roberto-mello
46 verified skills1,774 total stars
lavra-work-single
Single-bead implementation path for lavra-work, phases 1-5. Invoked by lavra-work router. Use when working on exactly one bead.
tools45
lavra-work
Execute work on one or many beads -- auto-routes between single-bead, sequential, and multi-bead parallel paths based on input
tools45
lavra-work
Execute work on one or many beads -- auto-routes between single-bead, sequential, and multi-bead parallel paths based on input
tools45
lavra-work-single
Single-bead implementation path for lavra-work, phases 1-5. Invoked by lavra-work router. Use when working on exactly one bead.
tools45
lavra-knowledge
Capture solved problems as knowledge entries for fast recall. Use when a solution should be preserved for future sessions.
tools45
lavra-knowledge
Capture solved problems as knowledge entries for fast recall. Use when a solution should be preserved for future sessions.
tools45
lavra-work-multi
Multi-bead orchestration path (Phases M1-M10) — invoked by lavra-work router. Use when working on multiple beads in parallel.
tools45
lavra-work-multi
Multi-bead orchestration path (Phases M1-M10) — invoked by lavra-work router. Use when working on multiple beads in parallel.
tools45
lavra-research
Gather evidence and best practices for a plan using domain-matched research agents
data-ai38
lavra-brainstorm
Explore requirements and approaches through collaborative dialogue before planning
data-ai38
lavra-eng-review
Engineering review -- parallel agents check architecture, simplicity, security, and performance
testing38
lavra-research
Gather evidence and best practices for a plan using domain-matched research agents
data-ai38
lavra-review
Perform exhaustive code reviews using multi-agent analysis and ultra-thinking
development38
lavra-brainstorm
Explore requirements and approaches through collaborative dialogue before planning
data-ai38
lavra-plan
Transform feature descriptions into well-structured beads with parallel research and multi-phase planning
research38
lavra-review
Perform exhaustive code reviews using multi-agent analysis and ultra-thinking
development38
lavra-eng-review
Engineering review -- parallel agents check architecture, simplicity, security, and performance
testing38
lavra-plan
Transform feature descriptions into well-structured beads with parallel research and multi-phase planning
research38
every-style-editor
Review and edit copy against Every's style guide. Use when editing articles, headlines, or any content that should follow Every's grammar and style rules.
documentation37
brainstorming
Explore user intent, approaches, and design decisions before planning. Use for ambiguous requests, brainstorming sessions, or feature exploration.
testing37
agent-native-architecture
Design agent-native architectures where agents are first-class citizens. Use when building autonomous agents, MCP tools, or self-modifying systems.
tools37
rclone
Sync and manage files across cloud storage using rclone. Use when uploading to S3, R2, Backblaze, Google Drive, Dropbox, or any S3-compatible storage.
development37
creating-agent-skills
Create and refine Claude Code Skills. Use when authoring SKILL.md files, building new skills, or improving existing skill structure and best practices.
development37
gemini-imagegen
Generate and edit images using the Gemini API. Use for text-to-image, image editing, style transfers, logos, stickers, or product mockups.
development37
lavra-ceo-review
CEO/founder-mode plan review -- challenge premises, validate business fit, run 10-section structured review
testing37
dhh-rails-style
Write Ruby and Rails code in DHH's 37signals style. Use for Rails apps, models, controllers, or when DHH/Basecamp/Hotwire conventions are requested.
development37
git-worktree
Manage Git worktrees for isolated parallel development. Use when creating, switching, or cleaning up worktrees for parallel bead work.
development37
frontend-design
Create distinctive, production-grade frontend interfaces. Use when building web components, pages, or apps where design quality and polish matter.
development37
file-todos
Manage file-based todos in todos/ directory. Use when creating, triaging, or tracking todos and integrating them with code review.
development37
agent-native-architecture
Design agent-native architectures where agents are first-class citizens. Use when building autonomous agents, MCP tools, or self-modifying systems.
tools37
andrew-kane-gem-writer
Write Ruby gems following Andrew Kane's patterns. Use when creating or refactoring gems, designing gem APIs, or building minimal production-ready Ruby libraries.
development37
andrew-kane-gem-writer
Write Ruby gems following Andrew Kane's patterns. Use when creating or refactoring gems, designing gem APIs, or building minimal production-ready Ruby libraries.
development37
brainstorming
Explore user intent, approaches, and design decisions before planning. Use for ambiguous requests, brainstorming sessions, or feature exploration.
testing37
creating-agent-skills
Create and refine Claude Code Skills. Use when authoring SKILL.md files, building new skills, or improving existing skill structure and best practices.
development37
dhh-rails-style
Write Ruby and Rails code in DHH's 37signals style. Use for Rails apps, models, controllers, or when DHH/Basecamp/Hotwire conventions are requested.
development37
dspy-ruby
Build type-safe LLM applications with DSPy.rb. Use when implementing AI features, LLM signatures, agent systems, or prompt optimization in Ruby.
development37
dspy-ruby
Build type-safe LLM applications with DSPy.rb. Use when implementing AI features, LLM signatures, agent systems, or prompt optimization in Ruby.
development37
every-style-editor
Review and edit copy against Every's style guide. Use when editing articles, headlines, or any content that should follow Every's grammar and style rules.
documentation37
file-todos
Manage file-based todos in todos/ directory. Use when creating, triaging, or tracking todos and integrating them with code review.
development37
gemini-imagegen
Generate and edit images using the Gemini API. Use for text-to-image, image editing, style transfers, logos, stickers, or product mockups.
development37
git-worktree
Manage Git worktrees for isolated parallel development. Use when creating, switching, or cleaning up worktrees for parallel bead work.
development37
lavra-ceo-review
CEO/founder-mode plan review -- challenge premises, validate business fit, run 10-section structured review
testing37
rclone
Sync and manage files across cloud storage using rclone. Use when uploading to S3, R2, Backblaze, Google Drive, Dropbox, or any S3-compatible storage.
development37
frontend-design
Create distinctive, production-grade frontend interfaces. Use when building web components, pages, or apps where design quality and polish matter.
development37
agent-browser
Browser automation via Vercel's agent-browser CLI. Use when browsing websites, filling forms, taking screenshots, or scraping data.
tools36
agent-browser
Browser automation via Vercel's agent-browser CLI. Use when browsing websites, filling forms, taking screenshots, or scraping data.
tools36