Explore skills

Run the full design-to-deploy pipeline using 3 AIs (Claude + Codex + Gemini). Use when starting a new feature, running /project, or needing end-to-end development with requirements, specs, implementation, testing, review, and deployment phases.

Generate UI screen design documents with component lists, state transitions, interactions, and responsive breakpoints. Use when designing screens, creating wireframes, or running /spec.

Generate E2E and unit test code from requirements using Playwright, delegated to Codex. Use when writing tests, checking acceptance criteria coverage, or running /test.

Test Prismstack by running a real domain through the full flow (plan → build → check). Records issues found for fixing. The ultimate integration test. Trigger: "dogfood", "test with real domain", "integration test", "try it for real" Do NOT use when: just want to run install tests (use `bash test/install-test.sh`)

Save and restore session state for continuity across Claude Code sessions. Captures tasks, changed files, context, and decisions. Use when ending a session, preserving progress, or running /checkpointing.

Generate distinctive, production-grade frontend UI code that avoids generic AI aesthetics. Follows opinionated design principles for unique visual identity. Use when building web UIs, components, or running /frontend-design.

Generate implementation code from design documents by delegating to OpenAI Codex. Use when you have specs ready and want to auto-generate source code, or when running /implement.

Generate a requirements document with user stories, acceptance criteria, and constraints. Use when defining features, writing specs, or running /requirements before implementation.

Conduct technical research using Gemini CLI, producing comparison reports with recommendations and code examples. Use when evaluating technologies, comparing libraries, or running /research.

Run code review against design documents, checking acceptance criteria, security, performance, and test coverage. Use when reviewing implementation quality or running /review.

Entry point for the Signal Prospecting Kit. Deep onboarding: researches the user's company from their domain, captures ICP, stack, and voice. Routes to /profile for market research. Triggers: /start, first run, "help me set up". Reads: ./gtm/ (all files). Writes: ./gtm/company.md, ./gtm/icp.md, ./gtm/voice.md. Standalone: yes.

Analyze entire codebases using Gemini CLI's 1M token context. Generates architecture reports covering structure, security, performance, and improvement roadmaps. Use when auditing code quality or running /analyze.