Skip to main content
skill CX Codex

zoom-out · haowjy, claude — Claude Code skill: orientation map for unfamiliar code

zoom-out spawns parallel explorers across structure, knowledge, and decision history, then merges their reports into a single orientation map of the area.

Apache-2.0 443 installs ★ 601 updated 2026-10-25

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add haowjy/creative-writing-skills --skill zoom-out -a claude-code
Open on GitHub

What zoom-out does

The skill orients you inside someone else's codebase or an unfamiliar subsystem. One explorer sees only a slice, so zoom-out fans out several at once: structure (callers, dependencies, module boundaries), documented knowledge (architecture, guides), decision history (why the area is shaped this way, what was rejected), and domain vocabulary.

Then it reads the reports and produces one orientation map: what the area is, key parts and connections, the decisions that explain its current shape, the terms needed to discuss it, and open threads. Contradictions get resolved rather than listed. The code shows current state, a settled decision shows intent; a stale doc gets flagged, a gap between state and intent goes into the report.

Before running, the skill requires the /creative-writing-skills:qi-layer to be loaded. Install with npx skills add haowjy/creative-writing-skills --skill zoom-out -a claude-code; the file lands in ~/.claude/skills/zoom-out/SKILL.md. The map stays tight: enough to navigate, not an exhaustive transcript.

What it helps with

  • Get oriented in an inherited codebase
  • Map structure of an unfamiliar subsystem: callers, dependencies, boundaries
  • Trace decision history behind the current design
  • Collect the vocabulary needed to discuss the area precisely
  • Merge parallel explorer reports into one readable map

Example prompts for the agent

  • Orient me in this repository: run zoom-out.
  • How is the payment module structured? Map its dependencies and entry points.
  • Why was auth built this way? Pull the decision history for this area.

How to install zoom-out

1Skills CLI (Vercel)

npx skills add haowjy/creative-writing-skills --skill zoom-out -a claude-code

2Manually: put the files in place

~/.claude/skills/zoom-out/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/zoom-out/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about zoom-out

How do I install zoom-out in Claude Code?

Run npx skills add haowjy/creative-writing-skills --skill zoom-out -a claude-code. The skill lands in ~/.claude/skills/zoom-out/SKILL.md.

What does zoom-out do?

It fans out parallel explorers across structure, documented knowledge, decision history, and vocabulary, then synthesizes their reports into one orientation map.

What does it need before running?

The /creative-writing-skills:qi-layer must be loaded first.

Source text

SKILL.md · Apache-2.0
---
name: zoom-out
description: 'Use when orienting in an unfamiliar area: fans out parallel explorers across structure, knowledge, and history, then synthesizes one orientation map.'
metadata:
  type: mode-shift
---

# Zoom Out

Load `/creative-writing-skills:qi-layer` if it isn't already loaded.

Orient in an unfamiliar area by fanning out parallel explorers, each covering a different angle, then synthesizing their reports into one orientation map. A single explorer sees one slice; zoom-out covers structure *and* knowledge *and* history at once, so the picture isn't skewed by one lens.

Use when starting in an unfamiliar subsystem, picking up someone else's work, or when the user says "orient me" / "what's the lay of the land here."

## Fan Out

Spawn in parallel the angles the area has material for, each scoped to one angle and one question.

- **Structure** (`@explorer`): how the area's parts connect and where behavior lives; in code, callers, dependencies, module boundaries, entry points.
- **Documented knowledge** (`@explorer` over the knowledge base): what's been written about this area, including architecture, guides, synthesized research.
- **Decision history** (`@session-miner`): why it's shaped this way. Prior choices, rejected alternatives, constraints discovered.
- **Domain concepts** (`@explorer`): the vocabulary in use (KB vocab pages, `.context/CONTEXT.md`, AGENTS.md).

Give each explorer one angle, scoped with concrete path or topic targets: the value is independent coverage.

