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
- 所属仓库
- JoseArron/skills
- 最近更新
- 2026-10-11
- Stars
- ★ 2
- 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agents/openai.yaml166 B
- 参考文档HTML-REPORT.md6.5 KB
03 SKILL.md 正文
Before applying another skill below, load it through the Skill tool when available; otherwise read its SKILL.md. A skill name alone does not load its instructions.
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
{agentRoot}/GLOSSARY.mdgives names to good seams; ADRs in{agentRoot}/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 ({agentRoot}/GLOSSARY.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 GLOSSARY.md vocabulary for the domain, and the /codebase-design vocabulary for the architecture. If {agentRoot}/GLOSSARY.md defines "Order," talk about "the Order intake module," rather than "the FooBarHandler" or "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, load the grilling skill through the Skill tool when available, or read its SKILL.md 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; load the domain-modeling skill through the Skill tool when available, or read its SKILL.md to keep the domain model current as you go:
- Naming a deepened module after a concept not in
GLOSSARY.md? Add the term to{agentRoot}/GLOSSARY.md. Create the file lazily if it doesn't exist. - Sharpening a fuzzy term during the conversation? Update
{agentRoot}/GLOSSARY.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
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
resync-upstream-skills
Resync a selectively derived skills repository with its recorded upstream sources. Use when the user wants to pull upstream skill releases, reconcile renamed or changed skills, refresh third-party attribution, or audit whether local adaptations have drifted.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
ux-review
Evaluate a built screen or flow against UX heuristics and report what to fix — each finding with a severity and a concrete fix. Use to review or audit a UI's usability, before shipping a flow, or to turn "this feels off" into specific, rankable problems. The UX counterpart to /code-review.
ux-flows
Design and implement app screens and user flows with calm, user-first UX — obvious CTAs, feedback at the point of action, thumb-zone layout, and domain-modularized components. Use when the user asks to build or polish UI/UX, design a user flow, make a screen "feel" right, or mentions effortless/calm design, confirmations, error states, or empty states.