the-rabak
142 verified skills142 total stars
file-todos
This skill should be used when managing the file-based todo tracking system in the todos/ directory. It provides workflows for creating todos, managing status and dependencies, conducting triage, and integrating with slash commands and code review processes.
development1
file-todos
This skill should be used when managing the file-based todo tracking system in the todos/ directory. It provides workflows for creating todos, managing status and dependencies, conducting triage, and integrating with slash commands and code review processes.
development1
orchestrating-swarms
This skill should be used when orchestrating multi-agent swarms using the host CLI's TeammateTool and Task system. It applies when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns.
tools1
gemini-imagegen
This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.
development1
agent-native-audit
Run a comprehensive scored audit of agent-native architecture principles
testing1
compound-refresh
Refresh stale or drifting learnings and pattern docs in docs/solutions/ against the current codebase
development1
deploy-docs
Validate and prepare documentation for GitHub Pages deployment
testing1
feature-video
Record a video walkthrough of a feature and add it to the PR description
content-media1
file-todos
This skill should be used when managing the file-based todo tracking system in the todos/ directory. It provides workflows for creating todos, managing status and dependencies, conducting triage, and integrating with slash commands and code review processes.
development1
frontend-design
This skill should be used when creating distinctive, production-grade frontend interfaces with high design quality. It applies when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
development1
generate_command
Create a new custom slash command following conventions and best practices
tools1
heal-skill
Fix incorrect SKILL.md files when a skill has wrong instructions or outdated API references
development1
laravel-conventions
Modern Laravel 11+ / PHP 8.3+ coding standards reference. Use when writing or reviewing PHP/Laravel code to ensure convention compliance.
development1
orchestrating-swarms
This skill should be used when orchestrating multi-agent swarms using Claude Code's TeammateTool and Task system. It applies when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns.
tools1
reproduce-bug
Reproduce and investigate a bug using logs, console inspection, and browser screenshots
tools1
resolve-pr-parallel
Resolve all PR comments using parallel processing. Use when addressing PR review feedback, resolving review threads, or batch-fixing PR comments.
documentation1
slrj
Full autonomous engineering workflow using swarm mode for parallel execution
tools1
test-browser
Run browser tests on pages affected by current PR or branch
testing1
workflows-brainstorm
Explore the WHY and WHAT of a feature through collaborative dialogue, producing a user story, architectural context, and design decisions that anchor all downstream phases
testing1
workflows-compound-refresh
Refresh stale learnings and pattern docs in docs/solutions/ against the current codebase
development1
workflows-plan
Transform feature descriptions into structured project plans anchored to user story, architectural context, and success criteria from brainstorm (or constructed fresh when no brainstorm exists)
data-ai1
agent-browser
Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Alternative to Playwright MCP - uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click button", "take screenshot", "scrape page", "web automation".
tools1
agent-native-architecture
Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.
tools1
brainstorming
This skill should be used before implementing features, building components, or making changes. It guides exploring user intent, approaches, and design decisions before planning. Triggers on "let's brainstorm", "help me think through", "what should we build", "explore approaches", ambiguous feature requests, or when the user's request has multiple valid interpretations that need clarification.
development1
cancel-ralph
Cancel an active ralph loop
tools1
changelog
Create engaging changelogs for recent merges to main branch
documentation1
compound-docs
Capture solved problems as categorized documentation with YAML frontmatter for fast lookup
development1
create-agent-skill
Create or edit the host CLI skills with expert guidance on structure and best practices
tools1
create-agent-skills
Expert guidance for creating the host CLI skills and slash commands. Use when working with SKILL.md files, authoring new skills, improving existing skills, creating slash commands, or understanding skill structure and best practices.
tools1
agent-browser
Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Alternative to Playwright MCP - uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click button", "take screenshot", "scrape page", "web automation".
tools1
rclone
Upload, sync, and manage files across cloud storage providers using rclone. Use when uploading files (images, videos, documents) to S3, Cloudflare R2, Backblaze B2, Google Drive, Dropbox, or any S3-compatible storage. Triggers on "upload to S3", "sync to cloud", "rclone", "backup files", "upload video/image to bucket", or requests to transfer files to remote storage.
development1
gemini-imagegen
This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.
