ix-architecture
Analyze system design — structure, coupling, code smells, and high-risk hotspots. Purely graph-based, no code reads.
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
Analyze system design — structure, coupling, code smells, and high-risk hotspots. Purely graph-based, no code reads.
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。
Route to the right Ix skill or command for your task
Root cause analysis — trace execution path to a failure, narrow candidates, read minimal source only at suspected failure points.
Generate narrative-first, importance-weighted documentation for a repo, system, or subsystem with a selective reference layer. Use --full for deeper module/class/method coverage.
Change risk analysis — blast radius, affected systems, and what to test. Depth scales with risk level; low-risk targets stop early.
Deep dive into a symbol, feature, or bug. Graph-first, minimal code reads, early stopping when sufficient evidence found.
Generate a risk-ordered implementation plan for a set of targets. Assesses blast radius per target, finds data flows between them, and produces a safe change sequence.
基于 SOC 职业分类
| name | ix-architecture |
| description | Analyze system design — structure, coupling, code smells, and high-risk hotspots. Purely graph-based, no code reads. |
Answer: how healthy is this system's design, where are the weak boundaries, and what should be improved? Never reads source code.
If the Ix runtime is unavailable, ix_status will report this; this skill cannot proceed without the graph.
For most cases:
ix_query({ mode: "architecture", targets: [$ARGUMENTS] })
Use the returned preview_markdown as the primary analysis. Supplement below for deeper investigation.
Call in parallel:
ix_subsystems() — region hierarchy, cohesion scores, external coupling, crosscut scoresIf $ARGUMENTS is provided, also call:
ix_inventory({ kind: "file", path: $ARGUMENTS }) — file composition of the targetExtract: region hierarchy, cohesion scores, external coupling, crosscut scores, confidence.
Call: ix_smells()
If $ARGUMENTS is scoped: ix_smells({ path: $ARGUMENTS })
Classify each finding: orphan / god-module / weak-component.
Call in parallel:
ix_rank({ by: "dependents", kind: "class", top: 10 })ix_rank({ by: "dependents", kind: "function", top: 10 })Correlate: are the most-depended-on entities also in poorly-bounded subsystems?
## Architecture Analysis
### System Structure
[Region hierarchy with file counts. Flag: low-confidence boundaries, high-coupling regions, cross-cutting modules.]
### Health Scores
| Region | Cohesion | Ext. Coupling | Boundary Ratio | Flag |
|--------|----------|---------------|----------------|------|
| [name] | [0-1] | [0-1] | [ratio] | [warning if bad] |
### Code Smells
**High severity:** ...
**Medium severity:** ...
### Hotspots
[Top components where structural debt + centrality combine]
### Improvement Areas
1. [specific issue] — [concrete suggestion]
### What's healthy
[Briefly note well-structured areas]
Every number must come directly from tool output.