Zoom Out
Orientation skill: fan out across code structure, docs, and history, then synthesize one map
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 31, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 823acda
Fetched SKILL.md via raw GitHub and confirmed frontmatter (name+description) parses; the one body reference, /qi-layer, exists (HTTP 200). Verified the install block in a temp HOME actually lands SKILL.md at ~/.claude/skills/zoom-out/SKILL.md. For output I used the repo's own cw/skills dir as the "unfamiliar area": BASELINE.md was a flat categorized skill list ending "start with muse and it pulls in the others"; following the body (SKILL_OUTPUT.md) forced a real fan-out — I grepped the "Load /" edges and derived the load graph (qi-layer/knowledge-layers mutual recursion, llm-writing/intent-modeling/information-hierarchy as most-shared leaves), explicitly skipped decision-history per the skill, and produced a 5-section map surfacing open threads (no in-repo decision docs, two parallel install systems) the baseline never mentioned. Docs docked 1: description advertises three lenses (structure/knowledge/history) but the body actually fans out four, adding domain-concepts/vocabulary.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 7/10
- Docs & honesty 4/5
What Zoom Out does
A methodology skill for orienting in an unfamiliar codebase or knowledge area: it explores several angles independently (structure/callers, documented knowledge, decision history, domain vocabulary) and then synthesizes them into a single orientation map instead of four separate dumps. Triggers when you start in an unfamiliar subsystem, pick up someone else's work, or ask "orient me" / "what's the lay of the land." Loads the /qi-layer skill first, so it is intended to run inside the full creative-writing-skills plugin.
How to install Zoom Out
git clone --depth 1 https://github.com/haowjy/creative-writing-skills.git /tmp/zoom-out-src
mkdir -p ~/.claude/skills
cp -R /tmp/zoom-out-src/cw/skills/zoom-out ~/.claude/skills/zoom-out
# First line of the body is "Load /qi-layer" — for full behavior also install its
# dependency chain (qi-layer -> knowledge-layers, llm-writing, information-hierarchy,
# intent-modeling, shared-dao) or just install the whole plugin:
# /plugin marketplace add haowjy/creative-writing-skills
# /plugin install creative-writing-skills@cw
# Degrades gracefully: the fan-out/synthesize method still works if /qi-layer is absent.
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Zoom Out
-
/zoom-outOrientation skill: fan out across code structure, docs, and history, then synthesize one map
It also activates on plain-language prompts like these:
-
Orient me in this unfamiliar codebase -
Give me a map of this project's structure -
Summarize this project's history and knowledge base
Frequently asked questions
- Is the Zoom Out skill free?
- Yes. The skill itself is free from haowjy/creative-writing-skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Zoom Out work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 31, 2026. Verdict: Tested · Works. Fetched SKILL.md via raw GitHub and confirmed frontmatter (name+description) parses; the one body reference, /qi-layer, exists (HTTP 200). Verified the install block in a temp HOME actually lands SKILL.md at ~/.claude/skills/zoom-out/SKILL.md. For output I used the repo's own cw/skills dir as the "unfamiliar area": BASELINE.md was a flat categorized skill list ending "start with muse and it pulls in the others"; following the body (SKILL_OUTPUT.md) forced a real fan-out — I grepped the "Load /" edges and derived the load graph (qi-layer/knowledge-layers mutual recursion, llm-writing/intent-modeling/information-hierarchy as most-shared leaves), explicitly skipped decision-history per the skill, and produced a 5-section map surfacing open threads (no in-repo decision docs, two parallel install systems) the baseline never mentioned. Docs docked 1: description advertises three lenses (structure/knowledge/history) but the body actually fans out four, adding domain-concepts/vocabulary.
- What is the Zoom Out SkillProof Score?
- 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.
- How do I install Zoom Out?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Zoom Out with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.