Use when writing, debugging, or reproducing GPUI tests in Zed, including gpui::test arguments, TestAppContext parameters, scheduler seeds, ITERATIONS/SEED reproduction, parking failures, and pending task traces.
Add, modify, or test a custom dylint lint in `tooling/lints`. Covers the module/registration layout, UI test conventions (including negative tests and the gpui test fixture), how to run tests with the crate's pinned nightly and update `.stderr` files, and how to validate a lint against the real codebase with `single-lint`. Use whenever the user asks to write a new lint or debug an existing one.
Cherry-pick one or more merged PRs and/or commits into Zed's `preview` or `stable` release branch. Use this whenever the user mentions cherry-picking to preview/stable, a failed cherry-pick run, or wants to manually port fix(es) into a release branch.
Helps you create new agent skills for Zed. Use this to create a skill, ask about SKILLs.md, or package reusable agent instructions.
Write clear, developer-first copy for Zed — leading with facts, grounded in craft.
Remove signs of AI-generated writing from text. Use after drafting to make copy sound more natural and human-written. Based on Wikipedia's "Signs of AI writing" guide.
Write clear, developer-first copy for Zed — leading with facts, grounded in craft.
Design, write, review, run, and interpret production-shaped GPUI Criterion benchmarks, including gpui::bench, BenchAppContext, renderer and task benchmarks, headless Metal frame data, responsiveness and hang regressions, feature isolation from test-support, and before/after performance evidence.