Skip to content

JPeetz/agent-skills / skills/development/mattpocock-dev-workflows

mattpocock-dev-workflows

Verified

Use when you need Matt Pocock's engineering workflow patterns: spec synthesis, deep-module design, domain modeling, two-axis code review, or disciplined bug diagnosis. A meta-skill covering five complementary sub-patterns for real engineering — not vibe coding.

CHANGELOG.md

View on GitHub
# Changelog

## 1.0.0 (2026-09-07)

Initial release of the Matt Pocock Dev Workflows meta-skill.

### Added

- **to-spec**: Synthesize conversation into structured spec on issue tracker. Proof-tested against original mattpocock/skills v0.3.0.
  - Spec template with Problem, Solution, User Stories, Implementation Decisions, Testing Decisions, Out of Scope
  - Seam identification protocol (prefer existing seams, propose highest possible new ones)

- **codebase-design**: Deep modules vocabulary and design discipline.
  - Full glossary (module, interface, depth, seam, adapter, leverage, locality)
  - Deep vs shallow module comparison framework
  - Dependency classification (in-process, local-substitutable, remote-but-owned, true-external)
  - Seam discipline rules (one adapter = hypothetical, two = real)
  - Design It Twice parallel sub-agent pattern for alternative interface exploration
  - Replace-don't-layer testing strategy

- **domain-modeling**: Shared language building for project contexts.
  - CONTEXT.md format with _Avoid_ notation
  - ADR format (minimal: 1-3 sentences, context-decision-why)
  - Multi-context support via CONTEXT-MAP.md
  - Active discipline: challenge, sharpen, stress-test, cross-reference, update inline

- **code-review**: Two-axis review (Standards + Spec) via parallel sub-agents.
  - Fowler smell baseline (12 smells from Refactoring ch.3)
  - Fixed-point pinning via three-dot diff
  - Spec source identification protocol
  - Deliberate separation of axes to prevent one masking the other

- **diagnosing-bugs**: 6-phase disciplined debug loop.
  - Phase 1: feedback loop construction (10 techniques from failing tests to HITL)
  - Phase 2: reproduce + minimise (every remaining element load-bearing)
  - Phase 3: 3-5 falsifiable hypotheses before testing
  - Phase 4: instrument (one variable at a time, tagged debug logs)
  - Phase 5: fix + regression test (correct seam required)
  - Phase 6: cleanup checklist
  - Secret redaction discipline throughout
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 322kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall