zoom-out

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/agentic-engineering/skills/zoom-out/SKILL.md

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An extremely lean, copy-paste-ready prompt template that is fully actionable for a single-step task, with no padding and a single well-signaled conditional reference.

Dimension	Reasoning	Score
Conciseness	Two lean sentences that assume Claude's competence and add nothing it already knows; the only extra is a one-line vendoring comment, which is metadata rather than padding.	5 / 5
Actionability	Concrete, ready-to-send instruction ('Go up a layer of abstraction. Give me a map of all the relevant modules and callers, using the project's domain glossary vocabulary (`CONTEXT.md` if present)'); no code is required for this instruction-only skill, but it gives no example of the expected 'map' output, capping it at 4.	4 / 5
Workflow Clarity	A single, unambiguous action (issue one orientation prompt); the simple-skill exception applies and there are no destructive or batch operations that would require validation checkpoints.	5 / 5
Progressive Disclosure	A 3-line skill with no bundle files and nothing to split; the only reference (`CONTEXT.md` if present) is a clearly signaled, one-level-deep conditional pointer to a project file, fitting the under-50-lines simple-skill carve-out.	5 / 5
	Total	19 / 20 Passed

Description

65%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A concise description with an explicit 'Use when...' trigger and natural phrasing, but its actions are abstract rather than concrete and it uses second-person voice instead of the expected third person.

Suggestions

Rewrite in third person (e.g., 'Gives a higher-level map of modules and callers...') instead of 'Tell the agent...' / 'Use when you're...'.

Replace abstract verbs ('zoom out', 'give broader context') with concrete capabilities (e.g., 'maps modules and callers, summarizes entry points and dependencies').

Add a couple of trigger synonyms ('overview', 'architecture', 'explain how this fits') for broader keyword coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain (code) and a couple of actions ('zoom out', 'give broader context', 'give a higher-level perspective'), but those actions are abstract/metaphorical rather than concrete; base 3 reduced by 1 because the voice is second person ('Tell the agent...', 'you're unfamiliar', 'you need') instead of third person.	2 / 5
Completeness	Both a 'what' ('zoom out and give broader context or a higher-level perspective') and an explicit 'when' ('Use when you're unfamiliar... or need to understand how it fits into the bigger picture') are present; the 'what' is somewhat abstract, keeping it below 5.	4 / 5
Trigger Term Quality	Includes natural phrases users actually say ('zoom out', 'broader context', 'higher-level perspective', 'bigger picture', 'unfamiliar with a section of code'); a few synonyms like 'overview' or 'explain' are missing, so not a 5.	4 / 5
Distinctiveness Conflict Risk	The 'zoom out / bigger picture / higher-level perspective' framing carves a fairly distinct niche for code-orientation, with only minor overlap risk against generic 'explain this code' skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: belchman/claude-skills
Path: plugins/agentic-engineering/skills/zoom-out/SKILL.md
Commit: 77a9e6b

Reviewed: 11 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.