Menu
Route to the right Ix skill or command for your task
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Analyze system design — structure, coupling, code smells, and high-risk hotspots. Purely graph-based, no code reads.
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.
| name | ix-help |
| description | Route to the right Ix skill or command for your task |
| argument-hint | <task or question> |
Goal: route only. Do not perform the task. Always return an exact invocation the user can copy-paste.
If $ARGUMENTS is empty, return this menu:
| Skill | Use when |
|---|---|
/ix-understand <target> | You want an architectural mental model of a subsystem |
/ix-investigate <symbol> | You want a deep dive on one symbol or feature |
/ix-impact <target> | You want blast radius before editing a file or symbol |
/ix-plan <targets...> | You need a risk-ordered plan for a multi-file change |
/ix-debug <symptom> | You need root-cause analysis for a bug or failure |
/ix-architecture [scope] | You want a design health audit (smells, coupling, hotspots) |
/ix-docs <target> | You need onboarding or reference documentation |
For simple one-step lookups, use raw MCP tools directly:
ix_locate with { symbol: "X" }ix_callers with { symbol: "X", limit: 15 }ix_callees with { symbol: "X", limit: 15 }ix_imported_by with { symbol: "X" }ix_text with { pattern: "X", limit: 20 }ix_inventory with { kind: "file", path: "..." }If $ARGUMENTS is non-empty, classify the request and recommend exactly one starting point:
/ix-understand <target>/ix-investigate <target>/ix-impact <target>/ix-plan <targets>/ix-debug <symptom>/ix-architecture <scope>/ix-docs <target>Output format:
Best start: <one sentence>
Run: <exact skill invocation or tool call>
Why: <one short sentence>
If the request is ambiguous, make the safest routing choice and state what target placeholder to replace.