Agent Skills Hub

writing-agents

A framework for creating, testing, and managing autonomous AI subagents within project environments using Test-Driven Development principles.

skills

A project-specific architectural template for Next.js 15, FastAPI, and Supabase applications, including structured AI integration patterns.

eval-harness

Official evaluation framework for AI agent sessions, implementing Evaluation-Driven Development (EDD) principles to ensure reliability.

using-git-worktrees

Creates isolated git worktrees for parallel development, automatically handling directory selection, .gitignore safety checks, dependency installation, and baseline test verification.

plugin-checker

Audit and validate Claude Code plugins for structural integrity, manifest compliance, and best practice adherence to ensure reliable agent and skill performance.

canvas

Interactive terminal UI toolkit for Claude Code. Spawn and control calendar, document, and flight booking interfaces directly within tmux panes.

problem-mapping

Structured problem-framing tool for design sprints and product strategy. Facilitates collaborative or individual sessions to define goals, stakeholders, constraints, and pain points before solution generation.

debug-hooks

Systematic debugging workflow for Claude Code hooks. Use to troubleshoot non-firing hooks, output errors, or unexpected behavioral issues.

doc-sync

Synchronizes and maintains CLAUDE.md and README.md documentation hierarchy across a repository to ensure consistent, just-in-time context for AI agents.

swarm-advanced

Orchestrate complex multi-agent swarms with topologies like mesh, hierarchical, and star for research, development, and testing workflows.

obsidian-vault-ops

Manage Obsidian vault operations: file creation, YAML frontmatter, wiki-links, and templated note processing for PKM systems.

cc-stack-analysis

Expert tool for auditing and validating the structural integrity, naming conventions, and best practices of Claude Code configurations, including skills, hooks, and commands.