ws-protocol
ws-protocol is a technical specification outlining the protocol version, message envelope, and idempotency keys for action submission, ensuring reliable and secure communication between AI agents and WebSocket servers.
Browse and install thousands of AI Agent skills in the Killer-Skills directory. Supports Claude Code, Windsurf, Cursor, and more.
ws-protocol is a technical specification outlining the protocol version, message envelope, and idempotency keys for action submission, ensuring reliable and secure communication between AI agents and WebSocket servers.
migrate-to-channels is a skill that migrates OmniClaw setups from a flat groups/ workspace model to a layered context architecture, organizing agents, servers, and channels
adapt is a macOS-based AI agent skill that analyzes project structures, detects conventions, and customizes configurations for pair and mob programming sessions.
Retro is a skill that verifies the effectiveness of improvement cycles and analyzes project health trends, providing guidance on operational improvement directions from a Site Reliability Engineering (SRE) perspective.
Minimalist yet powerful AI-assisted development framework. Production-ready CLAUDE.md & AGENTS.md system with 35+ guardrails, 4D methodology, and auto-loading language guides for TypeScript, Python, Go, and Rust.
Autonomous project generator for Claude Code. Write requirements, run one command, get a complete project with custom skills, agents, hooks, TDD, 80%+ coverage, and security-reviewed code.
convex-component-authoring is a technique for creating self-contained, reusable Convex components with proper isolation, exports, and dependency management.
moai-foundation-specs is a skill that provides expert-level SPEC lifecycle management, including version control, approval workflows, and integration with MoAI-ADK development pipelines.
supabase-audit-tables-list is a critical AI agent skill that ensures progressive file updates and logging for secure audit table listing in Supabase environments.
token-cost-ledger is a skill for tracking AI token consumption and costs, generating ledger entries in JSONL and summary reports in Markdown.
Evaluation is a process for assessing agent systems, requiring approaches that account for dynamic decision-making and non-deterministic behavior.
gh-fix-ci is a skill that automates GitHub CI fixes by inspecting PRs for issues and proposing a fix plan using the gh command.