Skip to main content

AI skills for everyday work

What do you want to get done?

Find a tested SKILL.md skill, follow clear setup instructions, and try it in Claude, ChatGPT, Gemini, or your own coding agent.

Source-linked SKILL.md listingsDownloadable practice filesExplicit output checklists

Step-by-step practice

Start with a ready-made task

Sample files, step-by-step instructions, and an example result. Choose one and follow along in your own AI tool.

All guided tasks
pdfxlsx
Recorded example output

Turn a PDF table into a usable Excel sheet

Extract six invoice lines, keep their source references, and reconcile the result before using it.

An editable workbook with all six items and a checked USD 1,250.00 subtotal.

Sample inputs included · beginner

Try this workflow
xlsxdocx
Recorded example output

Turn a sales spreadsheet into a monthly report

Check two months of figures, build a formula-backed summary, and write an editable one-page review.

A summary workbook and a Word report that distinguish revenue growth from margin change.

Sample inputs included · intermediate

Try this workflow
pptx
Recorded example output

Turn meeting notes into decision slides

Build a five-slide launch review that preserves decisions, owners, deadlines, and unresolved questions.

An editable PowerPoint deck with five slides and source references in its speaker notes.

Sample inputs included · beginner

Try this workflow

Portable SKILL.md format

Works across your AI tools

Browse listings grouped by the coding agent or assistant you use every day.

Curated starting points

Useful skills to start with

Selected from the directory for clear instructions and sources, with guided skills first. Check each skill’s setup before you start.

Browse all skills
Agent skillFirst-run guide

Systematic Debugging

A root-cause debugging loop for coding agents: reproduce, isolate, hypothesize, then change one thing — instead of shotgun patches.

Agent skillFirst-run guide

Test Driven Development

Force a coding agent to write a failing test first, then the minimum implementation, then refactor — so it cannot claim done without a red-green loop.

Agent skillFirst-run guide

Webapp Testing

Use Python Playwright to test local web applications, inspect visible UI behavior, capture screenshots, and collect browser logs.

Agent skillFirst-run guide

Skill Creator

Scaffold a new AI agent skill from a plain-language job description: folder, SKILL.md frontmatter, trigger description, and a first draft of the instructions.

Agent skillFirst-run guide

Docx

Create and edit Microsoft Word (.docx) files with headings, tables, and tracked-change-friendly structure from an agent workflow.

Agent skillFirst-run guide

Pdf

Read, fill, extract, and generate PDF documents from an agent session — forms, reports, and print-ready files rather than markdown-only output.

Documentation & concepts

New to skills? Start here

All guides

Looking for newly added listings or weekly summaries?

Explore fresh additions or read dated directory snapshots.

Weekly digest

Receive published digests of new listings and catalogue updates. Confirm your email to join.

Double opt-in required. You may unsubscribe at any time.