I counted every skill my AI invoked across 55 sessions. Here’s the leaderboard.

Description and use

The author counted skill invocations across 55 development sessions of ParkEase, finding that the workflow router, design skills, and safety nets were most used, while test‑driven development, though invoked rarely, produced thousands of tests, demonstrating high impact.

Problem

Determine which installed AI skills actually contributed most during development of ParkEase.

Outcome

The workflow router (‘flow’) was invoked 28 times, the most of any skill, followed by design skills and safety nets. Test‑driven development, though invoked only 4 times, produced 3,246 unit tests and 1,080 integration tests, showing high impact. The study informs which skills to prioritize when starting a new project.

Workflow

• 1. Gathered all 55 ParkEase sessions (10 Sep–19 Oct).
• 2. Searched Claude Code transcripts for explicit skill invocations.
• 3. Counted invocations per skill.
• 4. Compiled leaderboard table.
• 5. Analyzed surprising patterns and impact.
• 6. Listed recommended skills for future projects.

Evidence

I searched all 55 ParkEase sessions (10 September to 19 October) for every time the agent explicitly invoked a skill.

Source

The router came first. <code>flow</code> doesn't write a line of code. It decides which other skills run.

Source

Only 4 explicit calls, because it was loaded once per build phase and stayed loaded. Its output, 3,246 unit tests and 1,080 integration tests, is the clearest proof that invocation counts undersell the skills that stick.

Source