Menu
Use during research-slice and execute-slice when unfamiliar with a section of code. Go up a layer of abstraction and map relevant modules and callers.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when reviewing architecture decisions. C4 model, dependency inversion, hexagonal boundaries.
Use during discuss-slice and plan-slice to stress-test a spec or plan against domain vocabulary before approval.
Use during research-slice to build disposable experiments that answer technical uncertainty.
Use during project:init to scaffold repo-level agent configuration (CLAUDE.md, AGENTS.md, tracker labels).
Use when debugging. 4-phase investigation, root cause, minimal fix.
Use when implementing features/fixes. Iron law: ยฌโ production code without failing test.
| name | zoom-out |
| description | Use during research-slice and execute-slice when unfamiliar with a section of code. Go up a layer of abstraction and map relevant modules and callers. |
| version | 1.0.0 |
| tags | ["process","research"] |
During research-slice and execute-slice, when you encounter an unfamiliar code region. Use before making changes to code you do not fully understand.
Obtain broader context and a higher-level perspective on how a code region fits into the system.
Acknowledge the unfamiliar area and the specific question: "I do not know how X relates to Y."
Go up one layer of abstraction. Provide:
Describe the map using the project's domain glossary vocabulary (from CONTEXT.md or DOMAIN.md). Avoid generic terms like "handler" or "service" when domain-specific terms exist.
Highlight which modules will be affected by the planned change. Flag any cross-module dependencies that may require additional investigation.
