CtrlK
BlogDocsLog inGet started
Tessl Logo

logo-creator

Create logos using AI image generation. Discuss style/ratio, generate variations, iterate with user feedback, crop, remove background, and export as SVG. Use when user wants to create a logo, icon, favicon, brand mark, mascot, emblem, or design a logo.

85

2.32x
Quality

80%

Does it follow best practices?

Impact

93%

2.32x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

65%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 a well-structured, actionable overview with a clear iterative workflow and real supporting scripts. Its weaknesses are the absence of any validation/verification steps around batch generation and post-processing, and two referenced bundle files (templates/preview.html, examples/opc-logo-creation.md) that do not exist, which break navigation and Step 3 of the workflow.

Suggestions

Add verification checkpoints after risky steps: after batch generation, confirm the expected number of PNG files exist and flag failed API calls; after crop/remove_bg, inspect the output before proceeding to vectorize (the rubric's batch-operation cap is the main workflow_clarity deduction).

Fix broken references: either add templates/preview.html and examples/opc-logo-creation.md to the bundle, or remove the references and inline a minimal preview HTML snippet so Step 3 is self-contained.

Deduplicate content to tighten token use: consolidate the Step 1 aspect-ratio list with the Quick Reference ratio table, and merge 'Prompt Tips' into 'Common Prompt Patterns'; also replace the macOS-only `open` command with a portable fallback (e.g., `xdg-open` on Linux).

DimensionReasoningScore

Conciseness

The body is directive and assumes competence — prerequisites, output conventions, and concrete commands with no concept explanations — matching the efficient anchor 4. It falls short of anchor 5 because of real redundancy: aspect ratios are listed twice (4 options in Step 1, 9 in Quick Reference) and the 'Prompt Tips' section overlaps heavily with the 'Common Prompt Patterns' section, tokens that could be trimmed.

4 / 5

Actionability

Steps 2 and 5 give concrete, mostly copy-paste-ready commands (batch_generate.py, crop_logo.py, remove_bg.py, vectorize.py — all of which exist in scripts/), with example output trees and a naming convention. It is not anchor 5 due to minor gaps: the browser-open step uses macOS-only `open`, and unresolved placeholders like `<nanobanana_skill_dir>` leave small execution details to the reader.

4 / 5

Workflow Clarity

The six-step sequence is clearly ordered with a user feedback loop ('Wait for user confirmation before proceeding!', iterate until user selects final logo), but there are no validation/verification checkpoints anywhere: no check that batch generations succeeded, no verification of crop or background-removal output before vectorizing. The rubric caps batch-operation workflows without validation at 3, so despite good sequencing it cannot score 4.

3 / 5

Progressive Disclosure

Structure is good in intent — a lean overview with one-level-deep references (references/styles.md exists and is real, and the three scripts/ files exist) — but two referenced files are missing from the bundle: templates/preview.html (core to Step 3's workflow) and examples/opc-logo-creation.md. Per the guideline to score against the actual bundle structure, broken navigation for two of four referenced paths is worse than anchor 4's 'minor organization gaps', landing on anchor 3.

3 / 5

Total

14

/

20

Passed

Description

96%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.

A strong description: concrete, third-person action list with an explicit 'Use when' clause and a comprehensive set of natural trigger synonyms. Only weakness is slight overlap risk with general image-generation skills on terms like 'icon' and 'mascot'.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions spanning the whole workflow: "generate variations, iterate with user feedback, crop, remove background, and export as SVG", matching the comprehensive-coverage anchor. The only mildly generic phrase ("Discuss style/ratio") is a minor part of an otherwise complete action list, so it does not drop it to the anchor 4 example of 'minor gaps in coverage'.

5 / 5

Completeness

It explicitly answers both questions: what ("Create logos using AI image generation. Discuss style/ratio, generate variations, ... export as SVG") and when ("Use when user wants to create a logo, icon, favicon, brand mark, mascot, emblem, or design a logo"). This matches the anchor 5 example structure verbatim — clear what plus explicit concrete trigger phrases — so it is neither the weakly-implied 'when' of anchor 3 nor the less-explicit 'when' of anchor 4.

5 / 5

Trigger Term Quality

"Use when user wants to create a logo, icon, favicon, brand mark, mascot, emblem, or design a logo" covers six natural synonyms users would actually say, hitting the comprehensive-synonyms anchor. It is not the anchor 4 case ('a few natural terms missing') because the term family for this domain is thoroughly enumerated; file extensions are irrelevant triggers for logo creation.

5 / 5

Distinctiveness Conflict Risk

Logo creation is a clear niche with distinctive triggers (favicon, emblem, brand mark), but terms like "icon" and "mascot" have minor overlap with general AI image-generation skills, matching anchor 4 ('mostly distinct; minor overlap risk with closely related skills'). It does not reach anchor 5 because the generic image-generation surface it sits on could plausibly claim the same requests; it is well above anchor 3 since the trigger vocabulary is domain-specific, not generic.

4 / 5

Total

19

/

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

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
ReScienceLab/opc-skills
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.