ck:research
ck:research is a research methodology that follows a phased approach, including scope definition and systematic information gathering, to provide concise and honest research results.
Browse and install thousands of AI Agent skills in the Killer-Skills directory. Supports Claude Code, Windsurf, Cursor, and more.
This directory brings installable AI Agent skills into one place so you can filter by search, category, topic, and official source, then install them directly into Claude Code, Cursor, Windsurf, and other supported environments.
ck:research is a research methodology that follows a phased approach, including scope definition and systematic information gathering, to provide concise and honest research results.
implementation-runner is a skill that automates code implementation by checking requirements, defining change scope, and recording changes in repository files.
Auto Refresh is a skill that automatically refreshes market research data when a user logs in, utilizing sessionStorage to prevent re-triggering.
sd-review is a code analysis skill that combines defect review and refactoring analysis for comprehensive code evaluation
generate-import-modal is a skill that automatically generates Excel import modals based on project standards, including modal components, parser functions, and TypeScript interfaces.
Tapestry is a social graph integration tool for building social trading apps with React Native, Expo, and Polymarket
stitch-loop is an AI agent skill that implements an autonomous iterative build pattern for website creation. It uses a baton file (`.stitch/next-prompt.md`) to pass tasks between iterations, generating pages with Stitch MCP tools and integrating them into the site structure.
react:components is a skill that leverages system-level networking and AST-based validation to generate modular Vite and React components from Stitch designs.
pdca is a unified skill for managing the PDCA cycle, integrating project agents from bkit.config.json for automated workflow
Continuous-learning is a skill that automatically evaluates Claude Code sessions to extract reusable patterns and saves them as learned skills for future use.
agent-harness-construction is a developer skill for designing and optimizing AI agent action spaces, tool definitions, and observation formatting. It focuses on core constraints like action space quality and recovery quality to achieve higher completion rates for agents like Claude.
nanoclaw-repl is a zero-dependency, session-aware REPL built on Claude for operating and extending the NanoClaw v2 AI agent. It features persistent markdown-backed sessions, dynamic skill loading, session branching, history compaction, and export capabilities to MD, JSON, and TXT formats.