§Agent skills

What Fulminare reads before it starts.

Every session gets a copy of these at /home/user/.fulminare/skills/ — short, concrete playbooks that tell it which library to reach for and how to verify its own work, instead of reasoning a document format or a dev server setup from scratch every time.

generating-word-docs

Generating Word docs

Builds real .docx reports and briefs with python-docx — never a raw markdown file pretending to be a document.

generating-pdfs

Generating PDFs

Builds real PDFs with reportlab or weasyprint, from scratch or from HTML.

generating-slide-decks

Generating slide decks

Builds real .pptx decks with python-pptx — one idea per slide, charts embedded as images.

generating-spreadsheets

Generating spreadsheets

Builds real .xlsx workbooks with openpyxl — formulas, formatting, multiple sheets.

building-web-apps

Building web apps

Scaffolds a real React/Next.js app instead of loose HTML files, then verifies it actually renders.

serving-static-sites

Serving static sites

Serves plain HTML with a two-line Flask app — never python -m http.server, which leaks a directory listing.

running-background-tasks

Running background tasks

Backgrounds dev servers and slow installs with a task ID, then waits on them properly instead of blocking or polling.

verifying-with-browser

Verifying with browser

Opens what it just built in a real browser and checks it actually works before calling the job done.

visualizing-data

Visualizing data

Turns numbers into the right chart type with matplotlib — never defaults to a bar chart for everything.

debugging-systematically

Debugging systematically

Reproduces, isolates, and fixes the root cause of a bug — not guess-and-check edits.

The format is the same open SKILL.md standard used by Claude, Codex CLI, Cursor, and others — fork the repo, add your own, or read the docs for how Fulminare picks a skill mid-task.