writing-shape
๐ฏSkillfrom mattpocock/skills
|A composable engineering skill by Matt Pocock designed to fix common AI coding agent failure modes, featuring grilling sessions for alignment, documentation-driven development, and practical workflows based on decades of engineering experience.
Overview
writing-shape is a composable writing skill from Matt Pocock's "Skills For Real Engineers" collection that guides AI coding agents to structure written output with a clear overall shape and narrative arc. Part of a toolkit designed to fix common agent failure modes, this skill addresses the tendency of AI agents to produce flat, unstructured text by enforcing deliberate organization patterns. It works with any model and integrates with the broader skills ecosystem through the skills.sh installer.
Key Features
- Shape-driven writing structure that ensures AI agent output follows a coherent narrative arc rather than producing flat, stream-of-consciousness text
- Integration with grilling sessions (/grill-me, /grill-with-docs) to align on the desired shape and structure before writing begins
- Documentation-first approach that leverages CONTEXT.md and ADRs to maintain consistent terminology and reduce agent verbosity by up to 75%
- Composable with other skills including TDD, diagnose, and architecture improvement skills for a complete engineering workflow
- Quick installation via
npx skills@latest add mattpocock/skillswith support for Claude Code, Codex, and other coding agents
Who is this for?
- Engineers who need AI agents to produce well-structured documentation, PRDs, or technical writing with clear organization
- Developers frustrated with AI-generated text that lacks coherent flow and want a repeatable approach to shaping agent output
- Teams using AI-assisted development who want to maintain high writing quality standards across agent-generated content
Same repository
mattpocock/skills(55 items)
Installation
npx vibeindex add mattpocock/skills --skill writing-shapenpx skills add mattpocock/skills --skill writing-shape~/.claude/skills/writing-shape/SKILL.mdSKILL.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 skill that turns the current conversation context and codebase understanding into a structured PRD (Product Requirements Document) and submits it as a GitHub issue, with modular architecture and user story generation.
Breaks a plan, spec, or PRD into independently-grabbable GitHub issues using tracer-bullet vertical slices. Each issue is a thin end-to-end path through every integration layer that can be demoed or verified on its own.
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.