ix-infrastructure/ix-gemini-plugin/ix-understand
Claude Code and agent skill by ix-infrastructure/ix-gemini-plugin
- community
Checking that the SKILL.md file is still in the repository.
Build a mental model of a system, subsystem, or the whole repo. Graph-first, no code reads unless necessary.
Install
npx vskill@latest install ix-infrastructure/ix-gemini-plugin/ix-understandSKILL.md
Goal
Build an accurate mental model of the target's structure, purpose, and key components. Stop as soon as you can answer: what does this do, what are its key parts, and where should someone explore next?
If Ix is unavailable (tool calls fail, or ix_health() reports the backend unreachable), proceed with best-effort analysis.
Preferred path — one call
If $ARGUMENTS names a target, call ix_context first and use its ranked evidence (definition, members, callers, importers, related files) as the backbone of the answer:
For a whole-repo question (no target), start at Phase 1. Supplement with the phases below if the evidence needs more detail.
Phase 1 — Orient (always run)
Call in parallel:
ix_subsystems()— architectural regions, file counts, cohesionix_rank({ by: "dependents", kind: "class", top: 10 })— most central classesix_rank({ by: "callers", kind: "function", top: 10 })— most called functions
If $ARGUMENTS is non-empty, also call:
ix_locate({ symbol: $ARGUMENTS })— resolve the target in the graph
Extract: region names, file counts, cohesion scores; top 3-5 structurally central components.
Stop here if: $ARGUMENTS is empty and rank + subsystems give a clear picture.
Phase 2 — Key components (run only if needed)
Pick the 2-4 most central or unclear components from Phase 1. Call in parallel:
ix_overview({ target: <component> })for each
Do NOT call ix_explain yet — ix_overview is cheaper and sufficient for most components.
Stop here if: you can describe what each component does and how they relate.
Phase 3 — Clarify (run only if still unclear)
For at most 2 components still unclear after Phase 2:
ix_explain({ symbol: <component> })
Hard limits: No source code reads. No ix_map. No ix_trace. This skill never reads source code.
Output
Evidence labels: Mark every claim as [graph] (direct tool data) or [inferred] (structural reasoning). Never state facts without one of these labels.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/ix-understand/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/ix-infrastructure/ix-gemini-plugin/ix-understand)