Step up one layer of abstraction and surface a map of relevant modules and callers when the local view is too narrow. Trigger when the agent (or user) is unfamiliar with a code region and needs the surrounding architecture before committing to a change.
Scanned 9/2/2026
Install to Claude Code
npx -y skills add majiayu000/claude-skill-registry --skill zoom-out --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Zoom Out?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/majiayu000-zoom-out)More formats (shields.io, HTML) on the badges page.
---
name: zoom-out
description: Step up one layer of abstraction and surface a map of relevant modules and callers when the local view is too narrow. Trigger when the agent (or user) is unfamiliar with a code region and needs the surrounding architecture before committing to a change.
disable-model-invocation: true
---
Stop reading the local fragment. Climb one level of abstraction and produce a map: which modules surround this region, who calls into it, what it calls out to, and where its invariants live. Dispatch an Explore agent (`fd`-first discovery, then `git grep`/`ast-grep` for call-site enumeration) rather than reading individual files — the goal is structural orientation, not line-level detail.
Output is a compact module-and-caller map, not a narrative. Name the surrounding components, the inbound and outbound edges, and any obvious invariant boundaries (transactional scope, ownership, IO surfaces). Stop at one layer up unless the user asks for more — over-zoom dilutes the orientation.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...