development1
brainstorming
This skill should be used before implementing features, building components, or making changes. It guides exploring user intent, approaches, and design decisions before planning. Triggers on "let's brainstorm", "help me think through", "what should we build", "explore approaches", ambiguous feature requests, or when the user's request has multiple valid interpretations that need clarification.
development1
deploy-docs
Validate and prepare documentation for GitHub Pages deployment
testing1
deepen-plan
Enhance a plan with parallel research agents for each section to add depth, best practices, and implementation details
data-ai1
frontend-design
This skill should be used when creating distinctive, production-grade frontend interfaces with high design quality. It applies when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
development1
finishing-branch
Use when completing development on a feature branch -- verifies quality, presents completion options, and cleans up
development1
file-todos
This skill should be used when managing the file-based todo tracking system in the todos/ directory. It provides workflows for creating todos, managing status and dependencies, conducting triage, and integrating with slash commands and code review processes.
development1
feature-video
Record a video walkthrough of a feature and add it to the PR description
content-media1
lrj
Full autonomous engineering workflow
tools1
laravel-conventions
Modern Laravel 11+ / PHP 8.3+ coding standards reference. Use when writing or reviewing PHP/Laravel code to ensure convention compliance.
development1
rclone
Upload, sync, and manage files across cloud storage providers using rclone. Use when uploading files (images, videos, documents) to S3, Cloudflare R2, Backblaze B2, Google Drive, Dropbox, or any S3-compatible storage. Triggers on "upload to S3", "sync to cloud", "rclone", "backup files", "upload video/image to bucket", or requests to transfer files to remote storage.
development1
reproduce-bug
Reproduce and investigate a bug using logs, console inspection, and browser screenshots
tools1
resolve_todo_parallel
Resolve all pending CLI todos using parallel processing
tools1
resolve_pr_parallel
Resolve all PR comments using parallel processing. Use when addressing PR review feedback, resolving review threads, or batch-fixing PR comments.
documentation1
resolve_parallel
Resolve all TODO comments using parallel processing
documentation1
slrj
Full autonomous engineering workflow using swarm mode for parallel execution
tools1
setup
Configure which review agents run for your project. Auto-detects stack and writes compound-engineering.local.md.
documentation1
test-browser
Run browser tests on pages affected by current PR or branch
testing1
workflows-plan
Transform feature descriptions into well-structured project plans following conventions
tools1
workflows-compound
Document a recently solved problem to compound your team's knowledge
documentation1
triage
Triage and categorize findings for the CLI todo system
tools1
workflows-work
Execute work plans efficiently while maintaining quality and finishing features
testing1
workflows-review
Perform exhaustive code reviews using multi-agent analysis, ultra-thinking, and worktrees
development1
brainstorming
This skill should be used before implementing features, building components, or making changes. It guides exploring user intent, approaches, and design decisions before planning. Triggers on "let's brainstorm", "help me think through", "what should we build", "explore approaches", ambiguous feature requests, or when the user's request has multiple valid interpretations that need clarification.
development1
agent-native-audit
Run a comprehensive scored audit of agent-native architecture principles
testing1
create-agent-skills
Expert guidance for creating Claude Code skills and slash commands. Use when working with SKILL.md files, authoring new skills, improving existing skills, creating slash commands, or understanding skill structure and best practices.
development1
compound-refresh
Refresh stale or drifting learnings and pattern docs in docs/solutions/ against the current codebase
development1
git-worktree
This skill manages Git worktrees for isolated parallel development. It handles creating, listing, switching, and cleaning up worktrees with a simple interactive interface, following KISS principles.
development1
document-review
This skill should be used to refine brainstorm or plan documents before proceeding to the next workflow step. It applies when a brainstorm or plan document exists and the user wants to improve it.
documentation1
compound-docs
Capture solved problems as categorized documentation with YAML frontmatter for fast lookup
development1
laravel-conventions
Modern Laravel 11+ / PHP 8.3+ coding standards reference. Use when writing or reviewing PHP/Laravel code to ensure convention compliance.
development1
ideate
Generate and critically evaluate grounded improvement ideas for the current project before selecting one to brainstorm
data-ai1
frontend-design
This skill should be used when creating distinctive, production-grade frontend interfaces with high design quality. It applies when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
development1
finishing-branch
Use when completing development on a feature branch -- verifies quality, presents completion options, and cleans up
development1
resolve-pr-parallel
Resolve all PR comments using parallel processing. Use when addressing PR review feedback, resolving review threads, or batch-fixing PR comments.
