CtrlK
BlogDocsLog inGet started
Tessl Logo

gemini-logo-remover

Remove Gemini logos, watermarks, or AI-generated image markers using OpenCV inpainting. Use this skill when the user asks to remove Gemini logo, AI watermark, or any logo/watermark from images.

66

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/gemini-logo-remover/SKILL.md

The canonical home for this skill is gemini-logo-remover in bear2u/my-skills

SKILL.md
Quality
Evals
Security

Quality

Content

80%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 content is highly actionable and well-structured for a simple single-purpose skill, with copy-paste-ready code covering the main cases. Its main gap is the absence of any verification/feedback step for a coordinate-dependent image operation.

Suggestions

Add a verification step after inpainting (e.g., visually check the output region or compare mask bounds against the detected logo) before saving and calling present_files.

Make the 'Find Coordinates' snippet self-contained by defining input_path, or convert it into a reusable helper that prints image dimensions and suggests corner coordinates.

Replace the non-English comments in the Find Coordinates section with the English used elsewhere, or remove them since the same guidance already appears in Notes.

DimensionReasoningScore

Conciseness

The body is mostly lean: executable functions with minimal preamble and useful operational notes, with only minor removable redundancy (the Korean coordinate comments restate guidance already in Notes).

4 / 5

Actionability

It provides complete, copy-paste-ready functions (remove_region, remove_corner_logo) with concrete example calls and real output paths, covering the common coordinate- and corner-based cases.

5 / 5

Workflow Clarity

Setup, method choice, execution, and output are present, but there are no validation or feedback checkpoints (e.g., verify the mask region or confirm the logo was removed before presenting), and the coordinate-based operation is fragile, so it sits at the validation-gap anchor rather than higher.

3 / 5

Progressive Disclosure

This compact single-purpose skill has no external bundle files and is organized into clear sections (Setup, Usage subsections, Output, Notes) with no nested references, satisfying the simple-skill exception for progressive disclosure.

5 / 5

Total

17

/

20

Passed

Description

78%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.

The description is strong: it pairs a concrete capability statement with an explicit 'Use when...' trigger clause covering natural phrasings. Its main weakness is that the capability is essentially a single action and the 'any logo/watermark' wording slightly widens conflict risk.

DimensionReasoningScore

Specificity

The description names the domain and a concrete action ("Remove Gemini logos, watermarks, or AI-generated image markers using OpenCV inpainting"), but it is essentially a single action applied to several target types rather than multiple distinct actions, so it does not reach the 'several specific actions' anchor.

3 / 5

Completeness

It explicitly answers both 'what' (remove logos/watermarks via OpenCV inpainting) and 'when' ("Use this skill when the user asks to remove Gemini logo, AI watermark, or any logo/watermark from images") with concrete trigger phrases.

5 / 5

Trigger Term Quality

It includes natural terms users would say ("Gemini logo", "AI watermark", "logo/watermark from images") with some synonym coverage, but omits file extensions (jpg/png) and a few common phrasings, so it falls short of comprehensive.

4 / 5

Distinctiveness Conflict Risk

The Gemini/AI-logo niche is clearly distinct, but the clause "any logo/watermark from images" broadens scope and creates minor overlap risk with general image-editing or watermark-removal skills, keeping it just below a clear-niche score of 5.

4 / 5

Total

16

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
bear2u/my-skills
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.