84045 Skills Available

Find awesome
Agent Skills

Agent-Skills.md is a agent skills marketplace, to find the right agent skills for you.

Popular searches

backlog-manager

Manage backlog items across multiple backends (GitHub Issues, Linear, Beads). Configure task_management in .agents.yml.

majesticlabs-dev
majesticlabs-dev
5010

blueprint-discovery

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

majesticlabs-dev
majesticlabs-dev
5010

blueprint-research

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

majesticlabs-dev
majesticlabs-dev
5010

brainstorming

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

majesticlabs-dev
majesticlabs-dev
5010

business-logic-coder

Implement business logic with ActiveInteraction and AASM state machines. Routes to specialized skills for typed operations and state management.

majesticlabs-dev
majesticlabs-dev
5010

cloudflare-coder

This skill guides provisioning Cloudflare infrastructure with OpenTofu/Terraform. Use when managing zones, DNS records, WAF rules, SSL settings, Page Rules, or cache configuration.

majesticlabs-dev
majesticlabs-dev
5010

cloudflare-worker

Build edge-first TypeScript applications on Cloudflare Workers. Covers Workers API, Hono framework, KV/D1/R2 storage, Durable Objects, Queues, and testing patterns. Use when creating serverless workers, edge functions, or Cloudflare-deployed services.

majesticlabs-dev
majesticlabs-dev
5010

cloud-init-coder

This skill guides writing cloud-init configurations for VM provisioning. Use when creating user_data blocks in Terraform/OpenTofu, or cloud-init YAML for AWS, DigitalOcean, GCP, or Azure instances.

majesticlabs-dev
majesticlabs-dev
5010

compound-learnings

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

majesticlabs-dev
majesticlabs-dev
5010

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".

majesticlabs-dev
majesticlabs-dev
5010

constraints-reviewer

Review data constraints and referential integrity in Rails models and migrations.

majesticlabs-dev
majesticlabs-dev
5010

create-adr

Create Architecture Decision Records (ADRs) to document significant technical decisions, their context, alternatives considered, and consequences. Use when making architectural choices, selecting libraries/frameworks, or designing system components.

majesticlabs-dev
majesticlabs-dev
5010

csv-wrangler

Handle messy CSVs with encoding detection, delimiter inference, and malformed row recovery.

majesticlabs-dev
majesticlabs-dev
5010

data-profiler

Generate data profiles with column stats, correlations, and missing patterns for DataFrames. Use for EDA and data discovery.

majesticlabs-dev
majesticlabs-dev
5010

data-quality

Quality dimensions, scorecards, distribution monitoring, and freshness checks. Use for data validation pipelines and quality gates.

majesticlabs-dev
majesticlabs-dev
5010

data-validation

Data validation patterns and pipeline helpers. Custom validation functions, schema evolution, and test assertions.

majesticlabs-dev
majesticlabs-dev
5010

dbt-coder

dbt (data build tool) patterns for model organization, incremental strategies, and testing.

majesticlabs-dev
majesticlabs-dev
5010

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.

majesticlabs-dev
majesticlabs-dev
5010

devils-advocate

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

majesticlabs-dev
majesticlabs-dev
5010

devops-maintainability-checker

Infrastructure maintainability verification covering naming conventions, formatting, DRY patterns, and version constraints.

majesticlabs-dev
majesticlabs-dev
5010

devops-plan

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

majesticlabs-dev
majesticlabs-dev
5010

devops-platform-patterns

Platform-specific IaC checklists for DigitalOcean, Hetzner, AWS, and Cloudflare.

majesticlabs-dev
majesticlabs-dev
5010

devops-simplicity-checker

Infrastructure simplicity scoring. Detects overengineering in Terraform/OpenTofu and Ansible configurations.

majesticlabs-dev
majesticlabs-dev
5010

devops-verifier

Verify DevOps/infrastructure code against best practices, security, simplicity, and documentation standards. Use after implementing or before shipping infrastructure changes.

majesticlabs-dev
majesticlabs-dev
5010

dhh-coder

Write Ruby and Rails code in DHH's distinctive 37signals style. Use this skill when writing Ruby code, Rails applications, creating models, controllers, or any Ruby file. Triggers on Ruby/Rails code generation, refactoring requests, or when the user mentions DHH, 37signals, Basecamp, HEY, Fizzy, or Campfire style.

majesticlabs-dev
majesticlabs-dev
5010

dhh-code-reviewer

DHH-style code review. Reviews Ruby, Rails, and JavaScript code for convention violations, framework contamination, and unnecessary complexity.

majesticlabs-dev
majesticlabs-dev
5010

dialog-patterns

Native HTML dialog patterns for Rails with Turbo and Stimulus. Use when building modals, confirmations, alerts, or any overlay UI. Triggers on modal, dialog, popup, confirmation, alert, or toast patterns.

majesticlabs-dev
majesticlabs-dev
5010

digitalocean-coder

This skill guides writing DigitalOcean infrastructure with OpenTofu/Terraform. Use when provisioning Droplets, VPCs, Managed Databases, Firewalls, or other DO resources.

majesticlabs-dev
majesticlabs-dev
5010

django-coder

Build Django applications with models, views, forms, templates, REST APIs, and modern Django 5.x patterns.

