logicleap-labs/claude-plugins
11 skills
$npx skills add logicleap-labs/claude-pluginsSkillInstalls
accessibility-gateUse before declaring a UI change done, fixed, working, ready, or shipped.migration-safetyMANDATORY before any destructive database or schema work — DROP TABLE/COLUMN, TRUNCATE, DELETE or UPDATE across rows, irreversible ALTERs, data backfills,…no-debugMANDATORY before declaring code "done", "ready", or ending a turn after writing or debugging a function/handler/module.no-silent-assumptionsMANDATORY before declaring code "done", "ready", or ending a turn after working with anything you couldn't fully verify — an environment you didn't inspect, a…no-slopMANDATORY before declaring prose "done" or ending a turn after writing a README, doc, blog post, comment, or any .md/.mdx/.txt/.rst.no-stubMANDATORY before declaring code "done", "ready", or ending a turn after writing a function/handler/module.no-swallowMANDATORY before declaring code "done", "ready", or ending a turn after writing or editing anything with a try/catch, except, or error path.scope-guardUse at the START of any focused task — a bug fix, one feature, a single file's refactor — and ALWAYS when more than one agent shares a working tree.secret-guardUse whenever you are about to put a credential, API key, token, or password into code — or whenever a secret already appears in a file you're editing.verify-before-doneMANDATORY before declaring ANY code change "done", "fixed", "working", "ready", "shipped", or before ending a turn after editing source.visual-self-reviewMANDATORY acceptance gate before declaring ANY visual or UI work "done", "good", "working", or before screenshotting an interface and ending the task.