1,190 agent skills

Use it when:

You're building a game with an agent, in any engine, and want it to pull in the right game-dev know-how for each request.

It does:

The router detects your engine from project files, sorts the request into concepts, a genre and process steps, and reads only those skills, engine basics first.

router, create-game-assets, game-ai, ai-behavior-trees-utility-ai, procedural-gen, dialogue-systems, save-systems, audio-design, shader-programming, physics-tuning, level-design, input-systems, game-feel, game-ui-ux, camera-systems, performance-optimization, platformer, roguelike, rpg, fps-shooter, tower-defense, card-game, visual-novel, survival-crafting, puzzle, game-jam, prototype-fast

Use it when:

You want one install for building an interface and making its brand material: guidelines, tokens, logos, icons, banners, social images and decks.

It does:

ui-ux-pro-max picks styles, palettes and fonts for the UI; five skills by ClaudeKit keep a brand file in sync with design tokens and generate brand assets.

brand, design-system, ui-ux-pro-max, design, banner-design, slides

Use it when:

You want a screen or flow built or reviewed for accessibility, layout, copy, typography, color and visual polish, one domain at a time or all at once.

It does:

Six skills each own one domain; better-interface loads all six in a fixed order, accessibility first, and merges their findings into one table ranked by user impact.

interface-review, better-interface, better-accessibility, better-layout, better-writing, better-typography, better-colors, better-ui

Use it when:

You want polished motion in web UI: new transitions, or existing ones brought onto one consistent scale.

It does:

transitions-dev picks and installs whole transitions; transitions-polish retunes the durations, easings, distances, scales and blurs you already have.

transitions-dev, transitions-polish

Use it when:

You want a website checked and fixed for speed, accessibility, search and security, with measured evidence behind each finding.

It does:

Starts with web-quality-audit, one review across every area, then goes deep with one skill per area; each measures, fixes or recommends fixes, and measures again.

web-quality-audit, performance, core-web-vitals, accessibility, seo, best-practices

Use it when:

You want agent-built UI, copy and code comments free of the generic AI look, without being handed a house style.

It does:

The core antislop skill sets 40 rules and a final gate; five companion skills each add a pattern catalog for one concern and cite the core's rules.

antislop, antislop-ui, antislop-copywriting, antislop-human, antislop-layoutmobile, antislop-code

Use it when:

You want the agent to follow a full development process instead of jumping straight to code.

It does:

Chains its skills into one workflow: brainstorm, plan, build test-first on its own branch, review, then merge.

using-superpowers, brainstorming, using-git-worktrees, writing-plans, subagent-driven-development, executing-plans, test-driven-development, requesting-code-review, receiving-code-review, finishing-a-development-branch, systematic-debugging, verification-before-completion, dispatching-parallel-agents, writing-skills, diagnosing-superpowers

Use it when:

You want the agent to go deep before it ships: understand the code, settle the design, then prove the change works.

It does:

Runs multi-model workflows that explain, design, attack and check changes, plus writing rules and short engineering principles the workflows cite.

how, why, architect, arena, interrogate, blast-radius, technical-writing, unslop, principle-boundary-discipline, principle-type-system-discipline, principle-fix-root-causes, principle-prove-it-works, principle-guard-the-context-window, principle-encode-lessons-in-structure

Use it when:

You want to find and fix security vulnerabilities in your own app, API or code with autonomous AI pentesting.

It does:

Runs Strix agents that exploit a target and validate each finding with a PoC, then helps you patch and re-test.

penetration-testing-with-strix, application-security-testing, find-security-vulnerabilities-in-code, web-app-penetration-testing, api-security-testing, owasp-top-10-testing, fix-security-vulnerabilities-with-strix, ci-security-scanning-with-strix

Use it when:

You want the agent to use, test, record, debug or speed up your app, React Native above all, on a simulator, emulator, phone or TV.

It does:

Teaches the agent Argent's tools: drive the app by touch or TV remote, check UI flows, diff screenshots, record video, read logs, profile code and offer design variants.

argent-device-interact, argent-ios-device-interact, argent-tv-interact, argent-settings-permissions, argent-test-ui-flow, argent-screenshot-diff, argent-screen-recording, argent-metro-debugger, argent-react-native-optimization, argent-react-native-profiler, argent-native-profiler, argent-lens

Use it when:

Your coding agent over-engineers: abstractions, options, dependencies or code nobody asked for.

It does:

Keeps the agent to the smallest change that fully solves the task, then reviews a change or audits a whole repo for what will actually break.

ponytail, ponytail-review, ponytail-audit, ponytail-debt, ponytail-help