Two testing skills · both proven

grilling vs skill-creator

Both skills were run through Claude twice: once on a fixed brief without the skill, once with it. The briefs differ because each is written for the job the skill claims to do, so compare each skill against its own baseline, then decide which difference matters for your work.

grilling

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Category: Testing
Source: mattpocock/skills
License: MIT
Proof model: claude-opus-5-5
Brief: “Here is my plan. I want to launch a paid newsletter for independent game developers in six weeks. It will cost $8 a month, come out every Tuesday, and cover marketing tips, funding opportunities and interviews with developers who shipped on Steam. I have 1,200 followers on X and no email list yet. My goal is 500 paying subscribers in the first year. Grill me on this plan, and present the result as a single HTML page: every question you would ask me, in the order you would ask it, why each one matters, and what a weak answer would tell you.”
Skill commit: 5beb35b

Without the skillWith grilling

⇆

Without, runWith grilling, run3 independent runs per side, none selected by hand.

Download the with-skill page

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Category: Testing
Source: anthropics/skills
License: Not stated
Proof model: claude-opus-5-5
Brief: “Write a complete SKILL.md for a skill called release-notes that turns a list of merged pull request titles into customer-facing release notes grouped by feature, fix and breaking change, in the tone of a small developer-tools company. Present the finished SKILL.md as a single HTML page, with the frontmatter and body shown in a code block and a short note under it on how you decided what to include.”
Skill commit: dbd4588

Without the skillWith skill-creator

⇆

Without, runWith skill-creator, run3 independent runs per side, none selected by hand.

Download the with-skill page

We don’t pick a winner for you: the pages are the evidence. Both proofs can be repeated with the brief, model and commit shown above. See alternatives to grilling or alternatives to skill-creator.