dpi-upscaler-checker

Check if images meet 300 DPI printing standards, and intelligently restore blurry low-resolution images using AI super-resolution technology.

Quality

63%

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/dpi-upscaler-checker/SKILL.md

Quality

Content

67%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 skill body is well-structured, concise, and provides concrete executable commands backed by a real bundled script, with clear validation-first workflow and fallback handling. The main weakness is actionability: the SKILL.md documents several CLI flags (--json, --demo, --denoise, --face-enhance) that do not exist in the actual scripts/main.py.

Suggestions

Resolve the flag mismatch: either implement --json, --demo, --denoise, and --face-enhance in scripts/main.py or remove them from the Quick Check, Usage, and Parameters sections so documented commands are actually executable.

Add a concrete verify-checkpoint command to the Workflow (e.g. run a check --json on one image and confirm meets_300dpi before batch upscaling) to turn the generic validation step into an explicit validate-then-proceed loop.

Move the algorithm formula and the inlined JSON report schema into a short reference file (or trim them) to push progressive disclosure toward fully one-level-deep organization.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes competence (parameter tables, compact code blocks, terse Known Limitations), with only minor over-explanation such as re-stating the algorithm formula and re-explaining scope handling; matches 'efficient; minor instances that could be trimmed' rather than the perfectly lean 5.	4 / 5
Actionability	Provides concrete executable commands and a real bundled script, but the SKILL.md documents several flags that do not exist in scripts/main.py (--json, --demo, --denoise, --face-enhance), so the guidance is incomplete/unexecutable as written — between the 'mostly executable' 4 and 'incomplete' 3, settling at 3 for the documented-but-absent options.	3 / 5
Workflow Clarity	A clear sequenced Workflow with an explicit validation-first step, a Fallback Behavior loop, and Error Handling guidance is present; it is not a 5 because validation checkpoints are described generically rather than as concrete verify-then-proceed commands tied to the script.	4 / 5
Progressive Disclosure	Well-organized sections with a single real one-level-deep bundle file (scripts/main.py) that is referenced via concrete paths; structure is appropriate with only minor gaps (no separate reference/asset files, and some detail like full JSON schemas is inlined) — matches 'good structure; minor organization gaps'.	4 / 5
	Total	15 / 20 Passed

Description

58%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 with two concrete actions, but omits any explicit 'Use when...' trigger guidance, which the rubric caps at completeness 3. Trigger term coverage is decent but missing common synonyms and file extensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when checking images for 300 DPI print standards, fixing blurry/low-resolution photos, or batch-preparing images for print.'

Include natural user phrases and file extensions (JPG, PNG, TIFF, print-ready, blurry photos) to improve trigger term quality.

Add one more concrete action (e.g. batch folder processing or EXIF/DPI metadata correction) to move specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (DPI checking) and lists two concrete actions ('Check if images meet 300 DPI printing standards' and 'restore blurry low-resolution images using AI super-resolution'), which matches the 'several specific actions; minor gaps' anchor — below 5 because it stops at two actions rather than comprehensive coverage.	4 / 5
Completeness	The 'what' is clearly stated but there is no explicit 'when'/'Use when...' clause, so per the rubric guideline a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant terms ('images', '300 DPI', 'printing standards', 'low-resolution', 'super-resolution') but lacks the natural synonyms and file extensions a user would say (e.g. 'JPG/PNG', 'blurry photos', 'print-ready'), matching 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The 300-DPI print-check + AI super-resolution niche is fairly distinct with low overlap risk against generic image skills, matching 'mostly distinct; minor overlap risk' rather than the fully-delineated 5 anchor.	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/dpi-upscaler-checker/SKILL.md
Commit: 63c61d3

Reviewed: 7 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.