documentation1
systematic-debugging
Use when debugging unexpected errors during implementation -- provides a structured 4-phase methodology instead of trial-and-error
development1
agent-browser
Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Alternative to Playwright MCP - uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click button", "take screenshot", "scrape page", "web automation".
tools1
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
tools1
agent-native-audit
Run a comprehensive scored audit of agent-native architecture principles
testing1
compound-refresh
Refresh stale or drifting learnings and pattern docs in docs/solutions/ against the current codebase
development1
compound-docs
Capture solved problems as categorized documentation with YAML frontmatter for fast lookup
development1
create-agent-skills
Expert guidance for creating Claude Code skills and slash commands. Use when working with SKILL.md files, authoring new skills, improving existing skills, creating slash commands, or understanding skill structure and best practices.
development1
document-review
This skill should be used to refine brainstorm or plan documents before proceeding to the next workflow step. It applies when a brainstorm or plan document exists and the user wants to improve it.
documentation1
resolve-pr-parallel
Resolve all PR comments using parallel processing. Use when addressing PR review feedback, resolving review threads, or batch-fixing PR comments.
documentation1
git-worktree
This skill manages Git worktrees for isolated parallel development. It handles creating, listing, switching, and cleaning up worktrees with a simple interactive interface, following KISS principles.
development1
ideate
Generate and critically evaluate grounded improvement ideas for the current project before selecting one to brainstorm
data-ai1
rclone
Upload, sync, and manage files across cloud storage providers using rclone. Use when uploading files (images, videos, documents) to S3, Cloudflare R2, Backblaze B2, Google Drive, Dropbox, or any S3-compatible storage. Triggers on "upload to S3", "sync to cloud", "rclone", "backup files", "upload video/image to bucket", or requests to transfer files to remote storage.
development1
frontend-design
This skill should be used when creating distinctive, production-grade frontend interfaces with high design quality. It applies when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
development1
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
tools1
laravel-conventions
Modern Laravel 11+ / PHP 8.3+ coding standards reference. Use when writing or reviewing PHP/Laravel code to ensure convention compliance.
development1
systematic-debugging
Use when debugging unexpected errors during implementation -- provides a structured 4-phase methodology instead of trial-and-error
development1
disabled-skill
A skill with model invocation disabled
data-ai1
agent-native-architecture
Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.
tools1
agent-native-architecture
Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.
tools1
focused-ticket-priming
Package one plan execution packet into a compact ticket-local execution packet with parent refs, scope fences, feature-home ownership, and evidence commands. Use when converting plans into local tickets or when execution needs one ticket-sized context pack without the full plan.
tools1
focused-ticket-priming
Package one plan execution packet into a compact ticket-local execution packet with parent refs, scope fences, feature-home ownership, and evidence commands. Use when converting plans into local tickets or when execution needs one ticket-sized context pack without the full plan.
tools1
ralph-loop
Start a self-referential loop that continues until a completion promise is met
tools1
heal-skill
Fix incorrect SKILL.md files when a skill has wrong instructions or outdated API references
development1
setup
Configure which review agents run for your project. Auto-detects stack and writes compound-engineering.local.md.
documentation1
report-bug
Report a bug in the compound-engineering plugin
tools1
caveman
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
tools1
caveman
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
tools1
default-skill
--- name: default-skill --- Default skill
tools1
custom-skill
--- name: custom-skill --- Custom skill
tools1
skill-one
Sample skill
tools1
skill-one
Shared reusable skill.
tools1
ubiquitous-language
Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".
development1
adversarial-plan-audit
Run a deep adversarial review of plans and architecture before implementation. Use when validating strategy docs, contracts, roadmaps, and competitive positioning with scored findings and prioritized recommendations.
testing1
generate_command
Create a new custom slash command following conventions and best practices
tools1
git-worktree
This skill manages Git worktrees for isolated parallel development. It handles creating, listing, switching, and cleaning up worktrees with a simple interactive interface, following KISS principles.
development1
agent-native-architecture
Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.
tools1
agent-browser
Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Alternative to Playwright MCP - uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click button", "take screenshot", "scrape page", "web automation".
