image-processing

Batch-convert and compress local images with Pillow; use when you need an offline, scriptable pipeline for directory-based processing.

Quality

61%

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 ./scientific-skills/Other/image-processing/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 executable code and clean references, but it is weighed down by generic boilerplate sections and a mismatched Quick Validation block, and it lacks a real validation feedback loop for a batch operation.

Suggestions

Remove or drastically trim the generic boilerplate sections (When Not to Use, Required Inputs, Output Contract, Validation and Safety Rules, Failure Handling) that restate obvious cautions not specific to image processing.

Fix the Quick Validation block so its expected output matches the script's actual JSON summary, and add a real validate->fix->retry loop for batch failures to raise workflow clarity above 3.

Move extended usage variants into references/examples.md and keep SKILL.md a lean overview to improve conciseness and progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is noticeably padded with generic boilerplate sections ("When Not to Use", "Validation and Safety Rules", "Failure Handling", "Output Contract") that restate obvious cautions unrelated to image processing, plus a fabricated "Quick Validation" expected output, matching anchor 2's "several unnecessary explanations or padded sections" rather than the tighter anchor 3.	2 / 5
Actionability	It provides a copy-paste-ready command, a real executable script with argparse flags, a requirements file, and an examples.md covering the common conversion cases, fully matching anchor 5.	5 / 5
Workflow Clarity	For a batch operation the rubric caps workflow clarity at 3 when validation/feedback loops are missing; the documented workflow only runs `--help` and shows a fabricated expected output that does not match the script's JSON summary, with no real validate->fix->retry loop.	3 / 5
Progressive Disclosure	SKILL.md is a well-structured overview with one-level-deep, real references (scripts/convert_images.py, scripts/requirements.txt, references/examples.md), matching anchor 4; it stops short of 5 because the generic boilerplate sections bloat the overview rather than being trimmed or split.	4 / 5
	Total	14 / 20 Passed

Description

62%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 clearly states what the skill does and when to use it with a distinct offline-imaging niche, but it lists only two actions and lacks the natural user synonyms and concrete triggers that would raise specificity and trigger-term quality.

Suggestions

Add more concrete actions (e.g., convert formats, resize, compress) to lift specificity toward 4-5.

Include natural user phrases and file extensions ("compress images", "convert to WebP", .png/.jpg/.webp) to improve trigger-term coverage.

Make the "use when" clause more concrete (e.g., "Use when you need to batch convert a folder of PNG/JPG photos to WebP for the web") to reach completeness 5.

Dimension	Reasoning	Score
Specificity	"Batch-convert and compress local images with Pillow" names the domain plus two concrete actions, matching anchor 3; it does not list the several distinct actions needed for a 4.	3 / 5
Completeness	It states a clear "what" and an explicit "use when" clause, satisfying anchor 4; the "when" trigger is somewhat abstract ("offline, scriptable pipeline") rather than the concrete trigger phrases required for 5.	4 / 5
Trigger Term Quality	Phrases like "local images", "offline", "scriptable pipeline", and "directory-based processing" are relevant but miss common user synonyms such as "compress", "resize", "WebP", or file extensions, fitting anchor 3 rather than the fuller coverage of 4.	3 / 5
Distinctiveness Conflict Risk	"Local images with Pillow", "offline", and "directory-based processing" carve a mostly distinct niche with minor overlap risk (anchor 4), but the triggers are less concrete than the anchor 5 example.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Other/image-processing/SKILL.md
Commit: f5ef65b

Reviewed: ~15 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.