Search skill packs and skills together

Large website builds often lose context between pages and iterations. This skill gives Claude, Codex, and Claude Code a baton workflow for generating, integrating, and continuing Stitch-based site work.

Managing several coding agents across terminal panes can make state, focus, and output difficult to track. This skill uses Herdr commands to organize panes, coordinate agents, run commands, and inspect results.

Agent applications need clear feedback for tool calls, approvals, and results. This skill provides React patterns for presenting each lifecycle state consistently.

Teams need agent chat interfaces without rebuilding streaming, approvals, and tool displays. This skill guides setup of the inference.sh Agent component in React and Next.js.

Web3 developers need clear API guidance for ChainGPT products before they write integration code. This skill summarizes endpoints, SDKs, costs, and implementation patterns for ChainGPT-powered applications.

Long coding sessions lose context when subagents return verbose results. Cavecrew guides Claude, Codex, and Claude Code toward compact investigator, builder, and reviewer agents.

Complex web research can become scattered and hard to verify. This skill plans subtopics, delegates searches, and synthesizes cited findings into a clear answer.

Live meeting automation requires careful identity handling and separate identifiers. This skill guides authorized Lark discovery, participation, event reading, and communication through lark-cli.

AI-generated interfaces often look generic or miss production details. This skill gives Claude, Codex, and Claude Code strict design and frontend guardrails.

A first interface idea can hide weak assumptions and unnecessary complexity. This skill generates distinct options, compares trade-offs, and helps select or synthesize a stronger design.

Unfamiliar code is hard to change when modules, callers, and domain terms are unclear. This skill prompts Claude, Codex, or Claude Code to explain the broader map before implementation.

Implementation work often ships without tests that prove behavior. This skill guides Claude, Codex, and Claude Code through strict test-first development.