Basano — Development skill for Claude Code

Basano

**An open critic for the Claude Skills catalog.** Built by [RampStack](https://rampstack.co).

Basano is an open critic for the Claude Skills catalog, built by RampStack. It reviews a finished build against a standard and reports what holds and what fails. It reads the [claude-skills](https://github.com/rampstackco/claude-skills) catalog, selects the verification skills a review needs, runs the review, and returns a structured verdict: the failures, prioritized by severity, and the parts that hold, so the verdict is trustworthy in both directions.

The name comes from the Greek basanos, the touchstone: the stone against which gold was rubbed to test whether it was genuine. That is what Basano does to a build.

This repository documents what Basano does and shows worked examples. The critic is operated by RampStack.

---

What it does

• Scopes the review. Turns a build and a standard into the areas worth checking: SEO, accessibility, code quality, performance, content, and others as the build calls for.
• Selects the verification skills. For each area, it picks the relevant audit and review skills from the catalog, honoring each skill's own stated boundaries, so the review maps to skills that actually check that dimension.
• Reports a verdict. It synthesizes findings into a structured, prioritized result: what fails, ordered by severity with the reason it matters, and what holds.

---

The honest verdict

A critic is only worth having if its judgment is trustworthy in both directions. Basano is built so that:

• A failure is never softened into a pass or a minor note. If an area fails the standard, the verdict says so, with severity.
• What cannot be assessed is marked as such, never quietly counted as a pass.
• A verdict reads "passes" only when every assessed area holds. A passing verdict that carried a real failure is structurally impossible: it cannot be constructed.

That is the point of the tool: its "this holds" is trustworthy beca