majesticlabs-dev/majestic-marketplace

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use when building web components, pages, or applications. Includes framework-specific guidance for Tailwind, React, Vue, and Rails/Hotwire ecosystems.

原文语言：英语

skill-structure

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.

原文语言：英语

devils-advocate

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

原文语言：英语

reasoning-verifier

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

原文语言：英语

build-task

Autonomous task implementation - research, plan, build, review, fix, ship

原文语言：英语

favicon

Generate a complete favicon set (ICO, PNG variants, apple-touch-icon, web manifest) from a source image and integrate into the project's HTML layout. Use when user asks to generate favicons, set up PWA icons, or add an apple-touch-icon.

原文语言：英语

session-checkpoint

Save session state to ledger file for continuity across crashes, context switches, or /clear + reload cycles.

原文语言：英语

compound-learnings

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

原文语言：英语

learn

Extract cross-session patterns from git history, PRs, and handoffs, then recommend artifacts (skill/rule/hook/agent) based on frequency thresholds. Use when consolidating recurring patterns into durable artifacts. For single-session reflection, use `reflect`…

原文语言：英语

reflect

Reflect on the current session and suggest AGENTS.md improvements based on user corrections, repeated feedback, and patterns observed during interaction. Use when ending a session to encode lessons learned. Don't use for cross-session learning from git…

原文语言：英语

data-integrity-reviewer

Review data integrity for Rails changes. Use when the user asks for migration safety review, constraint validation, transaction boundary audit, or PII/privacy compliance review.

原文语言：英语

database-admin

PostgreSQL and SQLite database administration for Rails apps. Use when the user asks about backups, monitoring, connection pooling, vacuum/analyze, emergency procedures, restore testing, or production database health checks.

原文语言：英语

database-optimizer

Optimize PostgreSQL/SQLite query performance for Rails. Use when the user asks about EXPLAIN ANALYZE, slow queries, missing indexes (composite/partial/expression/covering/GIN/GiST/BRIN), N+1 detection, eager loading, or ActiveRecord batch processing.

原文语言：英语

gemfile-organize

Reorganize a Rails Gemfile with categorized sections, comment headers, and alphabetized gems within each section. Use when the user asks to organize, sort, group, clean up, or restructure a Gemfile.

原文语言：英语

gemfile-upgrade

Safely upgrade a Ruby gem with changelog review, breaking changes analysis, bundle update, test run, and commit. Use when the user asks to upgrade, bump, or update a gem, or to review outdated gems.

原文语言：英语

skill-eval

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.

原文语言：英语

blueprint

Transform feature descriptions into well-structured project plans

原文语言：英语

devops-plan

Gather DevOps context for infrastructure planning. Detects IaC tools, providers, and recommends skills. Use when Skill("blueprint") detects infrastructure work.

原文语言：英语

blueprint-discovery

Discovery phase for blueprint workflow - interview triggers, acceptance criteria, and feature classification

原文语言：英语

code-review

Generic code review that auto-detects tech stack and delegates to appropriate framework-specific orchestrator

原文语言：英语

design-tool-picker

Help choose the right design tool based on your current task. Use when unsure whether to use frontend-design, ui-ux-designer, visual-validator, or ui-code-auditor.

原文语言：英语

init-agents-config

Generate .agents.yml config from user answers. Provides tech stack templates for Rails, Python, Node, and Generic projects.

原文语言：英语

init

Initialize AGENTS.md with hierarchical structure and .agents.yml config

原文语言：英语

plan-builder

Write implementation plans with appropriate templates based on complexity. Use when planning features or changes. Provides minimal, standard, and full templates for different scope levels.

原文语言：英语

pr-screenshot-docs

Capture and document UI changes with before/after screenshots for pull requests. Use when creating PRs that include visual changes to ensure reviewers can assess design modifications.

原文语言：英语

quality-gate

Run quality gate checks on code changes with tech stack-aware reviewers

原文语言：英语

refactor-agents

Refactor existing AGENTS.md to follow progressive disclosure principles

原文语言：英语

run-blueprint

Execute all tasks in a blueprint using build-task workflow

原文语言：英语

ux-brief

Create junior-dev-ready design systems through guided discovery before implementation

原文语言：英语

skill-linter

Validate skills against agentskills.io specification. Use when adding new skills to the marketplace, reviewing skill PRs, checking skill compliance, or running quality gates on skills. Validates frontmatter fields (name, description, compatibility, metadata,…

原文语言：英语

blueprint-research

Research phase for blueprint workflow - toolbox resolution, lessons discovery, and parallel research agents

原文语言：英语

config-reader

Read project config from .agents.yml and .agents.local.yml with local overrides. Supports dot notation for nested fields. Invoke when agents/skills reference `config_read("field", "default")` pseudocode. Args format "FIELD DEFAULT".

原文语言：英语

debug

Debug errors, test failures, or unexpected behavior. Auto-detects project type.

原文语言：英语

prd

Create a Product Requirements Document (PRD) for a new product or feature

原文语言：英语

task-coordinator

Use when orchestrating multi-step workflows with Claude Code's native Task system (TaskCreate, TaskUpdate, TaskGet, TaskList) - lifecycle management, parallel execution, crash recovery, and progress visibility. Not for simple single-step tasks.

原文语言：英语

tdd-workflow

Test-driven development execution workflow with red-green-refactor cycle, increment decomposition, and pause/continue rules. Use when building features or fixing bugs using TDD. Framework-agnostic with language-specific configs for Python, TypeScript, Go, and…

原文语言：英语

ui-code-auditor

Review source code for UI quality, accessibility violations, and performance anti-patterns. Static code analysis (NOT screenshot-based). Provides file:line references with severity, WCAG refs, and fix suggestions.

原文语言：英语

visual-validator

Use proactively after UI changes to verify they achieved their intended goals. Skeptical visual QA through screenshot analysis, accessibility verification, and design system compliance checking.

原文语言：英语

question

Answer questions about the project structure, documentation, or external topics without coding

原文语言：英语

ship-it

Complete checkout workflow - runs linting, creates commit, and opens PR

原文语言：英语