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 an excellent skill description that clearly defines a narrow, specific capability with strong trigger terms and explicit 'Use when' and 'Triggers on' clauses. It distinguishes itself well from related skills (e.g., simulator screenshots) by specifying physical devices, USB, and the pymobiledevice3 tool. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists concrete actions: 'Take screenshots from physical iOS devices connected via USB using pymobiledevice3.' Specifies the tool (pymobiledevice3), connection method (USB), and target (physical iOS devices). Multiple specific use cases are named. | 3 / 3 |
Completeness | Clearly answers both 'what' (take screenshots from physical iOS devices via USB using pymobiledevice3) and 'when' (explicit 'Use when' clause covering debugging on-device, high-fidelity captures, plus a 'Triggers on' clause listing specific trigger scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms: 'screenshots', 'physical iOS devices', 'USB', 'iPhones/iPads', 'simulators' (as exclusion), 'on-device', 'pymobiledevice3', 'device captures'. These are terms users would naturally use when needing this capability. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive by specifying physical iOS devices (not simulators), USB connection, and pymobiledevice3. The explicit exclusion of simulators and the specific tool mention create a clear niche that is unlikely to conflict with general screenshot or simulator-based skills. | 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 concrete commands and a useful integration script. However, it suffers from internal contradictions (the --udid vs --tunnel advice for multiple devices differs between sections), redundancy between the Usage, Quick Reference, and Key Discovery sections, and lacks validation checkpoints in the workflow. Tightening the content and resolving contradictions would significantly improve it.
Suggestions
Resolve the contradiction about multiple device handling: Quick Reference says pass UDID to --tunnel while Troubleshooting says use --udid flag — pick one correct approach and be consistent throughout.
Merge the 'Key Discovery' section into the 'Usage' section since it repeats the same iOS 17+ DVT information, reducing redundancy.
Add explicit validation steps to the workflow, e.g., verify tunneld is connected and device is detected before attempting screenshot capture.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content has some redundancy — the multiple devices section contradicts itself (Quick Reference says pass UDID to --tunnel, Troubleshooting section says use --udid flag), and the 'Key Discovery' section 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 | Provides fully executable, copy-paste ready commands throughout — installation, tunneld setup, screenshot capture for different iOS versions, troubleshooting commands, and a complete integration bash script. All commands are concrete and specific. | 3 / 3 |
Workflow Clarity | The multi-step process (install → start tunneld → take screenshot) is present but lacks explicit validation checkpoints. The integration script has basic error checking but the main workflow doesn't include verification steps like confirming tunneld is actually connected to the device. The contradictory advice about --udid vs --tunnel for multiple devices creates confusion rather than clarity. | 2 / 3 |
Progressive Disclosure | The content is reasonably structured with clear sections, but it's somewhat monolithic at ~100 lines with no external references. The troubleshooting section and integration example could potentially be split out. However, for a standalone skill with no bundle files, the organization is acceptable though the redundancy between sections (Usage vs Key Discovery vs Quick Reference) hurts navigation. | 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
aa009ea
- 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.