Lightning-fast
Write one line. Get a complete skill package — validated, linted, and ready to install into your coding agent.
3 free generations. No account needed.
No prompt engineering, no boilerplate, no reading a specification first.
Every skill is generated against a versioned reference corpus, and cites the exact documents it used.
Schema and lint gates run inside the request. A skill that fails them never reaches you unmarked.
No copy-paste archaeology. One command drops the skill into your project.
Generation is the easy part. Everything below is the hard part.
You read the skill as it is written. No spinner, no dead wait — the elapsed timer is on screen the whole time.
Every published skill shows the prompts it was tested against and whether it actually triggered. Nobody else shows you this.
Skills are versioned. When a reference source changes, every skill citing the old version is flagged for refresh.
The registry is served as llms.txt, a typed JSON index and per-skill Markdown — so agents can cite it directly.
Every skill here passed the quality gates. The reports are public.
Creates, validates and installs Agent Skills without leaving the terminal. Use when the user asks to build a skill, turn a repeated workflow into a skill, find an existing skill for a task, or wants to know why a skill is not being triggered.
0 installs · v0.1.0
Audits a web application for Core Web Vitals regressions. Use when the user asks to check LCP, INP or CLS, investigate a Lighthouse score drop, or review front-end performance before a release.
1,284 installs · v1.2.0
Finds and diagnoses flaky tests in a test suite. Use when tests pass locally but fail in CI, when a suite fails intermittently, or when the user asks to stabilise or de-flake their tests.
963 installs · v1.1.0