← ClaudeAtlas

review-feature-suitelisted

Reviews a whole suite of `.feature` files against each other and reconciles them — cross-file consistency auditing for Gherkin/BDD. Checks that the suite holds one shared language across files, reuses step phrasing instead of duplicating it, carries no contradictory or redundant scenarios, and stays consistent in tags, naming, and data. Use whenever the user has multiple existing `.feature` files (a Cucumber, SpecFlow, Behave, or plain Gherkin suite) and wants to check, audit, align, reconcile, or de-duplicate them as a set — including phrasings like "our features use different words for the same thing", "do these scenarios contradict each other", "find duplicate steps across our features", or "make our feature files consistent". Do not use for authoring or refining a single feature in isolation — that is a single-feature concern, handled by a skill like define-behavior where one is available.
azborgonovo/ai-skills · ★ 0 · Code & Development · score 75
Install: claude install-skill azborgonovo/ai-skills
# Review Feature Suite A single `.feature` file can be flawless on its own and still be wrong in the company of its neighbors. The value of a BDD suite is that the whole team shares one language all the way down into the code, that step definitions are written once and reused, and that the features stand as living documentation that doesn't contradict itself. Those properties only exist *across* files, so they can only be checked across files. That is this skill's entire job: read every `.feature` file as one corpus and reconcile it. Work in two phases: **critique first, edit second.** Build the picture, surface the findings, settle the judgment calls with the user, and only then change files. ## Build the inventory first The findings live in the relationships between files, so don't read file-by-file and judge as you go — assemble a compact cross-file picture first, then reason over it. Use `Glob` to enumerate the `.feature` files from the path or glob the user gave (default to searching the project), then use `Grep` to pull the raw material across all of them at once rather than holding every full file in context: - **Steps** — every `Given`/`When`/`Then`/`And`/`But` line, so you can see which phrasings recur and which are near-duplicates. - **Tags** — every `@tag`, to spot the taxonomy and its typos. - **Titles** — every `Feature:` and `Scenario:`/`Scenario Outline:` line. - **Actors and data** — the roles, currency/number/date values, and named entities that recur, s