majestic-tools

Generate multiple response variants with probability scores for any request

Extract cross-session patterns from git history and handoffs, recommend artifacts (skill/rule/hook/agent) based on frequency.

Display all available commands in a formatted HUD grouped by plugin or category

List all available tools with detailed information

Generate a new Claude Code sub-agent configuration file from a description

Generate any Claude Code command with production-quality patterns

Create and configure Claude Code hooks for automating workflows and behavior control

Build or optimize prompts following Anthropic's best practices

Generate Claude Code skills following best practices. Creates skill files with proper structure, naming, and content.

Test and iterate on a skill using parallel eval runs. Spawns with-skill and baseline runs, grades results, and helps improve the skill based on feedback. Use when testing skill quality or iterating on skill improvements.

Optimize a skill's description for better trigger accuracy. Generates eval queries, runs automated optimization loop with train/test split, and applies the best description. Use after creating or improving a skill.

Reflect on current session and suggest AGENTS.md improvements based on patterns and feedback.

Deep discovery interview for any domain - engineering, brand, product, marketing, sales

Guide for coordinating multiple Claude Code instances as a team using Agent Teams. Covers TeammateTool operations, spawn backends, communication, task coordination, hooks, and orchestration patterns. Use when building multi-agent workflows requiring inter-agent communication.

Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes

Extract patterns from git history and session files, recommend artifacts (skill/rule/hook/agent) based on frequency thresholds

Forces adversarial reasoning before committing to decisions. Triggers on architectural choices, approach selection, and planning phases to prevent premature commitment bias.

Use when reviewing brainstorms, plans, or PRDs for clarity and readiness before next workflow phase. Assesses documents for vagueness, gaps, and YAGNI violations.

Patterns for designing multi-agent systems with Claude Code - job description method, shared folder communication, handbook consolidation, context management. Use when building complex agent orchestrations.

Verify LLM reasoning using Reverse Chain-of-Thought (RCoT) to detect overlooked conditions.

Four common skill archetypes with structure templates - CLI reference, methodology, safety/security, and orchestration. Use when creating new skills to select appropriate structure.

Core philosophy for designing Claude Code skills - when to use skills vs agents, the knowledge test, and what makes skills valuable. Use when deciding component type or evaluating skill quality.

Check for relevant skills before starting any task. Triggers on task start, new requests, beginning work, or implementation.

Evaluate skill test run outputs against expectations and extract implicit claims.

Skill file structure, naming conventions, directory layout, frontmatter requirements, and invocation control. Use when creating skill files or slash commands to ensure correct format and validation.

1 hook across 1 event