Agent Skills Hub

paper-writing

Full-stack automated paper writing pipeline from research narrative to polished LaTeX/PDF.

looped-builder

Scaffold complex, multi-step coding tasks into actionable implementation plans and execute them autonomously using a Claude-driven bash loop.

skill-code-review

Multi-LLM code review pipeline using consensus-based analysis to detect security, architectural, and quality issues.

kanban-based-development

Autonomous, parallel-safe development workflow using kanban-md. Coordinates multi-agent and human efforts with atomic claims, worktrees, and explicit handoffs.

test-skill

A testing fixture for validating AI agent skill configurations and detecting rule violations.

omc-plan

Intelligent strategic planning and requirements gathering with multi-perspective consensus loops and structured deliberation.

ios-debugger-agent

Automate iOS development workflows using XcodeBuildMCP: build, run, test, inspect UI, and capture logs on local simulators.

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.

sparc-methodology

SPARC methodology for multi-agent development: systematic Specification, Pseudocode, Architecture, Refinement, and Completion workflows via Claude Flow orchestration.

refactoring

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

claude-starter

An AI-powered skill that automatically retrieves relevant project context from your RAG knowledge base for complex coding tasks.

find-skills

Discover and install agent skills to extend your DeerFlow capabilities. Use this to find tools, workflows, or specialized knowledge for tasks like coding, testing, and deployment.