Agent Skills Hub

secure-claude-code

Monitor Runwall security posture, enabled guardrails, and recent audit logs for Claude Code, Codex, and MCP-based development environments.

vibe-build

The final execution agent for the vibe-coding workflow. Builds your MVP incrementally by following the AGENTS.md master plan, managing session continuity, and verifying each feature via testing.

mind

Persistent, Git-friendly memory for Claude. Automatically store and retrieve project decisions, bug fixes, and coding patterns in a local .mv2 file.

stream-chain

Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows within the Ruflo/Claude Flow ecosystem.

refactoring

Linter-driven refactoring agent that resolves complexity issues like cyclomatic depth, primitive obsession, and long functions using automated pattern extraction.

swift-concurrency-expert

Expert Swift Concurrency review, diagnostics, and remediation for Swift 6.2+ codebases, focusing on actor isolation, Sendable safety, and modern concurrency patterns.

strategy-scaling-architecture

Architectural planning and scaling for spectre-build, covering GUI, server layers, multi-model support, and industrial pipeline orchestration.

clean-code

Pragmatic AI-assisted coding standards focused on clean code, simplicity, and maintainability. Enforces best practices like SRP, DRY, and KISS to prevent over-engineering.

workflow-execute-plans

Execute implementation plans in small, verifiable batches with pause-for-feedback checkpoints to prevent drift and ensure code quality.

javascript-typescript

Advanced TypeScript and React development assistant for modern web applications. Expert in component architecture, state management, Vitest unit testing, Playwright E2E automation, and efficient TypeScript configuration.

evaluating-code-models

Evaluate code generation models using BigCode Evaluation Harness. Benchmarks include HumanEval, MBPP, and MultiPL-E with pass@k metrics for multi-language coding models.

moai-foundation-core

Foundational architectural principles for MoAI-ADK, featuring TRUST 5, SPEC-First TDD, delegation patterns, and token-efficient agent orchestration workflows.