Catalog
mattpocock/improve-codebase-architecture

mattpocock

improve-codebase-architecture

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

NewUpdated Sep 9, 2026

Improve Codebase Architecture

Surface architectural friction and propose deepening opportunities: refactors that turn shallow modules into deep ones. The aim is testability and AI-navigability.

This command is informed by the project's domain model and built on a shared design vocabulary:

  • Call the Skill tool with "codebase-design" for the architecture vocabulary (module, interface, depth, seam, adapter, leverage, locality) and its principles (the deletion test, "the interface is the test surface", "one adapter = hypothetical seam, two = real"). Use these terms exactly in every suggestion, and don't drift into "component," "service," "API," or "boundary."
  • The domain language in CONTEXT.md gives names to good seams; ADRs in docs/adr/ record decisions this command should not re-litigate.

Process

1. Explore

Scope before you scan: YAGNI. Deepening a module pays off by making future changes to it easier, so put extra weight on the parts of the codebase that have recently changed. Decide where to look before you look:

  • If the user named a direction (a module, a subsystem, a pain point), take it, and skip the inference below.
  • Otherwise, walk back a good stretch of the commit history (git log --oneline) to find the codebase's hot spots, the files and areas that keep coming up, and let those paths pull your attention first. If the changes are scattered with no clear hot spot, widen the net.

Read the project's domain glossary (CONTEXT.md) and any ADRs in the area you're touching first.

Then spawn a sub-agent to walk the codebase. Don't follow rigid heuristics; explore organically and note where you experience friction:

  • Where does understanding one concept require bouncing between many small modules?
  • Where are modules shallow, with an interface nearly as complex as the implementation?
  • Where have pure functions been extracted just for testability, but the real bugs hide in how they're called (no locality)?
  • Where do tightly-coupled modules leak across their seams?
  • Which parts of the codebase are untested, or hard to test through their current interface?

Apply the deletion test to anything you suspect is shallow: would deleting it concentrate complexity, or just move it? A "yes, concentrates" is the signal you want.

2. Present candidates as an HTML report

Write a self-contained HTML file to the OS temp directory so nothing lands in the repo. Resolve the temp dir from $TMPDIR, falling back to /tmp (or %TEMP% on Windows), and write to <tmpdir>/architecture-review-<timestamp>.html so each run gets a fresh file. Open it for the user (xdg-open <path> on Linux, open <path> on macOS, start <path> on Windows) and tell them the absolute path.

The report uses Tailwind via CDN for layout and styling, and Mermaid via CDN for diagrams where a graph/flow/sequence reliably communicates the structure. Mix Mermaid with hand-crafted CSS/SVG visuals: use Mermaid when relationships are graph-shaped (call graphs, dependencies, sequences), and hand-built divs/SVG when you want something more editorial (mass diagrams, cross-sections, collapse animations). Each candidate gets a before/after visualisation. Be visual.

For each candidate, render a card with:

  • Files: which files/modules are involved
  • Problem: why the current architecture is causing friction
  • Solution: plain English description of what would change
  • Benefits: explained in terms of locality and leverage, and how tests would improve
  • Before / After diagram: side-by-side, custom-drawn, illustrating the shallowness and the deepening
  • Recommendation strength: one of Strong, Worth exploring, Speculative, rendered as a badge

End the report with a Top recommendation section: which candidate you'd tackle first and why.

Use CONTEXT.md vocabulary for the domain, and the /codebase-design vocabulary for the architecture. If CONTEXT.md defines "Order," talk about "the Order intake module," not "the FooBarHandler," and not "the Order service."

ADR conflicts: if a candidate contradicts an existing ADR, only surface it when the friction is real enough to warrant revisiting the ADR. Mark it clearly in the card (e.g. a warning callout: "contradicts ADR-0007, but worth reopening because…"). Don't list every theoretical refactor an ADR forbids.

See HTML-REPORT.md for the full HTML scaffold, diagram patterns, and styling guidance.

Do NOT propose interfaces yet. After the file is written, ask the user: "Which of these would you like to explore?"

3. Grilling loop

Once the user picks a candidate, call the Skill tool with "grilling" to walk the decision tree with them: constraints, dependencies, the shape of the deepened module, what sits behind the seam, what tests survive.