## Synthesize

Read the reports and produce one orientation map, not stitched-together dumps:

- **What this is**: the area's purpose and boundaries, in two or three sentences.
- **Structure**: the parts and interfaces that matter and how they connect (a mermaid diagram if the shape is spatial).
- **Why it's like this**: the decisions and constraints that explain the current shape.
- **Vocabulary**: the terms needed to speak about it precisely.
- **Open threads**: gaps, debt, or unresolved questions the explorers surfaced.

When reports contradict each other, resolve it rather than listing both, by what each source governs: the thing itself (the code, the data, the manuscript) shows its current state, and a settled decision shows intent. A doc that misdescribes current state is stale (note it); a gap between current state and settled intent is a divergence to report. Keep the map tight: the goal is a reader who can now navigate the area, not an exhaustive transcript.

© haowjy · Apache-2.0 · haowjy/creative-writing-skills

Similar skills

All skills for Agent setup: memory, context, orchestration →

zoom-out by other authors comes first.

zoom-out haowjy zoom-out is a Claude Code skill that maps an unfamiliar part of a project. It starts when someone asks to get oriented or takes over work in an unfamiliar subsystem. CX Codex +1 443installs zoom-out akillness zoom-out draws a map of an unfamiliar part of a codebase before you change it: the modules involved, who calls whom, what depends on what. CX Codex +1 275installs fan-out haabe fan-out — a skill for Claude Code, Codex, Cursor and other platforms that spawns workers in parallel to explore multiple solutions, then collects their scorecards and picks a winner by evidence. CX Codex +1 ★ 54repo stars setup-zoom-mcp official anthropics setup-zoom-mcp helps decide whether Zoom MCP or a hybrid REST API fits your workflow, evaluates auth constraints, and drafts a PoC plan. CX Codex +1 2,200installs context-engineering-collection muratcankoylan context-engineering-collection is a Claude Code skill with patterns for context management, multi-agent systems, and long-running loops for reliable autonomous systems. CX Codex +1 4,500installs figure-it-out backnotprop figure-it-out — a skill for Claude Code, Codex, Cursor and other platforms that designs a step-by-step playbook when off-the-shelf tools don't fit. Scales rigor to task complexity, runs hypothesis loops, and logs decisions for review. CX Codex +1 10,300installs parallel-exploring spencerpauly parallel-exploring launches several explore subagents at once so you can map a large codebase fast. Useful for onboarding and for tracing a feature across layers. CX Codex +1 511installs explore OrchestKit explore spawns 3–5 agents in parallel to map code structure, trace data flows, identify architecture patterns, and assess code health. Useful for quickly understanding an unfamiliar repo or discovering how a large system is designed. CX Codex +1 224installs

From the same set32

The whole set →
grill-with-docs grill-with-docs challenges project plans through sequential questioning, verifies terminology against project docs, and records decisions on the fly. CX Codex +1 556installs creative-writing-modes creative-writing-modes — a skill that adds five prose modes to your writing pass: fresh draft, revision, bridge, alternate take and line polish. Useful once structure is settled and the page needs words. CX Codex +1 537installs kb-management kb-management organizes story knowledge bases in kb/ with rules for canon, vocab, and characters. It helps keep lore and continuity consistent across writing agents. CX Codex +1 531installs information-hierarchy information-hierarchy — a skill for large human-facing output: reports, docs, multi-section explanations. The answer comes first, depth sits behind it. CX Codex +1 456installs zoom-out zoom-out is a Claude Code skill that maps an unfamiliar part of a project. It starts when someone asks to get oriented or takes over work in an unfamiliar subsystem. CX Codex +1 443installs structured-artifact structured-artifact — a skill for building structured HTML artifacts: the agent decides how to present the content first, then picks the tools. CX Codex +1 443installs qi-layer The qi-layer skill provides a structure for maintaining agent instructions in AGENTS.md and .context/CONTEXT.md. It activates when writing or updating project-level context. CX Codex +1 441installs knowledge-layers The knowledge-layers Claude Code skill sorts project knowledge across nearby docs, a knowledge base, and work directories. It activates when choosing where information belongs or editing durable documentation. CX Codex +1 441installs

Project sponsors

Companies that keep this analytics open