AI skill registry

Show users how Continuous Claude works - the opinionated setup with hooks, memory, and coordination

Code quality checks, formatting, and metrics via qlty CLI

Audit and fix HTML accessibility issues including ARIA labels, keyboard navigation, focus management, color contrast, and form errors. Use when adding interactive controls, forms, dialogs, or reviewing WCAG compliance.

Search past reasoning for relevant decisions and approaches

Maps questions to the optimal tldr command. Use this to pick the right layer

Audit and fix animation performance issues including layout thrashing, compositor properties, scroll-linked motion, and blur effects. Use when animations stutter, transitions jank, or reviewing CSS/JS animation performance.

Research agent for external documentation, best practices, and library APIs via MCP tools

Formal theorem proving with research, testing, and verification phases

Planning agent that creates implementation plans and handoffs from conversation context

Resume work from handoff document with context analysis and validation

Fast file editing via Morph Apply API (10,500 tokens/sec, 98% accuracy)

Orchestrator-only workflow for migrating/rewriting codebases with full TDD and agent delegation

Full 5-layer analysis of a specific function. Use when debugging or deeply understanding code.

Computational geometry with Shapely - create geometries, boolean operations, measurements, predicates

Deterministic router for math cognitive stack - maps user intent to exact CLI commands

Token-efficient code analysis via 5-layer stack (AST, Call Graph, CFG, DFG, PDG). 95% token savings.

Search library documentation and code examples via Nia

Query the memory system for relevant learnings from past sessions

TDD workflow for migrations - orchestrate agents, zero main context growth

Get a token-efficient overview of any project using the TLDR stack

Validation agent that validates plan tech choices against current best practices

Router-First Architecture

Create and configure Claude Code sub-agents with custom prompts, tools, and models

Analyze brownfield codebase and create initial continuity ledger

Wiring Verification

Meta-skill workflow orchestrator for bug investigation and resolution. Routes to debug, implement, test, and commit based on scope.

Idempotent Redundancy

Scrape web pages and extract content via Firecrawl MCP

Deep interview process to transform vague ideas into detailed specs. Works for technical and non-technical users.

Implementation agent that executes a single task and creates handoff on completion

Complete Claude Code hooks reference - input/output schemas, registration, testing patterns

Environment Triage

Search Mathlib for lemmas by type signature pattern

Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)

Search GitHub code, repositories, issues, and PRs via MCP

Claude Code CLI commands, flags, headless mode, and automation patterns

Find unused functions and dead code in the codebase

AST-based code search and refactoring via ast-grep MCP

Create handoff document for transferring work to another session

Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration

Create or update continuity ledger for state preservation across clears

Debug issues by investigating logs, database state, and git history

Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.

Workflow orchestrator that chains existing skills for feature development

Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity

Create git commits with user approval and no Claude attribution

Guide for integrating Agentica SDK with Claude Code CLI proxy

Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging