cli-ux-tester
Expert UX evaluator for CLIs, terminal tools, and developer APIs. Use when reviewing command usability, error messages, help systems, or developer experience.
What this skill does
# CLI UX Tester
This skill evaluates the usability of command-line interfaces and developer tools. It identifies the target CLI,
asks clarifying questions if needed, runs three evaluation agents in parallel, then passes the collected results
to a synthesizer agent to produce artifacts.
**Architecture:** The skill spawns all evaluation sub-agents directly (one Explore agent and two test agents in
parallel). This works around the platform constraint that sub-agents cannot spawn further sub-agents. The
`cli-ux-tester:cli-ux-tester` agent acts as a pure synthesizer — it receives the pre-collected test data and
produces the scored report and artifacts.
## Step 1: Detect target CLI
Try to identify the CLI to evaluate from the user's message and current directory context.
**From the user's message:**
- If the user names a specific command or tool (e.g., "review my-tool"), use that as the target.
**From the current directory:**
```bash
# Check for executable entry points
ls -la *.sh bin/ scripts/ 2>/dev/null | head -20
# Check for package.json with a bin field (Node.js CLI)
cat package.json 2>/dev/null | grep -A5 '"bin"'
# Check for Python CLI setup
cat setup.py pyproject.toml 2>/dev/null | grep -A5 'console_scripts\|entry_points' | head -20
# Check for Go main package
ls main.go cmd/ 2>/dev/null
# Check README for CLI name and usage
head -50 README.md 2>/dev/null
```
## Step 2: Ask clarifying questions if needed
Skip this step if the target CLI was already identified from the user's message in Step 1.
Otherwise, ask exactly one AskUserQuestion using the appropriate form below:
**Entry point(s) detected in current directory** → ask which to evaluate:
```text
Question: "Which CLI should I evaluate?"
Options:
- [Each detected entry point]
- A different installed command (provide the name)
- A different path (provide the path)
```
**No entry points detected** → ask the user to specify:
```text
Question: "Which CLI tool should I evaluate?"
Options:
- An installed command available in $PATH (provide the name)
- A path to an executable (provide the path)
```
Proceed directly to Step 3 with whatever the user provides.
## Step 3: Run evaluation agents in parallel
Locate the reference files first:
- Use Glob (`**/testing-checklist.md`) to find `testing-checklist.md`; note the path
- Use Glob (`**/test-scenarios.md`) to find `test-scenarios.md`; note the path
Then spawn these three agents simultaneously, substituting the actual `{cli_command}` and `{working_dir}`:
**Explore agent** — codebase mapping:
```text
subagent_type: Explore
prompt: "Map the {cli_command} CLI codebase in {working_dir}. Find: all commands and subcommands,
help text locations, error handling code, version output, README and docs files, entry point(s),
flag/argument parsing. Return a structured summary: command tree, key file locations, patterns
observed."
```
**Test agent A** — discovery and help:
```text
subagent_type: general-purpose
prompt: "Test {cli_command}'s help system and discoverability (run from {working_dir}).
Run: {cli_command} --help, {cli_command} -h, {cli_command} help, {cli_command} (no args),
{cli_command} --version, {cli_command} -v, {cli_command} version, {cli_command} invalid-subcommand,
{cli_command} --invalid-flag. For each subcommand found, also run: {cli_command} subcommand --help.
Capture exact output. Note: what works, what fails, what's missing."
```
**Test agent B** — error handling and consistency:
```text
subagent_type: general-purpose
prompt: "Test {cli_command}'s error handling and consistency (run from {working_dir}).
Run: commands with missing required args, invalid flag values, nonexistent files, wrong syntax.
Check whether flag names are consistent across subcommands (--verbose always means the same thing).
Check exit codes with echo $?. Capture exact outputs. Note every inconsistency."
```
Wait for all three agents to complete and collect their full outputs before proceeding.
## Step 4: Launch synthesizer agent
Once all evaluation results are collected, launch the `cli-ux-tester:cli-ux-tester` agent.
Pass:
- The working directory
- The CLI entry point (command name, script path, or executable)
- Any relevant context from the user's message (e.g., "focus on error messages")
- The full output from all three evaluation agents (Explore, Test A, Test B)
- Path to `testing-checklist.md`
- Path to `test-scenarios.md`
## Step 5: Report results
When the agent completes, inform the user:
```text
✅ Evaluation complete!
📁 Results saved to: {timestamped_directory}
📊 Overall score: {overall_score}/5
🔍 Top issues: {brief_summary}
Clean up with: rm -rf CLI_UX_EVALUATION_*/
```
## Error handling
- **CLI not found**: Ask the user to confirm the command name or path
- **Permission denied**: Note the issue and ask if they want to test a different entry point
- **No CLI in current directory**: Ask the user to specify which tool to evaluate
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.