Skip to content

skilldrop·docs·How-to

Use the Skill engineering pack

Install the Skill engineering pack, run its first task, and follow a typical session step by step.

For people writing Agent Skills in their own repos: write a portable SKILL.md folder from a described task, then audit any skill for routing, portability, safety, structure and evals before you share it.

Reach for it when: You keep explaining the same task to your coding agent, or you are about to share or install a skill and want to know it will route, work in every tool, and do nothing unsafe.

1. Install it

npx skilldrop-cli install --pack skill-engineering                 # Claude Code, your user folder
npx skilldrop-cli install --pack skill-engineering --project       # Claude Code, this repo
npx skilldrop-cli install --pack skill-engineering --ide cursor    # or kiro, codex, antigravity, copilot
npx skilldrop-cli install --pack skill-engineering --local         # this repo, hidden from git

In Claude Code you can also add the marketplace once (/plugin marketplace add sananthanarayan/skilldrop) and run /plugin install skill-engineering@skilldrop.

It brings core with it, so the shared skills are there too.

2. Run the first task: turn a task you keep explaining into a skill, then review it

Before you start:

Paste this into your agent:

Make a skill that writes customer-facing release notes from the merged PRs I paste: grouped New / Improved / Fixed, breaking changes first, one line per PR with its number. We use Claude Code and Copilot, and we already have a launch-post skill for announcements. Then review the skill before I commit it.

How to tell it worked: skill-author writes a folder with SKILL.md, a template and evals, plus the install path for each of your tools, and skill-review returns a READY, FIX FIRST or REWRITE verdict with the lint script's output pasted in.

If nothing happens: If a skill does not activate, ask for it by name ("use skill-author"). If the lint script will not run, check that python3 is on your PATH; skill-review can walk the same checks by hand.

3. A typical session

Bring:

A session takes about 20–40 minutes.

  1. skill-author: Describe the task, the trigger phrases and the nearby skills, and answer one round of questions. You get: A skill folder: SKILL.md with a routable description, steps, quality bar, boundaries and anti-patterns, plus a template, evals, and the install path for each tool.
  2. skill-review: Point it at the folder and at the folder that holds your other skills. You get: The lint script's output and a verdict with severity-tagged findings on routing, portability, safety, structure and evals, each with a fix. You decide: Commit the skill, apply the fixes and review again, or rewrite it around one artifact.

You end with: A reviewed skill that installs into each of your tools from one folder, with evals to rerun when you change it.

Next

Edit this page on GitHub · View source