From supergraph
Generates a domain-vocabulary module map of the codebase to re-orient when lost in unfamiliar code or after a long deep-dive session.
How this skill is triggered — by the user, by Claude, or both
Slash command
/supergraph:zoom-outThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
One prompt. One map. Re-orient fast.
One prompt. One map. Re-orient fast.
Announce: "🔭 /supergraph:zoom-out — stepping back..."
1. Read CONTEXT.md for domain vocabulary (if exists):
head -60 CONTEXT.md 2>/dev/null
2. Get architecture overview:
mcp__code-review-graph__get_architecture_overview_tool()
mcp__code-review-graph__list_communities_tool()
3. Output module map using domain vocabulary from CONTEXT.md:
[Project name] — module map
[Community/Module A]
└── [file/symbol] — [one-line role in domain terms]
└── [file/symbol] — [one-line role]
[Community/Module B]
└── ...
Key flows:
[User action] → [Module A] → [Module B] → [output]
Hub nodes (high-change risk): [list]
Bridge nodes (coupling chokepoints): [list]
No implementation details. Domain language only. If a concept doesn't have a name in CONTEXT.md — use the most natural domain term and suggest adding it.
npx claudepluginhub datit309/supergraph --plugin supergraphMaps module structure and callers when navigating unfamiliar codebases. Use before editing new modules or when asked for a big picture overview.
Prompts the agent to zoom out and provide a high-level map of relevant modules and callers using the project's domain glossary. Use when unfamiliar with a code area or to understand how it fits into the bigger picture.
Produces a one-screen codebase map showing entry points, core modules, data flow, callers, and hidden coupling. Use when orienting in unfamiliar code.