vercel-composition-patterns
Vercel-composition-patterns is a set of guidelines for building maintainable React components using compound components, state lifting, and internal composition.
Browse and install thousands of AI Agent skills in the Killer-Skills directory. Supports Claude Code, Windsurf, Cursor, and more.
Vercel-composition-patterns is a set of guidelines for building maintainable React components using compound components, state lifting, and internal composition.
vibe-check is a browser automation skill that utilizes the vibium CLI to automate Chrome, supporting daemon mode and element reference mapping.
workflow-team is an autonomous parallel development workflow for Agent Teams, facilitating task management and dependency analysis.
opence-plan is a development approach that emphasizes simplicity, scoped changes, and clear communication, following conventions outlined in opence/AGENTS.md
tr-dashboard-autopilot is an AI agent skill that automates the creation and verification of TR dashboards, using inputs like AGENTS.md and option_c.json to generate plans and reports.
multilingial is a skill that supports right-to-left languages like Arabic, maintaining existing multilingual content for AI agents.
generate-figma is an operations system for teams that automates design processes in Figma using specialized AI agents and the Figma Console MCP.
browser-check is a skill that facilitates Chrome MCP-based app testing, verifying not just display but also operation accuracy.
file-context-planning is a Codex-compatible skill that uses persistent markdown files as working memory on disk for planning and automation purposes.
A curated collection of agent skills for coding agents designed to enhance the workflows of Software Engineers (and, let's be honest, me primarily).
Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.
Research pipelines as semantic execution units: each skill declares inputs/outputs, acceptance criteria, and guardrails. Evidence-first methodology prevents hollow writing through structured intermediate artifacts.