CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dpi-upscaler-checker

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

Quality

73%

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 ./scientific-skills/Other/dpi-upscaler-checker/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 executable commands, complete parameter references, demo mode, and explicit error/fallback handling. Its weaknesses are padded generic boilerplate in the Workflow/Response Template sections and a dangling requirements.txt reference; the core operational content is excellent.

Suggestions

Remove the generic agent-safety filler — the "Response Template" section and Workflow steps 2-4 ("Confirm the user objective...", "Return a structured result that separates assumptions...") — which restate default agent behavior and waste context tokens.

Fix the dangling reference: either add a requirements.txt to the bundle or replace "pip install -r requirements.txt" with an explicit "pip install Pillow opencv-python numpy" line matching the listed dependency versions.

Move changelog-style notes out of Known Limitations (e.g., "bare except replaced with specific exception types") and keep only operational limitations that affect usage decisions.

DimensionReasoningScore

Conciseness

The usage, parameter, and output sections are tight, but the body carries generic agent boilerplate Claude doesn't need — "Confirm the user objective, required inputs, and non-negotiable constraints", "Return a structured result that separates assumptions, deliverables, risks, and unresolved items", the "Response Template" (Objective/Inputs Received/Assumptions...), and a changelog-style note ("bare except replaced with specific exception types"). This fits anchor 3 (mostly efficient but includes some unnecessary explanation), not anchor 4, because the padding spans several sections.

3 / 5

Actionability

Fully executable, copy-paste-ready commands throughout: "python scripts/main.py check --input image.jpg --json", complete parameter tables for both subcommands, a concrete JSON output schema, a "--demo" mode requiring no real images, and a manual fallback ("from PIL import Image; img = Image.open('file.jpg'); print(img.info.get('dpi'))"). Common cases (single, batch, demo) are all covered — matches anchor 5.

5 / 5

Workflow Clarity

There is a real sequence with explicit checkpoints: "Validate input first — confirm the request is within scope", the Quick Check verification commands (py_compile, --help, Pillow import), "If scripts/main.py fails... switch to the fallback path and state exactly what blocked full completion", and "Script exits with non-zero code on error in both check and upscale modes". However, Workflow steps 2-4 are generic filler rather than task-specific sequencing, so it sits at anchor 4 rather than 5.

4 / 5

Progressive Disclosure

The bundle delegates implementation to scripts/main.py (verified to exist) with well-organized inline sections for usage, parameters, output, and limitations. However, the body instructs "pip install -r requirements.txt" while no requirements.txt exists in the bundle — a dangling reference — keeping it at anchor 4 (good structure, minor organization gaps) rather than 5.

4 / 5

Total

16

/

20

Passed

Description

61%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 communicates two concrete, well-qualified capabilities in a specific niche, but it omits any 'Use when...' trigger guidance and misses common trigger terms like "upscale". Adding an explicit when-to-use clause and the upscaling vocabulary would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions DPI, print quality/resolution requirements, blurry or low-resolution images, or asks to upscale/enlarge images for printing."

Include the natural verbs users actually say — "upscale", "enlarge", "increase resolution" — and common image formats (JPG, PNG, TIFF) as trigger terms.

Drop the filler adverb "intelligently" and spend those tokens naming a third concrete capability (e.g., batch-processing folders) to improve specificity.

DimensionReasoningScore

Specificity

Names the domain with two concrete actions — "Check if images meet 300 DPI printing standards" and "restore blurry low-resolution images using AI super-resolution" — but coverage stops there (no batch or output-format capabilities). This matches anchor 3 (1-2 concrete actions, not comprehensive) rather than anchor 4, which expects several listed actions; "intelligently" is mild fluff.

3 / 5

Completeness

The "what" is clear and concrete, but there is no "Use when..." clause or equivalent explicit trigger guidance anywhere in the description. Per the judging guidelines, a missing 'when' caps completeness at 3 even with a clear 'what'.

3 / 5

Trigger Term Quality

Natural terms include "images", "300 DPI", "printing standards", "blurry", "low-resolution", "restore", and "super-resolution" — a user asking "is this 300 DPI?" or "fix this blurry image" would hit them. Missing the very common verbs "upscale/upscaling" and file extensions, so it falls short of anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The "300 DPI printing standards" + "AI super-resolution" framing carves a mostly distinct niche with specific triggers, but there is minor overlap risk with general image-enhancement or image-conversion skills, keeping it below anchor 5's clear-niche bar.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

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.