improve-codebase-architecture
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
- License 许可
- MIT
- 最近更新
- 2026-07-05
- Stars
- ★ 7
- Forks
- 0
01 前言 Front Matter
- name
- improve-codebase-architecture
- description
- Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
- disable-model-invocation
- true
02 资源文件 2
- 参考文档HTML-REPORT.md6.5 KB
- 参考文档README.md2.2 KB
03 SKILL.md 正文
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:
- Run the
/codebase-designskill 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 — don't drift into "component," "service," "API," or "boundary." - The domain language in
CONTEXT.mdgives names to good seams; ADRs indocs/adr/record decisions this command should not re-litigate.
Process
1. Explore
Read the project's domain glossary (CONTEXT.md) and any ADRs in the area you're touching first.
Then use the Agent tool with subagent_type=Explore 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 — 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, run the /grilling skill to walk the design 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 — run the /domain-modeling skill to keep the domain model current as you go:
- Naming a deepened module after a concept not in
CONTEXT.md? Add the term toCONTEXT.md. Create the file lazily if it doesn't exist. - Sharpening a fuzzy term during the conversation? Update
CONTEXT.mdright 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? Run the
/codebase-designskill and use its design-it-twice parallel sub-agent pattern.
04 同仓库更多 Skills
static-project-gallery-upload
Use when a user provides project/portfolio/gallery images for a static website and wants them displayed on the site, exact duplicate images removed, visually related building views kept together, images optimized, and a host upload folder such as "UP FILE" prepared. Triggers include Persian requests like "عکس پروژه ها", "تکراری نباشن", "توی سایت نمایش داده بشن", "فایل های هاست", "UP FILE".
contact-location-section
暂无简介
azerbaijan-website-build
Build premium tri-lingual websites from scratch for Azerbaijani businesses. Handles data gathering (website scrape, social media, or interview), brand development, and full Astro + Tailwind build with AZ/RU/EN language support.
local-business-rebuild
Build a stunning new website for a local business prospect. Adapted from the full website-rebuild skill but optimized for speculative local business pitches. 10-phase process: brand extraction, SEO audit, design audit, rebuild plan, full build with design system, copy optimization, combined QA, pre-deploy checklist, and output to monorepo. Uses scraped content from prospect-scrape as input. No tools/calculator research phase. Single combined QA round. Triggers on: "rebuild prospect", "local business rebuild", "build prospect site", "rebuild their site", "prospect rebuild", or any request to build a new website for a qualified prospect.
website-rebuild
Full website rebuild agent. Takes an existing website URL and rebuilds it from scratch into a world-class, SEO-optimized, WCAG AA accessible, visually stunning website using Astro + Tailwind CSS, deployed to Vercel via GitHub. Executes a rigorous 14-phase process: brand extraction, content scraping, SEO audit, design audit, rebuild planning, full build with design system, copy optimization, 3 QA rounds, competitive tools research, tools build, tools QA, pre-deploy checklist, and Vercel deployment. Produces 11+ documentation deliverables. Triggers on: "rebuild website", "redesign website", "rebuild site from URL", "website rebuild", "redo this website", "make this website better", "rebuild from scratch", "full site redesign", or any request to take an existing URL and create a new, professional website from it. Also triggers when the user provides a URL and asks to build/create/design a new version of that site.
triage
Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.