ios-device-screenshot

Take screenshots from physical iOS devices connected via USB using pymobiledevice3. Use when capturing screenshots from real iPhones/iPads (not simulators), debugging on-device, or needing high-fidelity device captures. Triggers on physical iOS device screenshots, pymobiledevice3 usage, or USB-connected device capture tasks.

2.17x

Quality

—

Does it follow best practices?

Impact

100%

2.17x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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

Highly actionable with executable commands and a clear workflow, but held back by duplicated content, an internal contradiction on the UDID flag, and an all-inline structure that exceeds a lean overview for a skill this length.

Suggestions

Deduplicate the iOS 17+ screenshot command: it appears in Usage, Quick Reference, Key Discovery, and Troubleshooting — keep it in one canonical place and reference it from the others.

Resolve the multiple-device flag contradiction: Quick Reference says pass the UDID to --tunnel (not --udid), but Troubleshooting uses --udid — pick one and state it consistently.

Split the full integration bash script and detailed troubleshooting into reference files (e.g., scripts/ and references/TROUBLESHOOTING.md) to keep SKILL.md a lean overview and reduce inline length.

Dimension	Reasoning	Score
Conciseness	Mostly lean, command-driven content with no concept-padding, but the iOS 17+ screenshot command is repeated across Usage, Quick Reference, Key Discovery, and Troubleshooting, and the multiple-device UDID guidance is duplicated with a contradiction (--tunnel vs --udid).	2 / 3
Actionability	Provides concrete, executable commands with real flags and UDID examples, plus a complete copy-pasteable integration bash script with tunneld startup and screenshot capture.	3 / 3
Workflow Clarity	The two-step workflow (start tunneld, then capture) is clearly sequenced, with explicit error-recovery feedback loops in Troubleshooting and a validation checkpoint (tunneld-running guard plus output-file check) in the integration script.	3 / 3
Progressive Disclosure	Sections are well-organized with clear headers and no nested references, but the ~138-line body is entirely monolithic with no external reference files, and content like the full integration script and troubleshooting detail could be split out to keep the overview lean.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 strong description with a clear niche, explicit 'Use when'/'Triggers on' guidance, and natural trigger terms. The only weakness is that it describes a single capability rather than multiple concrete actions.

Dimension	Reasoning	Score
Specificity	Names the concrete action ('Take screenshots') and a specific tool/domain ('pymobiledevice3', 'physical iOS devices connected via USB'), but centers on a single capability rather than listing multiple distinct actions.	2 / 3
Completeness	Explicitly states what the skill does and when to use it via both a 'Use when...' and a 'Triggers on...' clause, clearly answering both halves.	3 / 3
Trigger Term Quality	Includes natural terms users would say ('screenshots', 'real iPhones/iPads', 'physical iOS devices', 'USB') alongside the tool name, giving good trigger coverage.	3 / 3
Distinctiveness Conflict Risk	The niche is narrow and explicit — physical (non-simulator) iOS devices via USB using pymobiledevice3 — making it unlikely to trigger for unrelated skills.	3 / 3
	Total	11 / 12 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: NeverSight/skills_feed
Commit: ff6a653

Reviewed: 4 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.