prototype
🎯Skillfrom mattpocock/skills
Installation
npx vibeindex add mattpocock/skills --skill prototypenpx skills add mattpocock/skills --skill prototype~/.claude/skills/prototype/SKILL.md
|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.
Overview
The prototype skill is part of Matt Pocock's "Skills For Real Engineers" collection, designed to fix the common failure mode where AI agents build polished code before the requirements are aligned. Instead of jumping to a final implementation, /prototype drives rapid, throwaway iterations so you and the agent converge on the right solution before committing to production-quality code.
Key Features
- Rapid iteration loop: Produces quick, minimal implementations to validate ideas before investing in production code
- Pairs with /grill-me: Use /grill-me or /grill-with-docs to align requirements first, then /prototype to validate the solution shape through fast cycles
- Composable workflow: Fits into the broader skill set alongside /triage (ticket categorization), /handoff (session context transfer), and /plan (implementation planning)
- Model-agnostic: Works with Claude Code, Codex, and other compatible coding agents
- Easy setup: Install via
npx skills@latest add mattpocock/skillsand run /setup-matt-pocock-skills for one-time configuration of your issue tracker and labels
Who is this for?
- Engineers who want to explore multiple solution approaches quickly before committing to one
- Teams building complex features where the right architecture is not obvious upfront
- Developers who have been burned by AI agents producing "finished" code that misses the actual requirement
Same repository
mattpocock/skills(55 items)
SKILL.md
More from this repository10
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.
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.
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.
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.
Initial setup skill for Matt Pocock's engineering skills collection that configures your backlog manager, triage labels, and documentation paths for AI coding agents.
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.
A composable skill for triaging issues and tickets using configurable labels, designed to fix common failure modes in AI coding agents by providing structured backlog management workflows.
A collection of composable engineering skills by Matt Pocock designed to fix common AI coding agent failure modes: misalignment via grilling sessions, verbosity through shared domain language (CONTEXT.md), code quality with TDD red-green-refactor loops, and codebase entropy with architecture improvement workflows.
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.
A model-invoked engineering skill that actively builds and sharpens a project's domain model by challenging terms against the glossary, stress-testing with edge-case scenarios, and updating CONTEXT.md and ADRs inline.