ix-infrastructure/ix-gemini-plugin/ix-docs
Claude Code and agent skill by ix-infrastructure/ix-gemini-plugin
- community
Checking that the SKILL.md file is still in the repository.
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.
Install
npx vskill@latest install ix-infrastructure/ix-gemini-plugin/ix-docsSKILL.md
Goal
Produce documentation that helps a new engineer understand the system quickly.
If Ix is unavailable (tool calls fail, or ix_health() reports the backend unreachable), this skill cannot proceed without the graph.
Core model
Every ix-docs run produces two layers:
- Narrative layer (always first) — human-readable, onboarding-focused
- Reference layer (always present, but selective) — compressed summaries of important components
Mode: default = narrative-heavy; --full = deeper coverage. Style: --style narrative (default) / --style reference / --style hybrid.
Non-negotiable rules
- Graph first — start with
ix_subsystems,ix_overview,ix_rank,ix_explain - Importance-weighted — expand detail by centrality, risk, coupling
- Selective low-level detail — never exhaustive
- No raw dumps — summarize tool results
- No redundancy — group repeated patterns
- Code reads are rare — default: max 2; full: max 5
Preferred path — one call
For a named target, call ix_context first and use its evidence as the skeleton of the narrative layer:
Supplement with the phases below for --full coverage.
Phases
Phase 1 — Scope
Call in parallel:
ix_stats()— graph size, file countix_subsystems()— top-level architecture
Phase 2 — Architecture
Call in parallel:
ix_overview({ target: $ARGUMENTS })ix_rank({ by: "dependents", kind: "class", top: 10 })
Phase 3 — Behavior
Call ix_explain({ symbol: <component> }) for the most important components (top 3-5 by rank).
Phase 4 — Relationships
For key components:
ix_callers({ symbol: <component> })ix_callees({ symbol: <component> })ix_depends({ symbol: <component>, depth: 2 })
Phase 5 — Risk
Call: ix_impact({ target: $ARGUMENTS })
Phase 6 — Health
Call: ix_smells()
Phase 7 — Optional reads (max 2-5 source reads for --full)
Output structure
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-docs/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-docs)