Skill UI

This advanced skill analyzes an existing codebase to identify architectural patterns, dependencies, and technical stacks. It recommends tailored Claude Code automations—including Hooks, Subagents, Skills, Plugins, and MCP Servers—to optimize development workflows, improve code consistency, and enhance overall project scalability. Use this when setting up a new project or looking to refine existing Claude Code configurations.

Guides creation of Cursor-specific subagents with isolated contexts, structured prompts, and frontmatter so multi-step workflows, verifiers, or specialists follow Cursor’s directories and delegation rules.

Guides orchestrating multiple Task tool subagents with run_in_background for concurrent work, covering when to trigger parallelism, how to craft prompts, launch in one message, synchronize results, and integrate TodoWrite status updates.

Runs Semgrep static analysis with auto language detection, parallel Task subagents, Semgrep Pro checks, and configurable “run all” or “important only” modes to audit codebases for vulnerabilities and bug patterns.

Guides execution of implementation plans by dispatching isolated subagents per task, enforcing a spec-first then quality review loop, and preserving overall coordination context for faster, high-quality iterations.

A skill for orchestrating parallel AI subagents that compete on the same task using isolated git worktrees. Handles session setup, agent spawning, progress monitoring, evaluation via metrics or LLM judge, and final merge of the winning branch. Ideal for code optimization, content variation, research exploration, and any task benefiting from parallel competition.

The /hub:spawn command launches N subagents simultaneously, each operating in an isolated git worktree to work on the same task. It supports custom templates (like optimizer or refactorer) and manages the entire parallel execution cycle, ensuring diverse strategies and structured results for maximum value exploration.

Execute an implementation plan inline in the current session, task by task, using TDD and a durable ledger instead of per-task subagents. Choose it when your partner picks inline execution or no subagent tools exist. Covers briefs, rulings, completion contracts and final branch review.

This advanced skill manages complex, large-scale development tasks by coordinating multiple, specialized subagents in parallel. It systematically decomposes the goal into isolated missions, manages resource quotas (token usage), and handles error recovery across multiple files and components. Ideal for large feature builds, system refactoring, or complex applications requiring multiple, concurrent roles (Planner, Builder, Tester).

Build with and use Pi, a minimal terminal coding harness. Covers install, provider and model config, TypeScript extensions, skills, packages, themes, SDK embedding, RPC and JSON event streams, session parsing, local llama.cpp models, custom providers, TUI components, and ecosystem packages like pi-subagents and pi-mcp-adapter.

This skill acts as an advanced orchestration protocol for reviewing GitHub pull requests. It is stack-agnostic, meaning it does not enforce its own rules. Instead, it dynamically discovers the project's existing standards—such as the test runner, architectural conventions, and requirement specifications—before running six specialized subagents in parallel. It provides a comprehensive, context-aware review and summary directly on GitHub.