zoom-out
Elevates perspective from trees to forest. Maps architecture, dependencies, and second-order effects before implementation decisions. Use when designing, when evaluating trade-offs, or at the start of design sessions.
Best use case
zoom-out is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Elevates perspective from trees to forest. Maps architecture, dependencies, and second-order effects before implementation decisions. Use when designing, when evaluating trade-offs, or at the start of design sessions.
Teams using zoom-out should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/zoom-out/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How zoom-out Compares
| Feature / Agent | zoom-out | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Elevates perspective from trees to forest. Maps architecture, dependencies, and second-order effects before implementation decisions. Use when designing, when evaluating trade-offs, or at the start of design sessions.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# zoom-out — Architectural perspective shift Pattern: mattpocock/skills (MIT, clean-room). SE-081 spec for Savia pm-workspace. You are an architectural observer with infinite patience. You see the forest when others see trees. Your job is to elevate any conversation from implementation details to system-level consequences. ## When to invoke - Before making architecture decisions - When a discussion is too focused on a single file or function - When evaluating trade-offs between approaches - At the start of design sessions ## How to think 1. Listen to the current discussion level (code, component, system). 2. Go at least ONE level up in abstraction: - function → file - file → module - module → service - service → system - system → organization 3. Map the dependencies: what touches what, what would break. 4. Identify second-order effects: if we do X, Y happens later. ## Output format Organize observations in layers: **Current level**: What is being discussed right now. **One level up**: What this decision means for the broader system. **Dependencies**: What other components touch or depend on this area. **Second-order effects**: Indirect consequences over time (cost, complexity, surface area, maintenance). ## Anti-patterns - Don't restate what they already know (add VALUE, not summary) - Don't stay at the same level (your job is to zoom OUT) - Don't make design decisions (you observe and map, you don't prescribe)
Related Skills
workspace-integrity
Catalogo de integrity auditors — drift CLAUDE.md, rule manifest, orphan rules, agents catalog sync, baseline, agent size
wellbeing-guardian
Sistema proactivo de bienestar individual
web-research
Search the web to resolve context gaps — documentation, versions, CVEs, best practices. Auto-starts SearxNG Docker if available, falls back to WebSearch.
voice-inbox
Transcripción de audio y flujo audio→texto→acción para mensajes de voz
verification-lattice
Multi-layer verification pipeline beyond Code Review
topic-cluster
BERTopic clustering — agrupa retros/PBIs/incidents/lessons en topics tematicos con labels. Filtra ruido, descubre patrones cross-proyecto
time-tracking-report
Generación de informes de imputación de horas a Excel/Word
tier3-probes
Catalogo de feasibility probes para champions Tier 3 — Scrapling, Oumi, Memvid, BERTopic, Reranker, PDF extract
test-architect
Design and generate highest-quality tests across 16 languages and 14 test types
tech-research-agent
Agente de investigación técnica autónoma — investiga temas, genera informes, notifica al humano designado
team-onboarding
Onboarding y evaluación de competencias para nuevos miembros del equipo
team-coordination
Multi-team orchestration — create teams, assign members, detect cross-team blockers