tobihagemann/turbo

Reusable workflows for planning, building, reviewing, and shipping with Claude Code and Codex.

What it solves

Turbo provides a repeatable, structured development process for AI coding agents (specifically Claude Code and Codex), preventing the need to manually rebuild complex prompts for common tasks like planning, debugging, and shipping code.

How it works

It packages development workflows as "Markdown skills" that can be invoked via specific commands (e.g., /turboplan or /finalize). These skills leverage the project's existing tests, linters, and formatters to guide an agent through a pipeline: planning a change, implementing it, and finalizing it for a pull request. It also includes a /self-improve feature to capture project-specific conventions and corrections for future sessions.

Who it’s for

Developers using AI coding agents like Claude Code or Codex who want to standardize their AI-assisted development cycle from idea to pull request.

Highlights

  • Repeatable Workflows: Standardizes planning, investigation, review, and shipping into reusable skills.
  • Modular Design: Individual skills can be used standalone or composed into larger pipelines.
  • $‚$Self-Improvement: Captures lessons and project conventions to improve agent performance over time.
  • Tool Integration: Works with the GitHub CLI and existing project infrastructure (tests, linters, hooks).

Related

  • Project
    mattpocock/skills

    A plug‑in library that adds disciplined engineering workflows (spec writing, TDD, architecture review, etc.) to AI coding agents like Claude, Codex, or Copilot via slash‑command skills.

  • Project
    AI-Builder-Club/skills

    A Claude Code plugin marketplace that enables the creation of "loop engineers"—autonomous agents that use a shared file-based memory and a codebase harness to perform and verify work independently.

  • Project
    coleam00/skills

    A library of 35 modular markdown-based skills and hooks for AI coding agents to standardize development workflows and reduce prompt bloat.

  • Project
    BuilderIO/skills

    A collection of composable skills and tools that extend AI agents with capabilities for visual planning, automated software delivery pipelines, and cost-efficient model orchestration.

  • Project
    EveryInc/compound-engineering-plugin

    Compound Engineering is a plugin that adds 36 AI‑agent skills for a structured “brainstorm → plan → work → simplify → review → compound” development loop. It runs on many coding agents (Claude Code, Cursor, Codex, Grok, etc.), automatically records learnings after each change, and can execute the whole pipeline hands‑off with the `lfg` skill. Installation is a one‑liner per host, and the README provides full docs, philosophy, and example commands.