Side effects happen inline as decisions crystallize; call the Skill tool with "domain-modeling" to keep the domain model current as you go:

  • Naming a deepened module after a concept not in CONTEXT.md? Add the term to CONTEXT.md. Create the file lazily if it doesn't exist.
  • Sharpening a fuzzy term during the conversation? Update CONTEXT.md right there.
  • User rejects the candidate with a load-bearing reason? Offer an ADR, framed as: "Want me to record this as an ADR so future architecture reviews don't re-suggest it?" Only offer when the reason would actually be needed by a future explorer to avoid re-suggesting the same thing; skip ephemeral reasons ("not worth it right now") and self-evident ones.
  • Want to explore alternative interfaces for the deepened module? Call the Skill tool with "codebase-design" and use its design-it-twice parallel sub-agent pattern.
Files3
3 files · 7.7 KB

Select a file to preview

Overall Score

82/100

Grade

B

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

82

Quality

85

Clarity

86

Completeness

75

Summary

This skill guides an AI agent to scan a codebase for architectural deepening opportunities, present findings as a visual HTML report with Tailwind and Mermaid diagrams, then interactively explore selected candidates. The skill applies sophisticated domain modeling (calling out to "codebase-design" and "grilling" sub-agents) and updates project context files (CONTEXT.md, ADRs) as decisions crystallize.

Detected Capabilities

codebase traversal and analysisgit log readingfile system read (CONTEXT.md, ADRs, project files)file system write (HTML report to temp directory)file write to project files (CONTEXT.md, ADRs)sub-agent invocation via Skill toolHTML/CSS/SVG generationexternal CDN references (Tailwind, Mermaid)

Trigger Keywords

Phrases that agents use to match this skill to user intent.

codebase architecture reviewdeepen shallow modulesrefactoring opportunitiesarchitectural frictiondomain-driven designmodule shallownesstestability seams

Risk Signals

INFO

External CDN references (cdn.tailwindcss.com, cdn.jsdelivr.net) for Tailwind and Mermaid JavaScript

SKILL.md, lines 78, 82 and HTML-REPORT.md scaffold
INFO

File writes to project directory (CONTEXT.md, docs/adr/*.md)

SKILL.md, lines 105-109
INFO

Temp directory file write for HTML report

SKILL.md, lines 69-71
INFO

Sub-agent invocation via Skill tool (domain-modeling, grilling, codebase-design)

SKILL.md, lines 96-115

Referenced Domains

External domains referenced in skill content, detected by static analysis.

cdn.jsdelivr.netcdn.tailwindcss.com

Use Cases

  • Identify architectural refactoring candidates in complex codebases
  • Surface shallow modules causing testing friction and cognitive overhead
  • Create visual architecture review reports for team discussion
  • Guide interactive deepening decisions with architectural vocabulary
  • Keep architecture ADRs and domain glossary current during refactoring conversations

Quality Notes

  • Excellent domain vocabulary enforcement: skill explicitly instructs agent to use exact terms from codebase-design glossary and CONTEXT.md, never drifting into synonyms like 'component' or 'service'
  • Strong scope boundaries: YAGNI principle applied upfront, git log analysis focuses on hot spots, deletion test provides clear selection heuristic
  • Comprehensive HTML report guidance: HTML-REPORT.md provides detailed scaffold, diagram patterns (Mermaid vs hand-built), style rules, and tone consistency
  • Clear decision tree: 3-phase process (Explore, Present, Grill) with explicit checkpoints and sub-agent hand-offs
  • ADR integration thoughtfully scoped: surface contradictions only when friction is real, offer ADR recording only for permanent reasons, not ephemeral ones
  • Excellent tone enforcement in HTML-REPORT.md: specific phrasings that fit style, examples of correct/incorrect terminology, emphasis on sparse prose and diagram-driven communication
  • Assumes agent familiarity with Skill tool sub-agent pattern and project structure (CONTEXT.md, docs/adr/)
  • No error handling guidance: what if CONTEXT.md is missing? What if git log is empty? What if HTML write fails?
Model: claude-haiku-4-5-20251001Analyzed: Sep 9, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

  1. v2.1

    Content updated

    ✦ AIAdds scoping guidance (YAGNI analysis of commit history before exploration), changes Agent tool reference to generic sub-agent spawn, and refines wording throughout.

    2026-09-09

    LATEST
  2. v2.0

    Contract changed: description

    ✦ AIChanges activation contract: now outputs visual HTML report and delegates domain vocabulary to a separate skill.

    triggering2026-06-28

    View This Version
  3. v1.0

    2026-05-02

    View This VersionInitial version

Use mattpocock/improve-codebase-architecture in your dev environment

Command Palette

Search for a command to run...