image-editor

Interactive visual editor for Instagram ad images. Use when editing generated images, adjusting text overlays, repositioning logos, or modifying ad visual elements.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./creative-skills/multi-channel-ad-ideation/channels/image-editor/SKILL.md

Quality

Content

61%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 with complete, executable code and a clear step sequence, but it is monolithic — large code blocks that belong in separate reference files are inlined and there is no output validation checkpoint in the compositing workflow.

Suggestions

Add an explicit validation step after the Pillow applicator saves the PNG (e.g. verify the file exists, dimensions match 1024x1024, and overlays render) before calling open_file, to lift workflow_clarity above the validation cap.

Extract the full React editor component and the Pillow applicator script into separate bundle files under scripts/ or references/, leaving concise inline summaries and links, to improve progressive_disclosure.

Trim the five-palette bgGradient list and the restated "Workflow note" paragraph to reduce redundant tokens.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly earns its tokens with copy-paste code and tight explanations, but sections like the five-palette bgGradient list and the restated "Workflow note" could be trimmed, fitting the 'efficient with minor over-explanation' anchor.	4 / 5
Actionability	Executable Python (poller + Pillow applicator) and a complete React component cover the common cases, but placeholder logo paths require manual resolution and the minified React code is hard to adapt, keeping it just below the fully copy-paste-ready top anchor.	4 / 5
Workflow Clarity	The numbered Steps 1 through 3 sequence clearly orders execution, but this compositing/save workflow lacks an explicit validation checkpoint on the final output; per the rubric, missing validation in such a workflow caps this dimension at 3.	3 / 5
Progressive Disclosure	No bundle files exist and the full React component and Pillow applicator are inlined in a single ~330-line file; content that clearly belongs in separate files is inlined, matching the anchor where inlined separate-file content keeps it just above the monolithic-text bottom anchor.	2 / 5
	Total	13 / 20 Passed

Description

75%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 concrete and explicit, naming the domain and several specific actions alongside a clear 'Use when' trigger clause. It is strong but stops short of the top anchors due to less-exhaustive triggers and minor overlap risk with generic image editing.

Dimension	Reasoning	Score
Specificity	"Interactive visual editor for Instagram ad images" plus "editing generated images, adjusting text overlays, repositioning logos, or modifying ad visual elements" lists several concrete actions, matching the anchor for minor gaps in coverage rather than the fully comprehensive top anchor.	4 / 5
Completeness	Both a clear "what" (interactive visual editor) and an explicit "Use when..." clause are present, but the trigger list could be more exhaustive and concrete, so it sits at the anchor where 'when' could be more specific rather than the top anchor.	4 / 5
Trigger Term Quality	Natural phrases like "Instagram ad images", "text overlays", and "repositioning logos" give good coverage, but common synonyms or extensions a user might say (e.g. "ad creative", "IG") are absent, fitting the anchor where a few natural terms are missing.	4 / 5
Distinctiveness Conflict Risk	The Instagram ad niche with overlay/logo triggers is mostly distinct with only minor overlap risk against a generic image-editing skill, matching the 'mostly distinct' anchor rather than the fully minimal-conflict top anchor.	4 / 5
	Total	16 / 20 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: treasure-data/td-skills
Path: creative-skills/multi-channel-ad-ideation/channels/image-editor/SKILL.md
Commit: 1a0845f

Reviewed: 3 hours 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.