๐ŸŽฏ

wayfinder

๐ŸŽฏSkill

from mattpocock/skills

Installation

Vibe Index InstallInstalls to .claude/skills/
$npx vibeindex add mattpocock/skills --skill wayfinder
skills.sh Installโš  Installs to .agents/skills/
$npx skills add mattpocock/skills --skill wayfinder
Manual InstallCopy SKILL.md content and save to the path below
path
~/.claude/skills/wayfinder/SKILL.md
VibeIndex|
What it does
|

A skill from the mattpocock/skills collection that provides composable, model-agnostic engineering practices for AI coding agents, focusing on alignment, feedback loops, domain modeling, and codebase design.

Overview

Wayfinder is part of the mattpocock/skills collection, a set of composable engineering skills designed for AI coding agents like Claude Code and Codex. The collection addresses four core failure modes in AI-assisted development: misalignment between developer intent and agent output, excessive verbosity from agents lacking domain context, broken code due to missing feedback loops, and architectural decay from unchecked complexity. Each skill is small, model-agnostic, and designed to be adapted to any project.

Key Features

  • Grilling sessions (/grill-me, /grill-with-docs) that interview you about your plan before the agent starts coding, closing the communication gap between you and the AI
  • Shared language and domain modeling through CONTEXT.md and ADRs, reducing agent verbosity and ensuring consistent naming across the codebase
  • Test-driven development (/tdd) with red-green-refactor loops, plus a structured /diagnosing-bugs workflow for hard-to-find issues
  • Architecture improvement (/improve-codebase-architecture) that scans for deepening opportunities and generates visual HTML reports
  • Issue management with /triage for state-machine-based issue triage and /to-issues for breaking plans into vertical slices
  • PRD generation (/to-prd) and prototyping (/prototype) for planning and exploring design questions

Who is this for?

  • Software engineers using AI coding agents (Claude Code, Codex, or similar) who want structured workflows instead of ad-hoc prompting
  • Teams experiencing misalignment between what they ask for and what the agent builds, and want grilling-based alignment before coding starts
  • Developers who care about code quality and want to maintain clean architecture even while shipping at AI-accelerated speed
  • Anyone looking for composable, hackable skills they can adapt to their own workflow rather than an opinionated framework that takes over the process
๐Ÿ“ฆ

Same repository

mattpocock/skills(58 items)

wayfinder

SKILL.md

785,078Installs
AddedJul 2, 2026

More from this repository10

๐ŸŽฏ
grill-me๐ŸŽฏSkill

Interviews the user relentlessly about every aspect of a plan or design until reaching shared understanding, resolving each branch of the decision tree one by one. Provides recommended answers for each question and explores the codebase when answers can be found there.

๐ŸŽฏ
grill-with-docs๐ŸŽฏSkill

A skill that runs a grilling session to challenge your plan against an existing domain model, sharpen terminology by building a shared language in CONTEXT.md, and document architectural decisions in ADRs before coding begins.

๐ŸŽฏ
improve-codebase-architecture๐ŸŽฏSkill

An agent skill from Matt Pocock's engineering toolkit that helps improve your codebase architecture. Part of a composable skill set designed to fix common AI coding agent failure modes through structured, experience-based workflows.

๐ŸŽฏ
tdd๐ŸŽฏSkill

Enforces test-driven development with a strict red-green-refactor loop using vertical slices (one test then one implementation at a time), emphasizing behavior verification through public interfaces rather than implementation-coupled testing.

๐ŸŽฏ
setup-matt-pocock-skills๐ŸŽฏSkill

Initial setup skill for Matt Pocock's engineering skills collection that configures your backlog manager, triage labels, and documentation paths for AI coding agents.

๐ŸŽฏ
grilling๐ŸŽฏSkill

A model-invoked productivity skill that interviews users relentlessly about a plan or design until every branch of the decision tree is resolved. It serves as the reusable interview loop behind the grill-me and grill-with-docs skills.

๐ŸŽฏ
prototype๐ŸŽฏSkill

Composable, model-agnostic agent skills for real engineering workflows, featuring /grill-me for requirement alignment, /prototype for rapid iteration, and task management tools designed to fix common failure modes in AI coding agents.

๐ŸŽฏ
codebase-design๐ŸŽฏSkill

A model-invoked engineering skill that provides shared discipline and vocabulary for designing deep modules: maximizing behavior behind small interfaces, placing code at clean seams, and ensuring testability through public APIs.

๐ŸŽฏ
diagnosing-bugs๐ŸŽฏSkill

A model-invoked skill that guides coding agents through a disciplined diagnosis loop for hard bugs: reproduce, minimise, hypothesise, instrument, fix, and regression-test.

๐ŸŽฏ
handoff๐ŸŽฏSkill

A collection of small, composable engineering skills designed for real development workflows, featuring grilling sessions for requirement alignment, issue tracking integration, and task triage with customizable labels.