Engineer robust ETL pipelines: clean messy CSVs/Parquet, infer schemas, profile datasets, detect anomalies, validate quality with Pydantic/Pandera/Great Expectations, implement incremental patterns, generate dbt models/SQL migrations/tests, and orchestrate autonomous backfills/pipeline testing via agents and CLI commands.
Generate or execute data migration scripts with safety checks.
Generate comprehensive data profile for a file or table.
Transform data files between formats or apply transformations.
Run data validation suite against a dataset.
Generate test suites for ETL pipelines using fixture generation and testing patterns.
Design and execute historical data backfill strategies with progress tracking.
Plan and coordinate multi-step ETL pipelines with dependency management.
Detect anomalies in data using statistical and ML methods. Z-score, IQR, Isolation Forest, and time-series anomalies.
Handle messy CSVs with encoding detection, delimiter inference, and malformed row recovery.
Generate data profiles with column stats, correlations, and missing patterns for DataFrames. Use for EDA and data discovery.
Quality dimensions, scorecards, distribution monitoring, and freshness checks. Use for data validation pipelines and quality gates.
Data validation patterns and pipeline helpers. Custom validation functions, schema evolution, and test assertions.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
The Majestic marketplace where we share our workflows.
New here? Check out the Marketplace Tutorial for an interactive walkthrough.
Coding is no longer the bottleneck. Planning, review, and learning loops matter more than syntax. Each feature makes the next one easier to build.
| Step | What Happens | Key Tools |
|---|---|---|
| Plan | Agents research codebase + best practices, produce detailed implementation plans | /majestic:plan, architect agent |
| Work | Agents write code, tests, and iterate using real app feedback | /majestic:build-task, coder skills |
| Assess | Multi-angle review: security, performance, simplicity, conventions | /majestic:code-review, quality-gate |
| Reflect | Analyze session patterns, capture lessons so future agents improve | /majestic-tools:insight:reflect, /majestic:add-lesson |
See the Workflow Guide for detailed documentation.
Run the installer:
curl -fsSL https://raw.githubusercontent.com/majesticlabs-dev/majestic-marketplace/master/install.sh | bash
This gives you options to:
Run claude and add the marketplace:
/plugin marketplace add https://github.com/majesticlabs-dev/majestic-marketplace.git
Then install a plugin:
/plugin install {plugin-name}
Export Majestic plugins to OpenCode or Codex with schema-aware conversion:
./scripts/install-codex.sh
# Install all plugins
./scripts/install-codex.sh --all
# Install all plugins to OpenCode
./scripts/install-opencode.sh --all
# Install specific plugins
./scripts/install-codex.sh engineer rails tools
# Example (explicit): convert engineer, rails, and tools to OpenCode
# Output target: ~/.config/opencode
./scripts/install-opencode.sh engineer rails tools
# Install one plugin (short or prefixed)
./scripts/install-codex.sh engineer
./scripts/install-codex.sh majestic-tools
Both commands are now local to this repository and only require Ruby (scripts/convert-plugin.rb).
This runs a converter pipeline (not a plain file copy), so incompatible Claude metadata is translated for target formats.
disable-model-invocation frontmatter is preserved as part of source metadata parsing, but it does not exclude a command from conversion for OpenCode/Codex output.
Output locations:
~/.codex/skills/ and ~/.codex/prompts/~/.config/opencode (opencode.json, agents/, skills/, plugins/)Limitations: Codex still does not support some Claude Code features (Task, hooks, some MCP integrations), so behavior is reduced there.
| Plugin | Description |
|---|---|
| majestic-engineer | Language-agnostic engineering workflows (17 agents, 8 commands, 12 skills) |
| majestic-rails | Ruby on Rails development tools (23 agents, 5 commands, 9 skills) |
| majestic-react | Modern React development with TypeScript (3 agents, 1 command, 4 skills) |
| majestic-python | Python development tools (2 agents) |
| majestic-devops | Infrastructure-as-Code and DevOps workflows (1 agent, 8 skills) |
| majestic-llm | External LLM integration - Codex, Gemini (5 agents, 1 command) |
| majestic-marketing | Marketing and SEO tools (14 agents, 2 commands, 24 skills) |
| majestic-sales | Sales acceleration tools (1 command, 6 skills) |
| majestic-company | Business operations and CEO tools (2 agents, 21 skills) |
| majestic-experts | Expert panel discussion system (2 agents, 1 command) |
| majestic-tools | Claude Code customization tools (10 commands, 3 skills) |
Claude Code customization tools. Includes 0 agents, 13 commands, and 12 skills.
Infrastructure as Code and DevOps tools. Includes 0 agents and 15 skills for OpenTofu, Ansible, Hetzner, DigitalOcean, Cloudflare, 1Password CLI, cloud-init, and devops-plan.
AI-powered creative tools for image generation, editing, and visual content creation. Includes 0 agents, 1 command, and 1 skill for Gemini image generation.
Expert panel discussion system with 22 curated personas. Includes 2 agents, 1 command, and 22 expert definitions.
Language-agnostic engineering workflows. Includes 20 specialized agents, 33 commands, 43 skills, and 5 toolbox presets. Now includes relay orchestration for fresh-context task execution with quality gates and compound learning.
npx claudepluginhub majesticlabs-dev/majestic-marketplace --plugin majestic-dataEditorial "Data Engineering" bundle for Claude Code from Antigravity Awesome Skills.
Data engineering agents providing expertise in ETL pipelines, streaming, and data warehousing
Spec-Driven Development framework for Data Engineering — 58 agents, 24 KB domains, 5-phase SDD workflow, 31 commands
Automated data preprocessing and cleaning pipelines
Data engineering plugin - warehouse exploration, pipeline authoring, Airflow integration
Quick insights from dlt pipeline data. Connect to a pipeline, profile tables, plan charts, and assemble marimo dashboards.