agentleFS
Sign inStart free
MicrosoftKnown publishermicrosoft/copilot-studio-gallery/submissions/sales-analyser/solution/botcomponents/crf9c_salesanalyser_WEs93i.file.skillmd_k_QDN/filedata/SKILL.md

polished-report-builder

Skill14 starsChanged 11 days agoMITView on GitHub

Use when the user asks to turn analysis results, metrics, or findings into a polished, presentation-ready report, one-pager, or executive summary -- especially when existing analysis (e.g. from the spreadsheet analysis skill) needs to become a document someone will actually read. Builds a branded PDF with reportlab from a short content file (headline, KPI tiles, one chart per point, data notes and the non-audit disclaimer) using the shared brand tokens, and runs a QA pass before delivery to catch walls of text, chart clutter, low-resolution charts, missing data notes or poor contrast. Do NOT use for a quick inline chat answer, a single ad-hoc chart with no report structure around it, a raw data export with no narrative, or to compute the figures themselves.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Headline: if the user hasn't given a conclusion, propose one from the analysis.

    line 20
  2. Very specific:

    Length: default one-pager; short or multi-section only when asked (references/content-balance-guide.md).

    line 21
  3. Distinctive:

    Never upload, save or move the PDF (or any output) to SharePoint - it is read-only for this agent.

    line 53

≈ “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

Polished report builder (PDF)

A good report is one headline the reader can repeat, a few numbers with context, one chart per point and honest data notes - not page count. This skill turns analysis that already exists into a branded PDF.

Branding - edit here. Colours, fonts, logo, header eyebrow and the footer disclaimer all come from spreadsheet-data-analysis-reporting/assets/style-tokens.json - the single brand file shared with the charts and the email. Don't edit colours in this skill. references/style-tokens.md explains each token. Logo: the PDF header draws spreadsheet-data-analysis-reporting/assets/logo-placeholder.png (a placeholder bar-chart icon on a white tile). To swap it, replace that file with your own PNG under the same name, or add your file to that assets/ folder and change brand.logo_path; brand.logo_height_pt sets its size. The header band is brand blue, so use a logo with its own light background or a light mark.

1. Clarify (one short question at most)

  • Headline: if the user hasn't given a conclusion, propose one from the analysis.
  • Length: default one-pager; short or multi-section only when asked (references/content-balance-guide.md).
  • Inputs: reuse the figures, chart PNGs and Data notes from the analysis skill. If figures don't exist yet, run the analysis skill first - never compute figures here.
  • Delivery: the PDF goes to the user as a chat attachment; for email, hand over to newsletter-style-email-composer, which attaches the PDF to the draft. Never save it to SharePoint.

2. Draft the content file

Copy assets/report-content-example.json to the working folder as report_content.json and fill it in:

  • headline: one sentence, 20-35 words, with a number and a comparison.
  • kpis: 2-5 tiles; each has a value, what it is, and its comparison (delta, direction). Set good_when_down: true for costs/returns so colours read correctly.
  • sections: one chart per point (chart = PNG from chart_style.py with apply_theme("report")), a caption, up to 3 bullets of ~20 words, optional small table (numeric_columns are right-aligned).
  • recommendations: actions, not observations.
  • data_notes: scope, transformations, fx, flags, caveats - all required (write "none" if nothing applies).

3. Render

python scripts/render_report.py report_content.json report.pdf - A4 PDF with a brand header band, headline callout, KPI tiles, charts at full column width, right-aligned table numbers, Data notes and the disclaimer plus page numbers on every page. Uses DejaVu Sans (bundled with matplotlib) so text matches the charts; chart PNGs are compressed for a small file.

4. QA before anyone sees it

python scripts/qa_report.py report_content.json --pdf report.pdf [--report-type one-pager] checks density budgets, headline, KPI labels, chart resolution (>= 1000 px), Data notes, page count, PDF size and brand contrast. Fix every FAIL and re-run; mention any WARN. Open the PDF and look at it once before delivering.

5. Deliver

  • Chat: give the headline, KPIs and the Data notes, and attach report.pdf to your reply as a chat attachment.
  • Email: hand over to newsletter-style-email-composer with the PDF (sandbox file path), the headline, KPIs and Data notes; it attaches the PDF to the draft.
  • Never upload, save or move the PDF (or any output) to SharePoint - it is read-only for this agent.

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