Agent Claude Code
Use when testing in browser, verifying UI works, checking end-user functionality, visual verification, cross-browser checks, or need automated browser testing.
2 2mo ago A 31 tokens
Agent Claude Code
Use when reviewing UX, user experience, interfaces, user-facing features, or need empathy/design perspective on code changes.
2 2mo ago A 27 tokens
Command Claude Code
Add support for a new service (like Slack, Notion, or GitHub) with full OAuth and API integration.
2 2mo ago A 23 tokens
Command Claude Code
Set up or update AI coding configurations - interactive setup for Claude Code, Cursor, and other AI coding tools.
2 2mo ago B 21 tokens
best-of
05Command Claude Code
Research how the best products handle a feature, analyze their approaches, then design our ideal version.
2 2mo ago A 18 tokens
Command Claude Code
Test the app like different users would (busy founder, UX critic, bug hunter) with automated browser testing.
2 2mo ago A 21 tokens
build-agent
07Command Claude Code
Create a specialized AI agent to handle specific tasks autonomously (like code review, research, or testing).
2 2mo ago A 21 tokens
build-next
08Command Claude Code
Figure out what to build next, then build it together - collaborative product planning and execution.
2 2mo ago A 17 tokens
design-lab
09Command Claude Code
Explore design options side-by-side - generate UI variations, compare them visually, iterate based on feedback.
2 2mo ago A 19 tokens
dev-server
10Command Claude Code
Start a fresh Next.js dev server with intelligent state management - handles port detection, cleanup, and optional browser opening.
2 2mo ago C 22 tokens
Command Claude Code
Audit documentation for consistency across docs/, knowledge/ specs, and feature-catalog.ts - find gaps, misleading claims, and sync issues.
2 2mo ago A 26 tokens
Command Claude Code
See how other products implement a feature by analyzing their code - research competitor implementation patterns.
2 2mo ago A 16 tokens
site-keeper
13Command Claude Code
Check production for errors and issues, create PRs to fix what's broken - autonomous production monitoring.
2 2mo ago A 18 tokens
Command Claude Code
Test a service integration through the chat interface - verifies operations work correctly and identifies adapter bugs.
2 2mo ago A 17 tokens
Command Claude Code
Research the current image generation landscape and update Carmenta's image model routing rubrics with latest models, capabilities, and pricing.
2 2mo ago A 25 tokens
Command Claude Code
Research the current LLM landscape and update Carmenta's model routing rubrics with latest models, capabilities, and pricing.
2 2mo ago A 24 tokens
PreCompact
17Hook Claude Code
Runs before the context is compacted, executing save-worktree-state.py via python3. From carmentacollective/carmenta.
2 2mo ago A
tokens not measured
SessionStart
18Hook Claude Code
Runs when a session starts on compact, executing restore-worktree-context.py via python3. From carmentacollective/carmenta.
2 2mo ago A
tokens not measured
carmenta
19Settings file Claude Code
Agent settings declaring 2 hook events (PreCompact, SessionStart).
2 2mo ago A
tokens not measured
Skill Claude CodeCodex
Use when writing user-facing copy, error messages, UI text, empty states, onboarding, or reviewing voice/tone.
2 2mo ago A 28 tokens
Skill Claude CodeCodex
Use when adding logging, error monitoring, metrics, Sentry, debugging production issues, or improving observability.
2 2mo ago A 26 tokens
Skill Claude CodeCodex
Use when writing tests, verifying functionality, QA, test scenarios, user testing, or browser automation tests.
2 2mo ago A 24 tokens
Skill Claude CodeCodex
Use when writing, reviewing, or refactoring React or Next.js code, optimizing React performance, fixing re-render issues, reducing bundle size, eliminating waterfalls, or improving data fetching patterns.
2 2mo ago A 44 tokens
Cursor rule Cursor
When creating or editing .agent files.
2 2mo ago A 7 tokens