decline, renders a brand-consistent one-page dashboard to PDF, and either merges it as page 1 of the board package, delivers it standalone, or hands it off to the monthly client email. For repeat clients, uses the prior delivered dashboard and the per-client spec file as the spec; for brand-new clients, runs a cold-start intake, defaults to standalone/no-trend, documents benchmark sources, and saves the approved spec for future months. Use when the operator asks to build a monthly dashboard, make the dashboard, build the board/client dashboard, add the dashboard to monthly financials, or prepend a dashboard to a board financials package. SCOPED TO THE DASHBOARD PAGE — it does not draft the client email or update the forecast workbook.

The file

Show its rules and text

We split this skill into the rules it gives an agent

40 rules. About 0 are common, 30 are distinctive, and 10 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈30

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 10

    Very specific

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

No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “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.

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.