Agent Skills Hub

code-quality-review

Holistic, multi-dimensional code review skill providing prioritized, actionable feedback on correctness, security, performance, design, and accessibility.

crane

Expert assistant for writing high-quality, modern, and memory-safe C++ code for V8 FFI wrappers and native integrations.

reset

Resets workflow artifacts in the .otto/ directory. Safely removes tasks, specs, and browser sessions for a clean start.

claude-code

Standardized skill for Claude Code agents to dynamically query OpenRouter model recommendations and metadata via the Claudish CLI.

agentic-workflows

Build production-grade AI agents using LangGraph, Anthropic/OpenAI/vLLM, and structured outputs. Features streaming, A2A protocol, Pydantic validation, vector memory, and guardrails for resilient, multi-agent workflows.

search

Search the web using Tavily's LLM-optimized search API for relevant, source-cited content without writing code.

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.

explaining-code

Explains code using visual diagrams, relatable analogies, step-by-step walkthroughs, and common pitfalls.

form-cro

Optimize non-signup forms to increase conversion rates. Includes lead capture, contact, demo, application, and survey forms.

codebase-inspection

Analyze codebase statistics: LOC, language distribution, and code-to-comment ratios using pygount.

pr-review-fix-loop

Orchestrate an automated PR review-fix loop. Dispatches subagents to analyze code, CI status, and comments, then applies iterative fixes until the PR reaches a passing state.

generate-sdk-types

Automates TypeScript type generation from Rust tool schemas to ensure end-to-end type safety between server and client in MCP-based projects.