majesticlabs-dev
majesticlabs-dev
5010

docs-researcher

Fetch and summarize API documentation from official sources before implementation. Covers Rails, Tailwind, external libraries, and gem source exploration. Triggers on fetch docs, API reference, library documentation, check docs, read documentation.

majesticlabs-dev
majesticlabs-dev
5010

document-refinement

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

majesticlabs-dev
majesticlabs-dev
5010

etl-core-patterns

Core ETL reliability patterns including idempotency, checkpointing, error handling, chunking, retry logic, and logging.

majesticlabs-dev
majesticlabs-dev
5010

etl-incremental-patterns

Incremental data loading patterns including backfill strategies, CDC, timestamp-based loads, and pipeline orchestration.

majesticlabs-dev
majesticlabs-dev
5010

etl-patterns

Production ETL patterns orchestrator. Routes to core reliability patterns and incremental load strategies.

majesticlabs-dev
majesticlabs-dev
5010

event-sourcing-coder

Record domain events and dispatch to inbox handlers for side effects, audit trails, and activity feeds. Use when building activity logs, syncing external services, or decoupling event creation from processing. Triggers on event recording, audit trails, activity feeds, or inbox patterns.

majesticlabs-dev
majesticlabs-dev
5010

external-llm-consulting

Get architecture and design second opinions from external LLMs (OpenAI Codex, Google Gemini) via their CLIs. Use when you need alternative perspectives on design decisions, model selection, or structured comparison of approaches.

majesticlabs-dev
majesticlabs-dev
5010

external-llm-review

Get code review feedback from external LLMs (OpenAI Codex, Google Gemini) with full project context. Use when you want a second opinion on code changes, with explicit control over review focus and project-aware prompts.

majesticlabs-dev
majesticlabs-dev
5010

fastapi-coder

Build FastAPI applications with async patterns, Pydantic validation, dependency injection, and modern Python API practices.

majesticlabs-dev
majesticlabs-dev
5010

fix-decision-router

Post-documentation decision menu for fix-reporter. Routes to critical patterns, skill updates, cross-references, or discovery enablement.

majesticlabs-dev
majesticlabs-dev
5010

fix-reporter

Capture solved problems as categorized documentation with YAML frontmatter for fast lookup

majesticlabs-dev
majesticlabs-dev
5010

fluff-detector

Detect human-oriented content in LLM artifacts. Flags attribution, personas, redundant explanations, marketing language, and decorative elements that waste tokens without improving LLM behavior.

majesticlabs-dev
majesticlabs-dev
5010

frontend-css-patterns

Framework-agnostic CSS patterns for typography, color, motion, and spatial composition.

majesticlabs-dev
majesticlabs-dev
5010

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.

majesticlabs-dev
majesticlabs-dev
5010

frontend-design-philosophy

Design thinking principles for distinctive interfaces. Covers aesthetic direction, anti-patterns, and avoiding generic AI-generated aesthetics.

majesticlabs-dev
majesticlabs-dev
5010

gem-builder

Build production-quality Ruby gems. Use when creating new gems, structuring gem architecture, implementing configuration patterns, setting up testing, or preparing for publishing. Covers all gem types - libraries, CLI tools, Rails engines, and API clients.

majesticlabs-dev
majesticlabs-dev
5010

gemini-image-coder

Generate and edit images using Google's Gemini API. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.

majesticlabs-dev
majesticlabs-dev
5010

git-researcher

Analyze git history to trace code evolution, identify contributors, and understand commit patterns. Use for archaeological analysis of repositories. Triggers on git history, blame analysis, code evolution, contributor mapping, commit patterns.

majesticlabs-dev
majesticlabs-dev
5010

git-worktree

Manage git worktrees for parallel development. Use when the user wants to work on multiple branches simultaneously, create isolated environments for features/fixes, or clean up completed worktrees.

majesticlabs-dev
majesticlabs-dev
5010

graphql-architect

Use proactively for GraphQL API design, schema optimization, or N+1 query issues. Designs schemas, resolvers, and subscriptions using graphql-ruby patterns.

majesticlabs-dev
majesticlabs-dev
5010

great-expectations

Data validation using Great Expectations. Expectation suites, checkpoints, and data docs for pipeline monitoring.

majesticlabs-dev
majesticlabs-dev
5010

Page 738 of 1681 · 84045 results

Adoption

Agent Skills are supported by leading AI development tools.

FAQ

Frequently asked questions about Agent Skills.

01

What are Agent Skills?

Agent Skills are reusable, production-ready capability packs for AI agents. Each skill lives in its own folder and is described by a SKILL.md file with metadata and instructions.

02

What does this agent-skills.md site do?

Agent Skills is a curated directory that indexes skill repositories and lets you browse, preview, and download skills in a consistent format.

03

Where are skills stored in a repo?

By default, the site scans the skills/ folder. You can also submit a URL that points directly to a specific skills folder.

04

What is required inside SKILL.md?

SKILL.md must include YAML frontmatter with at least name and description. The body contains the actual guidance and steps for the agent.

05

How can I submit a repo?

Click Submit in the header and paste a GitHub URL that points to a skills folder. We’ll parse it and add any valid skills to the directory.