image-processing

Process images for web development — resize, crop, trim whitespace, convert formats (PNG/WebP/JPG), optimise file size, generate thumbnails, create OG card images. Uses Pillow (Python) — no ImageMagick needed. Trigger with 'resize image', 'convert to webp', 'trim logo', 'optimise images', 'make thumbnail', 'create OG image', 'crop whitespace', 'process image', or 'image too large'.

Quality

90%

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

Quality

Content

76%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 highly actionable with complete executable code and clear sectioning, but its batch and optimise workflows omit validation/verification checkpoints, which the rubric caps at 3 for workflow clarity. The referenced img-process CLI also has no corresponding bundle file.

Suggestions

Add validation/verification steps to the batch and optimise workflows (e.g., re-open output to confirm it is valid, report before/after file sizes, or list any files that failed to convert) to lift workflow_clarity above the cap of 3.

Either ship the referenced img-process CLI in a bin/ directory or replace the 'shipped in bin/' framing with the actual fallback (generate a Pillow script) so the body does not reference a non-existent bundle file.

Tighten the few explanatory sentences in Core Patterns (e.g., the RGBA-to-JPG compositing note) to lean phrasing, or move the longer code patterns into a reference file so SKILL.md stays a concise overview.

Dimension	Reasoning	Score
Conciseness	The body is dense and code/table-heavy with minimal prose padding, but a few explanatory sentences ('Different formats need different save parameters', 'System font paths differ by OS') could be trimmed, placing it just below the lean score-5 anchor and above the mostly-efficient score-3.	4 / 5
Actionability	Provides complete, copy-paste-ready functions (save_image, resize_image, get_font) and concrete CLI commands covering the common cases, matching the fully-executable score-5 anchor; not 4 because the examples are complete rather than having minor gaps.	5 / 5
Workflow Clarity	Workflows are sequenced (Logo Cleanup, Hero Image, Batch Process, Gemini pipeline) but batch and destructive operations lack any validation/verification steps, so per the rubric cap workflow_clarity cannot exceed 3; not 4 because the explicit validation checkpoint is absent.	3 / 5
Progressive Disclosure	Well-organized into clear sections (Quick Reference, Prerequisites, Output Format Guide, Core Patterns, Workflows) with no nested references, but the referenced 'img-process' CLI in bin/ is not actually bundled and all content is inline, keeping it just below the score-5 ideal.	4 / 5
	Total	16 / 20 Passed

Description

100%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 exemplary: it enumerates comprehensive concrete capabilities, supplies abundant natural trigger phrases, and clearly states both what the skill does and when to use it. Voice is third-person/imperative with no first/second-person drift.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'resize, crop, trim whitespace, convert formats (PNG/WebP/JPG), optimise file size, generate thumbnails, create OG card images' — giving comprehensive coverage, matching the score-5 anchor rather than the 4 (which expects minor gaps).	5 / 5
Completeness	Explicitly answers both 'what' (the enumerated image operations) and 'when' ('Trigger with ...'), with concrete trigger phrases, matching the score-5 anchor; not 4 because the 'when' is fully explicit rather than improvable.	5 / 5
Trigger Term Quality	Provides nine natural trigger phrases users would actually say ('resize image', 'convert to webp', 'trim logo', 'optimise images', 'make thumbnail', 'create OG image', 'crop whitespace', 'process image', 'image too large'), matching comprehensive-coverage anchor; not 4 because no common variations are missing.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (web image processing via Pillow, 'no ImageMagick needed') with distinct triggers, giving minimal conflict risk; not 4 because the triggers are tightly scoped to this skill's domain.	5 / 5
	Total	20 / 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: jezweb/claude-skills
Path: plugins/design-assets/skills/image-processing/SKILL.md
Commit: ee91a87

Reviewed: 6 days 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.