Agent
An agent that combines findings from engineering test research and a user-focused review into one test strategy. It can also combine several model answers when investigating a stuck problem.
Agent
An engineering agent that researches how similar open-source projects test a feature and proposes a focused list of verification commands. It considers normal cases, edge cases, errors, and end-to-end behavior.
Agent
A product-focused critic that examines a feature from the user's point of view. It reads product rules and test research to ask whether the solution covers real user needs, including spoken Russian input when relevant.
Agent
An agent that builds a validation set: realistic test scenarios, expected results, and yes-or-no scoring for a product or feature.
Hook
Runs before the agent uses a tool for Write, Edit, MultiEdit and Bash tool calls, executing dispatch-pre-tool-use.sh via bash. From andrewcigan/vibe-dev-plugin.
Hook
Runs after a tool call finishes for Bash, Edit, Write and MultiEdit tool calls, executing dispatch-post-tool-use.sh via bash. From andrewcigan/vibe-dev-plugin.
Hook
Runs when the agent finishes a response, executing dispatch-stop.sh via bash. From andrewcigan/vibe-dev-plugin.
Hook
Runs when you submit a prompt, before the agent sees it, executing dispatch-user-prompt.sh via bash. From andrewcigan/vibe-dev-plugin.
Hook
Runs when a session starts, executing dispatch-session-start.sh via bash. From andrewcigan/vibe-dev-plugin.
Hook
Runs when a message is displayed, executing dispatch-message-display.sh via bash. From andrewcigan/vibe-dev-plugin.
Hook
Runs before the context is compacted, executing pre-compact.sh via bash. From andrewcigan/vibe-dev-plugin.
Skill Claude CodeCodex
A first-pass system architecture workflow that limits the design to a small set of components, maps their relationships, states key rules, and identifies major risks.
Skill Claude CodeCodex
An independent project-health review that scores seven areas, including instructions, current state, verification, scope, lifecycle, learning, and cost safety, from 1 to 5.
Skill Claude CodeCodex
A progress-saving workflow that records the current project state in files, synchronizes task statuses, archives finished information, and runs a fresh-start check.
Skill Claude CodeCodex
A guided process for choosing one software technology stack based on an application's main architectural bottleneck.
Skill Claude CodeCodex
A workflow for narrowing a long list of product ideas by checking them against rules, risks, target markets, budgets, and a fixed scoring scheme.
Skill Claude CodeCodex
A handoff workflow that turns product and architecture documents into a brief for Claude Design, an AI design tool, including screens, user flows, and required interface parts.
Skill Claude CodeCodex
A command that expands a chosen technology plan into a detailed software architecture. It documents API rules, data models, error handling, and the order in which parts can be built.
Skill Claude CodeCodex
A planning tool that breaks a software project into features arranged in dependency-based waves, or groups of work that can be done in sequence or parallel.
Skill Claude CodeCodex
A project self-check that tests whether the project’s monitoring hooks and plugin components are actually working. Hooks are automatic scripts that run when specific events occur.
Skill Claude CodeCodex
A session-closing command that records project state, synchronizes notes, commits changes, and prepares a restart command.
Skill Claude CodeCodex
A two-round process for expanding an early product idea into a list of possible directions, each with reasons and alternative interpretations.
Skill Claude CodeCodex
A Russian-language workflow for taking one software feature through development while allowing only one active feature at a time. It also uses tests, project rules, and reviews from both a tester and a user-focused critic.
Skill Claude CodeCodex
A session-closing checklist for recording work and confirming that a project is ready to continue later.