CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

device-frames

Create device-framed screenshots, product images, videos, or live UI mockups. Use when placing an image, recording, webpage, or component inside a phone, foldable, tablet, watch, laptop, monitor, or browser frame, including App Store-style visuals and launch videos.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

The body is an exceptionally concrete, data-dense instruction set with genuine verification checkpoints and error-recovery loops. Its main weaknesses are the fully monolithic structure (bulk geometry lookup tables inlined rather than split into reference files) and some repetition of the open-Duo guidance.

Suggestions

Move the measured-hardware tables, corner profiles, and button positions into a references/ file (e.g., references/geometry.md), keeping SKILL.md as an overview with well-signaled one-level-deep pointers.

Consolidate the open-Duo "one continuous screen, no gap at the hinge" guidance, which is currently repeated across the Device geometry, Fully open Duo, and Coordinate example sections, into a single authoritative section.

Consider moving per-device point-size tables to a reference file as well and keeping only the most common devices (e.g., current iPhone and the Duo) inline in SKILL.md.

DimensionReasoningScore

Conciseness

Nearly every line carries non-obvious data (mm case sizes, corner offset profiles, scale factors) with no explanations of known concepts, but the open-Duo "no gap at the hinge" warning is repeated across three sections and "951 × 669" appears four times, which could be consolidated.

4 / 5

Actionability

For an instruction-only skill the guidance is fully concrete: exact point dimensions, `[x, y]` corner profiles, worked scale factors (`k = 466 / 77.17 ≈ 6.0386`), a complete coordinate example, and a specific fill color (`#d8d8dc`), covering the common cases.

5 / 5

Workflow Clarity

A clear sequence (deliverable → construct frame → geometry → output/verification) with explicit validation and feedback loops: "measure the rendered screen bounds... If the ratio or shape is wrong, fix and rerender it" and "Inspect the actual image or representative video frames before delivery".

5 / 5

Progressive Disclosure

Section headers are clear, but the ~218-line body inlines everything with no bundle files: the measured-hardware tables, corner profiles, and button positions (~90 lines of lookup data) clearly belong in separate reference files, fitting the "content that should be separate is inline" anchor.

3 / 5

Total

17

/

20

Passed

Description

87%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 strong description: it pairs a concrete capability statement with an explicit, trigger-rich "Use when" clause covering all device types and deliverable formats. The only minor weaknesses are single-verb action phrasing and a few missing natural synonyms.

DimensionReasoningScore

Specificity

"Create device-framed screenshots, product images, videos, or live UI mockups" lists several concrete deliverables, but all hang on a single verb ("create"), leaving minor coverage gaps relative to the multi-verb comprehensiveness of the top anchor.

4 / 5

Completeness

It clearly answers both questions: the "what" ("Create device-framed screenshots, product images, videos, or live UI mockups") and an explicit "Use when placing an image, recording, webpage, or component inside a phone, foldable, tablet, watch, laptop, monitor, or browser frame" clause with concrete trigger phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

Natural terms are well covered ("screenshots", "phone", "foldable", "tablet", "watch", "laptop", "monitor", "browser frame", "App Store-style visuals", "launch videos", "mockups"), but a few natural synonyms (e.g., "bezel", "app mockup", format extensions like png/mp4) are missing, so it falls just short of the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

Device framing is a clear niche with distinct triggers (placing media "inside a phone... frame", "App Store-style visuals"); only negligible overlap with generic image or mockup skills, so the minimal-conflict anchor fits better than the minor-overlap anchor below it.

5 / 5

Total

18

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

ibelick/ui-skills

Path

skills/device-frames/SKILL.md

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.