一键导入
improve-codebase-architecture
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
Use it to load and enforce domain glossary throughout the task.
Use when writing, editing, or restructuring a guide, reference page, or any content under the `docs/` directory.
Use this skill when adding, editing, or reorganizing translations in the main app.
Make changes to the UI Kit. Use this skill when you need to create new or update existing UI components, their themes, stories, or tests.
Verify code quality after making changes in this project. Use this skill whenever you've finished implementing a feature, fix, or refactor and need to run the verification pipeline.
| 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 |
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:
/codebase-design skill for the architecture vocabulary and its principles.
Use these terms exactly in every suggestion.CONTEXT.md gives names to good seams.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:
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.
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:
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."
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?"
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 /embroiderly-context skill to keep the domain model current as you go:
CONTEXT.md?
Add the term to CONTEXT.md.
Create the file lazily if it doesn't exist.CONTEXT.md right there./codebase-design skill and use its design-it-twice parallel sub-agent pattern.