agentleFS
MicrosoftKnown publishermicrosoft/new-copilot-studio-tech-guide/sample/archive/store-solution/skills/merch-report-html/SKILL.md

merch-report-html

Skill21 starsChanged 5 months agoMITView on GitHub

Generate the shareable end-of-quarter markdown review as a single self-contained interactive HTML report by running the bundled merch_report.py script. Use as the final step once the analysis and policy-bound markdown recommendations are decided. The script renders top sellers, slow movers, and the markdown recommendations into one BlastBox Omega themed HTML file with inline SVG charts, sortable tables, and a clearance toggle - no internet, no external assets. Hand the file to the manager to download and open in any browser.

1 other project uses a version of this.

Adopted by

Most recently taken up by

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. Very specific:

    Use this as the last step, after sales-analysis has produced the top sellers and slow movers and markdown-optimizer has produced the …

    line 15
  2. Distinctive:

    If the template file is missing it falls back to a minimal embedded template.

    line 68
  3. Distinctive:

    Never invent numbers - every figure comes from the analysis, optimizer, and Store Policy Agent results.

    line 71

≈ “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

Merch Report (interactive HTML)

This skill produces the shareable report that closes out the end-of-quarter markdown review by running the bundled merch_report.py script. You do not write any Python and you do not invent numbers: every value comes from the earlier steps. The script renders one self-contained, interactive HTML file (BlastBox Omega theme) - all CSS, JavaScript, and SVG charts are inlined, so it references nothing external and works fully offline once downloaded.

Use this as the last step, after sales-analysis has produced the top sellers and slow movers and markdown-optimizer has produced the policy-bound recommendations.

Inputs (pass the JSON you already have as flags)

FlagSource
--top-sellerstop sellers from sales-analysis - [{name, units, velocity, revenue}]
--slow-moversslow movers from sales-analysis - [{name, sku, weeks_of_cover, price, cost, margin}]
--recommendationsRECOMMENDATIONS_JSON from markdown-optimizer - [{name, sku, price, rec_discount_pct, new_price, new_margin, binding, flag_clearance}]
--policythe guardrails from the Store Policy Agent - {max_discount_pct, margin_floor_pct, min_useful_promo_discount_pct}
--windowthe review window label, e.g. "Apr 12 - May 31, 2026"
--weeksanalysis window length (default 8)
--woc-thresholdslow-mover weeks-of-cover threshold (default 8)
--outoutput path (default merch_report.html)

Run the bundled script

python3 merch_report.py \
    --window "Apr 12 - May 31, 2026" --weeks 8 \
    --top-sellers '[{"name":"MEGA Lizards from Outer Space","units":540,"velocity":67.5,"revenue":37794.6}]' \
    --slow-movers '[{"name":"OmegaVision VR Headset","sku":"SKU-VR-GOGGLES","weeks_of_cover":64.0,"price":199.99,"cost":70.0,"margin":65.0}]' \
    --recommendations '[{"name":"OmegaVision VR Headset","sku":"SKU-VR-GOGGLES","price":199.99,"rec_discount_pct":30.0,"new_price":139.99,"new_margin":50.0,"binding":"max_discount","flag_clearance":false}]' \
    --policy '{"max_discount_pct":30,"margin_floor_pct":15,"min_useful_promo_discount_pct":10}'

The script writes merch_report.html to the working directory and prints a one-line confirmation (file size + counts). Hand that file back as a download.

What the report contains (so you can describe it)

  • A KPI strip: slow movers, promo markdowns, items flagged for clearance, deepest promo cut, average new margin.
  • Top Sellers and Slow Movers sections, each with an inline SVG bar chart (the slow-mover chart marks the weeks-of-cover threshold) and a sortable table.
  • A Markdown Recommendations section: a discount-depth chart, the policy chips, a sortable table showing current price, discount, new price, new margin, and the binding constraint, with clearance-flagged rows highlighted and a toggle to hide them.

Report back

Tell the manager the interactive report is ready (merch_report.html), that it opens in any browser, and that tables are sortable and clearance items can be toggled. Summarize the headline: how many promo markdowns, the deepest cut, and which items were routed to clearance.

Notes

  • The bundled files are merch_report.py and report_template.html.j2; the script uses only the Python standard library plus Jinja2 (available in the runtime). If the template file is missing it falls back to a minimal embedded template.
  • The report inlines everything - no CDN, no web fonts, no network. It is safe to share and open offline.
  • Never invent numbers - every figure comes from the analysis, optimizer, and Store Policy Agent results. All data is mock; for demo purposes only.

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.

Reviews can't be read right now.

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.