Total 58,118 skills
Showing 12 of 58118 skills
Structures and organizes Storybook files for scalability using battle-tested patterns from Cassondra Roberts' "A Storybook format that scales with you". Covers story definitions, template composition, controls/args, visual regression with Chromatic, component documentation, and CSF conventions. Activates on any Storybook question — file structure, controls, args, or component documentation.
Use when writing a complete SEO article. Includes the full anti-AI-slop ruleset (banned vocabulary, banned phrases, banned structural patterns) and voice rules. The agent researches the SERP itself if needed — no keyword data exports required.
Build, review, debug, migrate, or plan TanStack Form v1 React forms with current docs. Use for @tanstack/react-form, @tanstack/form-core, useForm, form.Field, createFormHook, createFormHookContexts, withForm, withFieldGroup, formOptions, form.Subscribe, useSelector, useStore, validators, Standard Schema validation, Zod, Valibot, ArkType, Effect Schema, async validation, dynamic validation, array fields, FormGroup, linked fields, listeners, SSR, TanStack Start, Next.js, Remix, devtools, UI libraries, accessibility, and production form composition.
Production-grade skills for product thinking, discovery, prioritization, and launch decisions. Covers the full PM lifecycle with a different author and focus than other PM skill packages in the catalogue.
Generates or updates Sorbet inline type signatures directly in Ruby source files using sig blocks. Triggers when creating, updating, or maintaining inline type signatures for Ruby source files.
Use when debugging services on a user's dedicated server via SSH. Use when needing to run a command on the server, inspect pods, check container logs, view k8s resources, or run kubectl commands. Use when "service exec" is insufficient and you need server-level access. Use when user says "check my server", "run X on my server", "debug pod", "kubectl", "SSH into server", "check k8s", or "inspect cluster".
Build standalone interactive HTML artifacts as the medium for agent↔designer conversation — review docs with approve/deny/discuss, N-way prototype variants, before/after motion comparisons, visual explorers for APIs/content, and inline-editable copy ecosystems. Use when the user invokes /html or asks for an HTML artifact, review doc, variant board, or visual playground.
Generate a git commit message compliant with Conventional Commits 1.0.0 (and the de facto @commitlint/config-conventional rules) from currently staged changes. Outputs Korean by default, or another language if the user explicitly requests it. Trigger when the user asks for a commit message — e.g. "/conventional-commits", "write a commit message", or any equivalent. Scope is limited to producing the message text; executing `git commit` is outside this skill's responsibility.
In chat-only mode, reply like a chat assistant without changing the current code base.
Simplify an already-bounded code or documentation area without changing intended behavior. Use for deletion, direct-flow refactors, wrapper or branch reduction, clearer data models, reduced mutable state, or concrete simplification findings; use improve-architecture when the opportunity or design is still unclear.
Use this skill when designing onboarding, when diagnosing why users keep getting confused, when migrating users from one product convention to another, or when the system genuinely differs from familiar comparable products. Trigger when the user mentions "users don't get it," "we keep getting the same support tickets," or "this is a new pattern they need to learn." Sub-aspect of `mental-model`; read that first.
Use this skill when constructing visual hierarchy through color and tone (value, contrast, saturation) — picking which elements get full-color emphasis and which recede into greys, building a tone ladder, and deciding when color should *be* the hierarchy versus when it should *support* a size/weight hierarchy. Trigger when picking the primary color, building a neutral palette, designing a status badge system, or fixing a UI where color is "too loud" or "too flat." Sub-aspect of the broader `hierarchy` principle; read that first if you haven't already.