# AI workflow demo - create a skill with evals in antigravity

DevFeed: [AI workflow demo - create a skill with evals in antigravity](<https://devfeed.tech/articles/ai-workflow-demo-create-a-skill-with-evals-in-antigravity-113368.md>)

Original publisher: [Read original article](<https://www.maiatoday.net/p/ai-workflow-skills-evals/>)

Published: 2026-11-01T17:01:30Z

Content type: tutorial

Language: en

Sources: [Maiatoday](<https://devfeed.tech/sources/maiatoday.md>)

Topics: [Test automation](<https://devfeed.tech/topics/test-automation.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [evals](<https://devfeed.tech/tags/evals.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [repo](<https://devfeed.tech/tags/repo.md>), [resources](<https://devfeed.tech/tags/resources.md>), [skill-creator](<https://devfeed.tech/tags/skill-creator.md>), [skills](<https://devfeed.tech/tags/skills.md>), [summary](<https://devfeed.tech/tags/summary.md>), [test](<https://devfeed.tech/tags/test.md>), [testing](<https://devfeed.tech/tags/testing.md>), [want](<https://devfeed.tech/tags/want.md>), [work](<https://devfeed.tech/tags/work.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

## AI overview

The author recommends pairing important skills with evals so their behavior can be checked, repeated, and revisited. Evals record triggering prompts, expected outcomes, and optional fixtures or code snippets. In the Antigravity demo, Anthropic's `skill-creator` builds a repository-history catch-up skill and two eval cases; the author reviews and edits the evals, then runs them with and without the skill using the currently loaded model. The reported result suggests the skill helps in that scenario. Evals are also presented as a way to check whether newer models can do the task without the skill. For reusable skills, the author found Antigravity's `~/.gemini/config/skills` location unavailable to other agents, so chose `~/.agents/skills` with symlinks to agent-specific locations. The Anthropic version of `skill-creator` stores results in a sibling `<skill-name>-workspace` folder, which the author says Claude Code ignores and some agents may error on; they changed it to store results beside the evals.

## Source excerpt

What When I create an important skill for me or my team it is useful to know if it works. To do this I also create an eval that contains what prompt is used to trigger the skill and what the outcome should be. The eval can also contain fixtures and sample code snippets to work on. This workflow isn't specific to antigravity but I tested it there. Why Sharing If I am sharing skills with other people I want to make sure they work as expected. Initially I would test them by hand a few time but I would have to rely on my memory to know if the work. Also this manual testing takes a long time. With evals I can automate these steps. Model changes Models become more powerful and sometimes the skills become obsolete because newer models know how to do the tasks. With an eval I can see if the model can perform better than the skill. If it does then the skill can be deleted and the context freed up. Future me If I come back to a skill after some time, sometimes I can't remember how it worked. If I read the eval I can see what I expected it to do Resources A useful open source skill that you can use to create skills and evals and run evals is skill-creator from anthropic. A good tutorial explaining how to create a skill including the evals. General skills documentaion Demo Creating a skill and an eval Use the skill-creator to create a new skill. The detail of what the skill does doesn't matter. How you ask for it and checking that the evals are created is the most important part of this workflow. For our example I am creating a skill to pull the history on a repo after I come back from some time away touching grass. The prompt is this use skill creator to create a user level skill that will pull the history of a git repo and give me a summary of what happened while I was away. The time period could be anything but typically 6 weeks. Summarise by type of tasks, features, chores and show who did the work. Also group related tasks. I want to use this to get a scanable overview of