AI Skills

optimize-web

Optimizes Unity WebGL and WebGPU builds for smaller downloads and faster load

router

Routes any game-development request

saas-metrics

SaaS business metrics analysis

slack-workflows

Slack automation and workflow builder

web-search

Web search. Returns ranked results with snippets, URLs, thumbnails

yahoo-finance

Get stock prices, quotes, fundamentals, earnings, options, dividends

actualize

Reconcile the project's FPF state with recent repository changes

add-task

Creates draft task file in .specs/tasks/draft/ with original user intent

agent-evaluation

Evaluate and improve Claude Code commands, skills, and agents

analyse

Auto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target

analyse-problem

Comprehensive A3 one-page problem analysis with root cause and action plan

analyze-issue

Analyze a GitHub issue and create a detailed technical specification

apply-anthropic-skill-best-practices

Comprehensive guide

attach-review-to-pr

Add line-specific review comments to pull requests using GitHub CLI API

brainstorm

Creating or developing, before writing code or implementation plans

cause-and-effect

Systematic Fishbone analysis exploring problem causes across six categories

commit

Create well-formatted commits with conventional commit messages and emoji

context-engineering

Understand the components, mechanics

create-agent

Comprehensive guide for creating Claude Code agents

create-hook

Create and configure git hooks

create-ideas

Generate ideas in one shot using creative sampling

create-pr

Create pull requests using GitHub CLI with proper templates and formatting

create-rule

Found gap or repetative issue, that produced by you or implemenataion agent

create-skill

Guide for creating effective skills

critique

Comprehensive multi-perspective review using specialized judges

do-and-judge

Execute a task with sub-agent implementation

do-competitively

Execute tasks through competitive multi-agent generation

do-in-parallel

Run independent tasks concurrently across multiple files or targets

do-in-steps

Execute one complex task as ordered, dependent steps run sequentially

fix-tests

Systematically fix all failing tests after business logic changes or refactoring

git-worktrees

Working on multiple branches simultaneously, context switching without stashing

implement-task

Implement a task step by step

judge

Launch a meta-judge then a judge sub-agent

judge-with-debate

Evaluate solutions through multi-round debate between independent judges until

launch-sub-agent

Launch an intelligent sub-agent

memorize

Curates insights from reflections and critiques into CLAUDE.md

multi-agent-patterns

Design multi-agent architectures for complex tasks

open-prose

Activate when the user types `prose ...`, opens a `.prose.md` file

plan-do-check-act

Iterative PDCA cycle for systematic experimentation and continuous improvement

plan-task

Refine a draft task specification into a fully planned

prompt-engineering

You writing commands, hooks, skills for Agent

reflect

Reflect on previus response and output

review-local-changes

Review your local uncommitted working-tree changes

review-pr

Review an existing GitHub pull request

setup-serena-mcp

Guide for setup Serena MCP server for semantic code retrieval

subagent-driven-development

Executing implementation plans

test-prompt

Creating or editing any prompt

test-skill

Creating or editing skills, before deployment

thought-based-reasoning

Tackling complex reasoning tasks requiring step-by-step logic

tree-of-thoughts

Execute tasks through systematic exploration, pruning, and expansion