Designer Skills Pack
Agentic skills, commands, and plugins for design — from research to systems, UI, interaction, and delivery.
- Source repo
- Owl-Listener/designer-skills
- Stars
- ★ 3k
- Last updated
- 1mo ago
- License
- MIT
- Primary language
- Markdown
- FA score
- 38/100 · Major gaps
At a glance
- How it runs
- Works with
- Platform-specificClaude Code
- Cost
- Free, no paid service needed
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- A designer starting a new product uses /design-research:discover to run user research and validate assumptions.
- Not a fit if
- Teams using Cursor, Copilot, or other non-Claude Code assistants
- Non-developers unwilling to use a terminal or CLI install
- Teams needing pinned versions and stable release cadence
- Source review
- 38/100 · Major gaps 8 safety controls not found
What does this agent do, and when should you use it?
Designer Skills is a collection of skills, commands, and plugins for AI coding assistants, with 239 skills and 88 commands across 33 plugins in five collections: design practice, AI product design, UX program management, design leadership, and inclusive design. This repository is the home of the design practice collection, containing 97 skills and 30 commands across 9 plugins covering design research, design systems, UX strategy, UI design, interaction design, prototyping and testing, design operations, designer toolkit, and visual critique. Skills are domain knowledge units (nouns), and commands are workflows (verbs) that chain skills together. Plugins are installed via Claude Code's /plugin command, and also support Gemini CLI as extensions. The suite is written to make design judgment legible to AI agents.
The repository provides installable plugins for Claude Code, each containing skills and commands for a specific design domain. For example, /design-research:discover runs a full user research discovery cycle, /visual-critique:critique-screen performs seven visual critiques on a screen and outputs a prioritized fix list, and /design-systems:create-component scaffolds a component specification. Commands like /design-ops:handoff generate developer handoff packages. After installation, users trigger these workflows by typing slash commands, and the agent executes the workflow, producing design artifacts such as personas, design tokens, or test plans.
- A designer starting a new product uses /design-research:discover to run user research and validate assumptions.
- A product manager auditing an existing product uses /visual-critique:critique-screen to get a prioritized list of visual issues.
- A developer needing to implement a design system component uses /design-systems:create-component to generate a detailed specification.
- A design ops lead planning a sprint uses /design-ops:plan-sprint to structure the workflow.
- An AI product designer designing AI experiences combines this collection with the ai-design-skills collection.
- A freelancer quickly generating a color palette uses /ui-design:color-palette, which includes accessibility checks.
How do you install or deploy this agent?
- Download and install Claude Code (Anthropic's free app) from claude.com.
- In Claude Code, type:
/plugin marketplace add Owl-Listener/designer-skills - Type
/pluginto open the Discover tab, then select the collections or plugins you want.
For Gemini CLI, clone the repo and copy extensions:
git clone https://github.com/Owl-Listener/designer-skills /tmp/designer-skills
mkdir -p .gemini/extensions
cp -r /tmp/designer-skills/.gemini/extensions/. .gemini/extensions/How do you use this agent?
After installation, invoke commands directly, e.g., /design-research:discover. For new products, follow the sequence: /ux-strategy:frame-problem to define the problem, /ui-design:design-screen for UI design, /interaction-design:design-interaction for interactions, and /design-systems:create-component for systemizing components. For existing products, start with /visual-critique:critique-screen for a visual audit, then use /prototyping-testing:evaluate or /design-ops:handoff as needed. A recommended minimum install is: design-research, ux-strategy, ui-design, and design-ops.
What are this agent's strengths and limitations?
- Comprehensive coverage of the design process, from research to delivery, with 97 skills and 30 commands.
- Skills and commands are composable; commands chain skills for efficient workflows.
- Supports both Claude Code and Gemini CLI.
- Actionable commands like /visual-critique:critique-screen provide concrete output.
- Primarily designed for Claude Code; Gemini CLI support requires manual extension copying and may be partial.
- Locked into Anthropic's Claude Code ecosystem; other AI coding assistants may not be supported.
- Installation requires terminal use, which may be a barrier for non-developers.
- Versioning of skills is not explicit; updates may affect stability.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Designer Skills Pack This agent | 38 · Major gaps | Agent plugin / skillFree | ★ 3k | 1mo ago | Markdown | Claude Code |
| UIZZE · Better UI for Coding Agents | 47 · Major gaps | Agent plugin / skillFreemium | ★ 63 | 6d ago | JavaScript | Codex · Claude Code |
| Superdesign Skill | 43 · Major gaps | Agent plugin / skillFreemium | ★ 841 | 1mo ago | JavaScript | Codex · Claude Code |
| DESIGN.md Specification | 80 · Good | CLIFree | ★ 28k | 2d ago | TypeScript | — |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence shows no permission declarations, user confirmation mechanisms, data flow transparency, or sensitive data handling policies. All trust criteria are absent, scoring 0.
Self-consistency: README claims 241 skills and 91 commands, but design practice section lists 107 skills and 32 commands, and plugin table and command table are consistent, but total counts are inconsistent with README, minor contradiction. Dependency availability: Only mentions Claude Code and Gemini CLI, no version requirements or dependency list, insufficient evidence. Failure messages: No documentation of error handling or failure messages.
Audience and scenarios: README provides multiple usage scenarios and entry paths, covering different user needs. Capability boundaries: Clear capability scope via plugin and command lists. Trigger precision: Command naming is clear, but no trigger conditions or prerequisites. Environment fit: Explicitly supports Claude Code and Gemini CLI, but no other environments.
Information architecture: Clear table of contents and index, but no file structure. Install notes: Detailed installation steps, but no system requirements. Naming stability: Consistent command and plugin naming, but no version history. Examples and FAQ: Usage examples provided, but no FAQ. Known limitations: Not explicitly listed. License: MIT license clear. Versioning and changelog: Release workflow exists, but no changelog content. Maintenance responsibility: No explicit maintainer or update policy.
Output usability: Command descriptions clearly state outputs, but no output examples. Marginal value: Provides many skills and commands, but no comparison with other tools. Cost-benefit: Simple installation, but no performance or resource consumption information.
Claim traceability: Claims in README lack specific evidence or sources. Cross-source corroboration: No other sources to verify. Fact-inference separation: No clear distinction between facts and inferences.
- Not found in source: least-privilege scopingGrant only what the task needs: a dedicated account or read-only token, scoped to specific directories and repos.
- Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
- Not found in source: data-flow disclosureWatch which external services it contacts (proxy or firewall logs) and keep sensitive data out until you know where it goes.
- Not found in source: sensitive-data handlingUse dedicated, low-privilege, revocable API keys — never production credentials — and keep secrets out of logs.
- Not found in source: dependency securityPin versions and run a dependency audit (npm audit, pip-audit) before installing; prefer running it in a container.
- Not found in source: disclosed external effectsEstablish which external systems it writes to, sends to or changes, and verify with test accounts or repos before production.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- Not found in source: verifiable attributionInstall from the official repo or registry and check the publisher and URL to avoid look-alike packages.
- The repository provides no permission or security documentation; assess risks before use.
- The skill and command counts in README are inconsistent with the specific lists, which may affect user expectations.
- No dependency version requirements are provided, which may cause compatibility issues in different environments.