Menü
Route to the right Ix skill or tool for the current task. Route only; do not perform the task.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
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 tool for the current task. Route only; do not perform the task. |
| metadata | {"openclaw":{"requires":{"bins":["ix"]}}} |
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:
Skills (slash commands):
/ix-understand <target> — architectural mental model of a repo, subsystem, or file/ix-investigate <symbol> — deep dive on one symbol, class, or feature/ix-impact <target> — blast radius and risk before editing/ix-plan <targets...> — risk-ordered multi-file change plan/ix-debug <symptom> — root-cause analysis for a bug or failure/ix-architecture [scope] — design health, coupling, and structural smells/ix-docs <target> — onboarding or reference documentationDirect tool calls (for quick lookups):
ix-query — look up a symbol by exact nameix-locate — search by text pattern or keywordix-explain — full role, importance, and caller details for a symbolix-neighbors — callers, callees, and dependenciesix-impact — blast radius for a file or symbolix-trace — full execution path traceix-rank — top symbols by dependents, callers, or membersix-subsystems — all subsystems with file counts and hierarchyix-inventory — enumerate files or symbols in a path scopeix-stats — graph-wide statistics and healthix-smells — architecture smell detectionix-map — architectural overview with subsystem tableix-ingest — graph status and refresh triggerix-decide — pre-edit policy verdict (ALLOW / REVIEW / BLOCK)ix-health — CLI and graph availability checkIf $ARGUMENTS is non-empty, classify the request and recommend exactly one best starting point:
Architecture, onboarding, "how does X work", system overview:
/ix-understand <target>
Symbol deep dive, "what does X do", feature internals, implementation details:
/ix-investigate <target>
Pre-edit risk, blast radius, "what breaks if I change X":
/ix-impact <target>
Multi-file change, refactor, migration, implementation plan:
/ix-plan <targets or change description>
Bug, failure, regression, unexpected behavior, error message:
/ix-debug <symptom>
Design quality, complexity, coupling, smells, architecture health:
/ix-architecture <scope>
Documentation, onboarding guide, reference docs:
/ix-docs <target>
Simple lookup requests (use tools directly, not skills):
ix-query with symbol: "X"ix-locate with pattern: "X"ix-neighbors with symbol: "X", direction: "callers"ix-neighbors with symbol: "X", direction: "callees"ix-trace with symbol: "X"ix-inventory with path: "src/...", kind: "file"ix-rank with by: "dependents"ix-smellsix-healthOutput format:
Best start: <one sentence>
Run: <exact slash command or tool call>
Why: <one short sentence>
If the request is ambiguous, make the safest routing choice and note what target placeholder to replace.