FigJam plugin development can fail when the CLI, WebSocket server, and plugin consoles disagree. This skill gives a focused checklist for diagnosing connection, sync, and patch problems.

FigJam plugin changes can fail when main-thread and UI APIs are mixed. This skill guides Claude, Codex, and Claude Code through the project structure, build flow, and import workflow.

Core DSL changes can break validation, normalization, diffing, and patch behavior. This skill gives Claude, Codex, and Claude Code a focused workflow for safe core package updates.

Prompt changes can silently reduce output quality. This skill builds golden datasets, runs Promptfoo evaluations, and summarizes failures and recent trends.

Large repositories are difficult to map quickly with local context alone. This skill guides Claude, Codex, or Claude Code to call Gemini CLI for architecture, pattern, and implementation analysis.

Technical documentation searches can consume context and slow focused work. This skill routes library and framework questions to a Context7 research agent and suggests efficient orchestration patterns.

Complex research often needs more than one quick search result. This skill guides Claude, Codex, and Claude Code through layered searches, source checks, and structured synthesis.

Software failures often have unclear causes and scattered evidence. This skill guides Claude, Codex, and Claude Code to produce structured diagnosis reports with practical repair steps.

Browser work can flood the main chat with page state, screenshots, and request logs. This skill delegates those tasks to a Chrome DevTools agent and returns concise results.

Building a reusable AI skill can create inconsistent instructions and weak validation. This template gives Claude, Codex, and Claude Code a structured workflow for skill creation.

Teams need consistent commits and checks before code lands. This skill guides commit message structure, formatting, and test steps for Claude, Codex, and Claude Code.

Teams lose consistency when Deno formatting and documentation rules are unclear. This skill guides agents to format with mise and document symbols in English.

Portfolio Buddy 2 development needs consistent project memory across React, TypeScript, and trading analytics work. This skill gives Claude, Codex, and Claude Code the project context needed for safer implementation decisions.

Portfolio Buddy feature work can drift into risky refactors or mobile gaps. This skill guides Claude, Codex, and Claude Code to plan conservative, responsive changes.

Teams often start coding before requirements, scope, and tradeoffs are clear. This skill guides Claude, Codex, and Claude Code through structured planning and prioritization.

Migration work becomes risky when feature status and known issues are scattered. This skill gives Claude, Codex, and Claude Code concise context for Portfolio Buddy parity work.

Frontend teams need consistent React and TypeScript patterns across repeated code work. This skill gives Claude, Codex, and Claude Code concrete standards for Portfolio Buddy 2 components, hooks, tests, imports, and reviews.

Portfolio Buddy changes require quick context about components, hooks, and data flow. This skill gives a concise project map for safer feature work.

Large features are hard to split across autonomous coding agents. This skill provides a worktree-based workflow for issue design, wave planning, monitoring, merging, and cleanup.

Teams often need clear process diagrams but Mermaid syntax can be hard to remember. This skill guides Claude, Codex, and Claude Code to draft valid flowcharts with Mermaid syntax details.