Agent skills

Deep cultural adaptation of translated blog posts.

Turn a one-line objective into a step-by-step construction plan any coding agent can execute cold.

Simulate a 5-member expert board deliberation for major decisions.

Populate or refresh a persistent, high-level project snapshot in memoir.

Provides brand naming frameworks, evaluation criteria, and templates for startup naming work.

Break down epics and features into concrete backlog tasks with dependencies.

Browser automation with cmux embedded webviews (not Chrome/Chromium).

Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app.

Fill a web form by mapping field-name → value, with optional template lookup from browser-templates for known forms

Cloud browser infrastructure for AI agents - create sessions, persist contexts, and automate browsers

Fix build and TypeScript errors with minimal changes

Search and ask questions about your coding agent session history.

This skill should be used when the user asks about Central Station threads, community discussions, support questions, feature requests, or…

This skill should be used when users need to generate detailed, structured prompts for creating UI/UX prototypes.

Auto-generate a structured changelog from git history and code graph entity mapping.

Template system for building quarterly social channel roadmaps with KPIs

Read-only drift detector. Diffs SPEC.md against current code and reports violations grouped by severity. Writes nothing — suggests…

Google Chrome with DevTools on port 9222, Chrome DevTools MCP on port 9224, and browser-open helper.

Generates a Mermaid class diagram showing types, inheritance, and composition.

Transforms raw transcripts, OCR text, and fragmented study materials into structured, review-ready WPS learning notes.

Interactive getting-started walkthrough for new Claude Code users.