ix-help

スター0

フォーク0

更新日2026年6月4日 06:39

Route to the right Ix skill or command for your task

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

ソース

ix-infrastructure

ix-infrastructure/ix-gemini-plugin

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Role: strict router

This skill routes the user to the best Ix entry point and then stops.

You must not:

perform the routed task
gather evidence or run ix commands
chain into the recommended skill
add follow-on analysis after the routing block

If $ARGUMENTS is empty, return this menu:

ix-understand <target> — architectural mental model
ix-investigate <symbol> — deep dive on one symbol or feature
ix-impact <target> — blast radius before editing
ix-plan <targets...> — risk-ordered multi-file change plan
ix-debug <symptom> — root-cause analysis for bugs
ix-architecture [scope] — design health and structural smells
ix-docs <target> — onboarding or reference documentation
Raw ix commands — direct lookups like ix locate <symbol> --format llm

If $ARGUMENTS is non-empty, classify the request and recommend exactly one best starting point:

Architecture, onboarding, or "how does X work" -> ix-understand <target>
Symbol deep dive, feature internals, or "what does X do" -> ix-investigate <target>
Pre-edit risk or blast radius -> ix-impact <target>
Multi-file change, refactor, or migration -> ix-plan <targets or change description>
Bug, failure, regression, or unexpected behavior -> ix-debug <symptom>
Design quality, coupling, complexity, or smells -> ix-architecture <scope>
Documentation or onboarding/reference docs -> ix-docs <target>
Simple lookup requests:
- exact definition -> ix locate <symbol> --format llm
- fuzzy search -> ix text "<term>" --limit 10 --format llm
- incoming callers -> ix callers <symbol> --limit 15 --format llm
- outgoing callees -> ix callees <symbol> --limit 15 --format llm
- path inventory -> ix inventory --kind file --path <path> --format llm

Return exactly this block and nothing else:

Best start: <one sentence describing the recommended entry point>
Run: <exact copy-paste skill invocation or ix command>
Why: <one short sentence>

If the request is ambiguous, make the safest routing choice and say which placeholder to replace.

このリポジトリの他の Skills

同じリポジトリ

ix-architecture

ix-infrastructure/ix-gemini-plugin

Analyze system design — structure, coupling, code smells, and high-risk hotspots. Purely graph-based, no code reads.

2026-05-170

ix-debug

ix-infrastructure/ix-gemini-plugin

Root cause analysis — trace execution path to a failure, narrow candidates, read minimal source only at suspected failure points.

2026-05-170

ix-docs

ix-infrastructure/ix-gemini-plugin

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.

2026-05-170

ix-impact

ix-infrastructure/ix-gemini-plugin

Change risk analysis — blast radius, affected systems, and what to test. Depth scales with risk level; low-risk targets stop early.

2026-05-170

ix-investigate

ix-infrastructure/ix-gemini-plugin

Deep dive into a symbol, feature, or bug. Graph-first, minimal code reads, early stopping when sufficient evidence found.

2026-05-170

ix-plan

ix-infrastructure/ix-gemini-plugin

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.

2026-05-170

name	ix-help
description	Route to the right Ix skill or command for your task
argument-hint	<task or question>

Role: strict router

This skill routes the user to the best Ix entry point and then stops.

You must not:

perform the routed task
gather evidence or run ix commands
chain into the recommended skill
add follow-on analysis after the routing block

If $ARGUMENTS is empty, return this menu:

ix-understand <target> — architectural mental model
ix-investigate <symbol> — deep dive on one symbol or feature
ix-impact <target> — blast radius before editing
ix-plan <targets...> — risk-ordered multi-file change plan
ix-debug <symptom> — root-cause analysis for bugs
ix-architecture [scope] — design health and structural smells
ix-docs <target> — onboarding or reference documentation
Raw ix commands — direct lookups like ix locate <symbol> --format llm

If $ARGUMENTS is non-empty, classify the request and recommend exactly one best starting point:

Architecture, onboarding, or "how does X work" -> ix-understand <target>
Symbol deep dive, feature internals, or "what does X do" -> ix-investigate <target>
Pre-edit risk or blast radius -> ix-impact <target>
Multi-file change, refactor, or migration -> ix-plan <targets or change description>
Bug, failure, regression, or unexpected behavior -> ix-debug <symptom>
Design quality, coupling, complexity, or smells -> ix-architecture <scope>
Documentation or onboarding/reference docs -> ix-docs <target>
Simple lookup requests:
- exact definition -> ix locate <symbol> --format llm
- fuzzy search -> ix text "<term>" --limit 10 --format llm
- incoming callers -> ix callers <symbol> --limit 15 --format llm
- outgoing callees -> ix callees <symbol> --limit 15 --format llm
- path inventory -> ix inventory --kind file --path <path> --format llm

Return exactly this block and nothing else:

Best start: <one sentence describing the recommended entry point>
Run: <exact copy-paste skill invocation or ix command>
Why: <one short sentence>

If the request is ambiguous, make the safest routing choice and say which placeholder to replace.