tools1
compound-docs
Capture solved problems as categorized documentation with YAML frontmatter for fast lookup
development1
brainstorming
This skill should be used before implementing features, building components, or making changes. It guides exploring user intent, approaches, and design decisions before planning. Triggers on "let's brainstorm", "help me think through", "what should we build", "explore approaches", ambiguous feature requests, or when the user's request has multiple valid interpretations that need clarification.
development1
cancel-ralph
Cancel an active ralph loop
tools1
changelog
Create engaging changelogs for recent merges to main branch
documentation1
create-agent-skill
Create or edit Claude Code skills with expert guidance on structure and best practices
development1
create-agent-skills
Expert guidance for creating Claude Code skills and slash commands. Use when working with SKILL.md files, authoring new skills, improving existing skills, creating slash commands, or understanding skill structure and best practices.
development1
deepen-plan
Enhance a plan with parallel research agents grounded in user story, architectural context, and success criteria to add depth without losing purpose
data-ai1
document-review
This skill should be used to refine brainstorm or plan documents before proceeding to the next workflow step. It applies when a brainstorm or plan document exists and the user wants to improve it.
documentation1
finishing-branch
Use when completing development on a feature branch -- verifies quality, presents completion options, and cleans up
development1
gemini-imagegen
This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.
development1
git-worktree
This skill manages Git worktrees for isolated parallel development. It handles creating, listing, switching, and cleaning up worktrees with a simple interactive interface, following KISS principles.
development1
ideate
Generate and critically evaluate grounded improvement ideas for the current project before selecting one to brainstorm
data-ai1
lrj
Full autonomous engineering workflow
tools1
ralph-loop
Start a self-referential loop that continues until a completion promise is met
tools1
report-bug
Report a bug in the compound-engineering plugin
tools1
rclone
Upload, sync, and manage files across cloud storage providers using rclone. Use when uploading files (images, videos, documents) to S3, Cloudflare R2, Backblaze B2, Google Drive, Dropbox, or any S3-compatible storage. Triggers on "upload to S3", "sync to cloud", "rclone", "backup files", "upload video/image to bucket", or requests to transfer files to remote storage.
development1
resolve_parallel
Resolve all TODO comments using parallel processing
documentation1
resolve_todo_parallel
Resolve all pending CLI todos using parallel processing
tools1
setup
Configure which review agents run for your project. Auto-detects stack and writes compound-engineering.local.md.
documentation1
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
tools1
systematic-debugging
Use when debugging unexpected errors during implementation -- provides a structured 4-phase methodology instead of trial-and-error
development1
workflows-compound
Document a recently solved problem to compound your team's knowledge
documentation1
triage
Triage and categorize findings for the CLI todo system
tools1
workflows-work
Execute work plans while maintaining WHY tracing from problem narrative through user story to implementation. Grounds every subagent in purpose.
testing1
workflows-ideate
Generate and rank grounded improvement ideas before selecting one to brainstorm
data-ai1
workflows-review
Perform exhaustive code reviews grounded in the user story. Filters technical findings through WHY context to protect purpose while improving quality.
development1
finishing-branch
Use when completing development on a feature branch -- verifies quality, presents completion options, and cleans up
development1
ubiquitous-language
Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".
development1
workflows-brainstorm
Explore requirements and approaches through collaborative dialogue before planning implementation
data-ai1
systematic-debugging
Use when debugging unexpected errors during implementation -- provides a structured 4-phase methodology instead of trial-and-error
development1
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends the model's capabilities with specialized knowledge, workflows, or tool integrations.
tools1
gemini-imagegen
This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.
development1
document-review
This skill should be used to refine brainstorm or plan documents before proceeding to the next workflow step. It applies when a brainstorm or plan document exists and the user wants to improve it.
documentation1
orchestrating-swarms
This skill should be used when orchestrating multi-agent swarms using Claude Code's TeammateTool and Task system. It applies when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns.
tools1
setup
Configure which review agents run for your project. Auto-detects stack and writes compound-engineering.local.md.
documentation1
orchestrating-swarms
This skill should be used when orchestrating multi-agent swarms using Claude Code's TeammateTool and Task system. It applies when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns.
tools1
adversarial-plan-audit
Run a deep adversarial review of plans and architecture before implementation. Use when validating strategy docs, contracts, roadmaps, and competitive positioning with scored findings and prioritized recommendations.
testing1
grill-with-docs
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, brainstorm docs, plan docs, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
testing1
grill-with-docs
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, brainstorm docs, plan docs, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
testing1