Tobias Hagemann

Iteratively refine planning artifacts until no new findings emerge.

Commit, push, and manage pull requests for staged changes with ease.

Engage in multi-turn consultations with Codex CLI for collaborative problem-solving.

Automate code reviews for reuse, quality, efficiency, and clarity, followed by fixes.

Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build landing pages, websites, dashboards, web components, or any frontend UI. Generates creative, polished code that avoids generic AI aesthetics.

Run autonomous tasks using the codex CLI for efficient execution.

Streamline your pull request reviews with automated fetching and evaluation of comments and code.

Systematically investigate bugs and failures using a structured methodology.

Facilitate collaborative discussions to create detailed project specifications.

Run an independent peer review via codex. Use when the user asks to "peer review", "peer review my code", "peer review my plan", "peer review my spec", "peer review my shells", "get a second opinion", or "independent review".

Streamline your post-implementation quality assurance workflow with ease.

Enforce consistency in new code by mirroring existing styles and patterns.

Recall the reasoning behind past code changes by locating relevant transcripts.

Defines shared conventions for changelogs to ensure consistency and clarity.

Stage files and create a commit in one step with a consistent message style.

Streamline your improvement process by validating and implementing changes from your backlog.

Establishes writing style rules for GitHub outputs, differentiating between insider and outsider voices.

Project-wide health audit pipeline that fans out to all analysis skills in parallel, evaluates findings, and produces a unified report at .turbo/audit.md. Use when the user asks to "audit the project", "run a full audit", "project health check", "audit my code", "codebase audit", or "comprehensive review".

Analyze task complexity and determine the appropriate execution mode for project planning.

Create a GitHub pull request with a drafted title and description.

Fetch and summarize unresolved GitHub PR review comments without making changes.

Establishes shared commit message rules and technical constraints for Git operations.

Commit already-staged changes and push in one step.

Expand a shell into a comprehensive implementation plan with verification and concrete references.

Draft and post conversational replies to GitHub PR comments in one go.

Analyze and audit dev tooling infrastructure for projects, identifying gaps in essential tools.

Critically assess external feedback and decide which suggestions to apply using adversarial verification.

Automate the selection and planning of the next shell in your project workflow.

Consult ChatGPT Pro for complex problem-solving using browser automation.

Run AI-powered code reviews effortlessly using the codex CLI.

Turbo is a modular collection of skills for streamlining the development process with Claude Code.

Perform thorough, multi-level testing to identify bugs and ensure app functionality.

Automatically create a CHANGELOG.md with version history from GitHub releases or git tags.

Manually verify that an application works by interacting with it through a smoke test.

Generate structured test plans based on code changes to ensure comprehensive testing coverage.

Migrate legacy TurboPlan files to the current layout, ensuring proper frontmatter and organization.

Detect outdated or vulnerable dependencies across multiple package managers.

Automate the process of polishing code through staging, formatting, linting, testing, and reviewing until stable.

Review code for bugs, security vulnerabilities, API misuse, consistency issues, simplicity problems, or test coverage gaps by running internal reviews and a peer review in parallel and returning combined findings. Single-concern with a type argument, or full review with no argument. Use when the user asks to "review my code", "full code review", "review my changes", "check for bugs", "scan for bugs", "review correctness", "security audit", "find vulnerabilities", "review security", "check API usage", "verify against docs", "check for cross-file duplication", "review consistency", "check for code reuse", "review simplicity", "find untested code", or "review test coverage".

Choose an implementation path for evaluated findings and dispatch it efficiently.

Identify and analyze dead code in your codebase, focusing on production usage.

Execute implementation plans efficiently by loading task-specific skills and managing execution steps.

Fetch and rank open GitHub issues by community engagement to prioritize your work.

Automatically update the Unreleased section of CHANGELOG.md based on current changes.

Generate comprehensive architecture reports by inspecting various aspects of a codebase.

Draft an implementation plan quickly and efficiently.

Automatically update GitHub pull request titles and descriptions based on branch changes.

Capture out-of-scope improvement opportunities to ensure they aren't forgotten.

Decompose specification files into structured shells for implementation.

Draft and post replies to GitHub PR review threads efficiently.

Developer onboarding guide that composes architecture mapping, tooling review, and agentic setup review with setup, troubleshooting, and next-steps agents to produce a comprehensive guide at .turbo/onboarding.md and .turbo/onboarding.html. Use when the user asks to "onboard me", "onboard to this project", "generate onboarding guide", "new developer guide", "how do I get started", or "help me ramp up".

Submit improvements to turbo skills back to the upstream repository efficiently.

Execute a split plan by creating separate branches, commits, and PRs for each change group.

Review agentic coding infrastructure in a project for AI readiness.

Commit already-staged changes with a consistent message style.

Generates project-specific skills by scanning codebases for inferred conventions.

Quickly implement code changes without a predefined plan or backlog.

Translate complex concepts into plain language for better understanding.

Survey the codebase for existing patterns and reusable utilities without writing code.

Upgrade project dependencies while researching breaking changes for major updates.

Generate a structured threat model for a codebase, detailing assets, attack surfaces, and risks.

Easily update installed Turbo skills with dynamic changelog and conflict resolution.

Interpret third-party feedback to clarify intent and correctness concerns through parallel analysis.

Automatically generate answers to reviewer questions on pull requests.

Extract lessons from sessions and route them to the appropriate knowledge layer.

Stage specific implementation changes for commit with precise file selection.

Conduct thorough exploratory testing to identify bugs and validate application functionality.

Stage files, create a commit, and push in one step.

Create or update skills that enhance Claude's capabilities with specialized knowledge and workflows.

Automatically evaluate and respond to GitHub pull request review comments.

Apply code changes based on evaluated findings to improve code quality.

Review planning artifacts by running internal and peer reviews in parallel.