tt-a1i/matt-skills-with-to-goal

Generates a concise handoff document from the current conversation, including suggested skills, so another AI agent can seamlessly continue the work. Saves to temporary directory and redacts sensitive data.

A router that helps determine which skill or workflow to use for a given task. Use when you need guidance picking the right tool from a suite of AI agent skills.

Ask Matt routes you to the right skill or flow for your situation. Use it when you need help choosing between planning, implementation, debugging, or review paths.

Claude Handoff writes a concise handoff summary and starts a fresh background agent with that prompt so work can continue immediately. Use it when you need to pass an active task to another agent without saving a file.

Reviews code changes since a fixed point along two independent axes: coding standards compliance and spec/issue fidelity. Runs both reviews in parallel sub-agents and reports findings side by side. Ideal for reviewing branches, PRs, or work-in-progress changes.

Code Review reviews changes since a fixed point along Standards and Spec axes. Use it for branch, PR, or work-in-progress reviews, including requests to review since a given commit or tag.

A shared vocabulary and principles for designing deep, testable modules with small interfaces and high leverage. Use when designing or improving module interfaces, deciding where to place seams, or making code more maintainable and AI-navigable.

Guides systematic debugging of hard bugs and performance regressions through building a tight feedback loop, reproducing, minimizing, hypothesizing, and instrumenting. Use when encountering difficult or flaky bugs.

Diagnosing Bugs helps you build tight repro loops for hard bugs, failures, and performance regressions. Use it when debugging broken, throwing, failing, or slow behavior and you need to isolate the cause.

Execute Spec In Fork orchestrates one approved SPEC READY through a same-directory Codex App fork, runs spec-executor, validates the receipt, and archives the child when complete. Use it for explicit spec execution or to handle messenger replies and recovery events for that fork.

Goal Crafter turns vague tasks into verifiable goal prompts for AI coding agents like Claude Code, Codex Automations, and Pi. It is used when you need a self-running task with clear completion criteria and constraints.

Craft verifiable goal prompts for AI coding agents like Claude Code, Codex, or Pi. Turns vague tasks into precise goals with checkable completion criteria, ensuring agents run unattended.

A relentless interview session to sharpen your project plan or design through tough questioning and feedback.

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Grills the user relentlessly about a plan, decision, or idea to stress-test their thinking. Use when the user wants to explore every aspect or uses any 'grill' trigger phrases.

Implement a piece of work based on a spec or set of tickets, using test-driven development, typechecking, and code review before committing.

Improve Codebase Architecture scans a codebase for shallow modules and deepening opportunities, then generates an HTML report of candidates. It is used to find refactors that improve locality, testability, and AI navigability before drilling into one choice.

Scans a codebase for architectural friction, identifies shallow modules, and presents deepening opportunities as an interactive HTML report. Guides refactoring through a decision-tree grilling process, improving testability and AI-navigability.

Loop Me grills you about the workflows you want to build and turns the answers into workflow specs in this workspace. Use it when you want to define recurring loops, triggers, checkpoints, and briefs before implementation.

Prototype builds throwaway code to answer a design question. Use it to sanity-check state logic or explore what a UI should look like, with the prototype kept close to the code it is testing.

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

Resolves in-progress git merge or rebase conflicts by identifying primary sources, preserving intent, and running automated checks. Use when you need to finish a merge or rebase without aborting.

Setup Matt Pocock Skills configures a repository for the engineering skills by setting the issue tracker, triage labels, and domain doc layout. Use it once before running the other engineering skills.

Configures a project's issue tracker, triage labels, and domain documentation layout for Matt Pocock's engineering skills suite. Run once before using other skills like triage or to-tickets.

Setup Ts Deep Modules wires dependency-cruiser into a TypeScript repo to enforce deep modules. It limits imports to package entry points, blocks subfolder access and cycles, and adds a starter example package.

Spec Executor implements one approved spec in a forked execution thread and returns a structured receipt. Use it when a final SPEC READY block is approved and the work fits one implementation session.

Enables an AI agent to teach you a skill or concept through a structured workspace with interactive HTML lessons, reference materials, and learning records, emphasizing long-term retention and practical application.

Test-Driven Development guides red-green-refactor cycles for writing tests before implementation. Use it when building features or fixing bugs test-first, choosing seams, or adding integration tests.

Guides test-driven development for AI coding agents, ensuring tests are spec-like, seams are confirmed, and the red-green loop produces maintainable tests. Use when building features or fixing bugs test-first.

Turn approved specs and tickets into a verifiable execution goal without re-interviewing the user. Gathers evidence, selects scope, and drafts goals for coding agent sessions.

To Spec turns the current conversation and codebase context into a project issue spec. It publishes the spec, applies the ready-for-agent label, and avoids interviewing the user.

Synthesizes the current conversation and codebase context into a spec (PRD) and publishes it to the project issue tracker with appropriate labels.

To Tickets breaks a plan, spec, or conversation into tracer-bullet tickets with explicit blocking edges. Use it when you need to publish a staged set of implementation tickets to a tracker or local issue files.

Breaks a plan, spec, or conversation into tracer-bullet tickets with blocking edge declarations, published to an issue tracker.

Triage moves issues and external pull requests through category and state labels, verifies claims, and writes agent-ready briefs. It is used when a maintainer wants to sort, confirm, or route incoming work.

Moves issues and external pull requests through triage states and roles. Use it to classify, verify, and prepare items with agent-ready or human-ready briefs.

Wayfinder plans large efforts as a shared map of decision tickets on an issue tracker, then resolves them one at a time until the route to the destination is clear. Use it when the work is too big for one agent session and needs decisions before execution.

Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

Wizard generates an interactive bash script that guides a human through manual setup steps, migrations, or secret entry. Use it when the agent needs a person to click, copy, confirm, or enter values it cannot perform itself.

Reference for writing and editing skills so they behave predictably. Use it when defining skill descriptions, structure, disclosure, or pruning rules.