Skill UI

This skill enables personal execution of implementation plans task-by-task in the current session without spawning subagents per task. It employs Test-Driven Development (TDD) for verification, tracks progress via a ledger, and resolves conflicts autonomously. Suitable for inline execution choices or when subagent tools are unavailable, it reduces context costs while ensuring quality through final review.

This skill executes implementation plans by assigning a dedicated sub-agent to each independent task. It ensures quality through task-specific reviews and a final branch review. It emphasizes continuous execution, autonomous decision-making, and isolated contexts to prevent context pollution, suitable for structured software development workflows.

Cavecrew provides three subagent presets—investigator, builder, and reviewer—that compress tool results into minimal structured output, reducing main-context usage. Ideal for code search, small edits, and diff reviews in long sessions.

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 a comprehensive maintenance orchestrator for the brooks-lint plugin repository. It executes a rigorous, sequential subagent pipeline—including authoring, evaluation, QA, trigger auditing, and release management. Use this when adding, editing, or updating skills to ensure all related components (manifests, README, CHANGELOG) are synchronized and adhere to strict quality gates throughout the development lifecycle.

Execute discrete, bounded coding, review, or verification tasks using the Codex CLI as an isolated subagent. This tool is ideal for tasks requiring explicit file ownership, such as isolated refactoring, feature implementation, or independent code verification, without relying on continuous conversational context. It runs in a safe sandbox environment.

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.

Orchestrates sequential subagent stages to maintain the brooks-lint plugin: author, eval, QA, trigger audit, and release, with PASS/FAIL gating and document sync checks.

This skill enables launching OpenAI's Codex CLI as an isolated subagent for bounded coding, review, or verification tasks. It runs non-interactively in a sandbox, streaming progress while keeping context separate. Ideal for parallel work, independent verification, and self-contained coding tasks with clear success criteria. Users must ensure authentication and handle file ownership explicitly.

Automates creation and verification of EGM-compliant README.md files across repository directory trees. Establishes architectural contracts for developers and AI assistants. Supports subagent delegation, safety gates for large trees, and verification command discovery for various programming languages including Node.js, Rust, Go, Python, and C/C++.