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.
88
82%
Does it follow best practices?
Impact
100%
2.17xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, well-crafted skill description that clearly specifies the concrete action (taking screenshots), the precise context (physical iOS devices via USB with pymobiledevice3), and explicit trigger conditions. The distinction from simulators is particularly effective for disambiguation. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists concrete actions: 'Take screenshots from physical iOS devices connected via USB using pymobiledevice3.' Also mentions specific use cases like debugging on-device and high-fidelity device captures. | 3 / 3 |
Completeness | Clearly answers both 'what' (take screenshots from physical iOS devices via USB using pymobiledevice3) and 'when' (explicit 'Use when' clause with triggers like capturing from real devices, debugging on-device, needing high-fidelity captures, plus a 'Triggers on' clause). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'screenshots', 'physical iOS device', 'iPhones/iPads', 'not simulators', 'USB', 'pymobiledevice3', 'on-device', 'device captures'. These are terms users would naturally use when needing this specific capability. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — explicitly scoped to physical iOS devices via USB using pymobiledevice3, and explicitly distinguishes from simulators. This creates a very clear niche that is unlikely to conflict with simulator screenshot skills or general screenshot tools. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid, actionable guidance for taking iOS device screenshots with pymobiledevice3, with good coverage of different iOS versions and troubleshooting scenarios. However, it suffers from a critical contradiction regarding --udid usage with tunneld (Quick Reference says don't use it, Troubleshooting says do use it), and has redundant content across sections that could be tightened. The integration example is a nice practical touch.
Suggestions
Resolve the contradiction between Quick Reference ('NOT --udid flag which doesn't work with tunneld') and Troubleshooting ('Use specific UDID' with --udid flag) — pick one correct approach and be consistent throughout.
Consolidate the 'Key Discovery' section into the main Usage section since it repeats the iOS 17+ DVT requirement already covered there.
Add a brief validation step to the main workflow (e.g., check file exists and has non-zero size after screenshot capture).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but has some redundancy. The 'Multiple devices connected' troubleshooting section contradicts the Quick Reference section (one says use --udid, the other says don't use --udid with tunneld). The 'Key Discovery' section partially repeats information already covered in the Usage section. Some explanatory text like 'The `--tunnel ""` flag tells it to use the tunneld for device communication' is unnecessary padding. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste ready commands throughout. Installation, usage for different iOS versions, troubleshooting, and even a complete integration bash script are all concrete and specific with real command-line examples. | 3 / 3 |
Workflow Clarity | The multi-step process (install → start tunneld → take screenshot) is present but there's a significant contradiction: the Quick Reference says NOT to use --udid with tunneld, while the Troubleshooting section says to use --udid. This conflicting guidance would confuse Claude. There's also no explicit validation step after taking a screenshot (the integration example checks file existence, but the main workflow doesn't). | 2 / 3 |
Progressive Disclosure | The content is reasonably well-structured with clear sections (Usage, Quick Reference, Troubleshooting, Integration Example), but it's somewhat long for a single-file skill and has overlapping content between sections. The Quick Reference, Troubleshooting, and Key Discovery sections could be consolidated or some content split into a separate reference file. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- NeverSight/skills_feed
- Commit
f772de4
- Reviewed
Table of Contents
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.