ray-so-code-snippet

Generate beautiful code snippet images using ray.so. This skill should be used when the user asks to create a code image, code screenshot, code snippet image, or wants to make their code look pretty for sharing. Saves images locally to the current working directory or a user-specified path.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/ray-so-code-snippet/skills/SKILL.md

Quality

Content

71%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 fully executable commands and a clear step sequence, but it suffers from significant duplication (the Complete Example restates the workflow verbatim) and a monolithic single-file structure that inlines content better suited to reference files. Workflow validation exists at the edges (availability check, troubleshooting) but not as inline checkpoints.

Suggestions

Remove or drastically trim the 'Complete Example' section — it duplicates Steps 4-5 almost line for line; a short reference back to the workflow steps would save ~80 lines.

Add a lightweight output validation checkpoint after capture (e.g., verify the PNG file is non-empty or decodable) before reporting success in Step 6.

Move the Troubleshooting section and full worked example into a reference file (e.g., references/examples.md) to reduce the monolithic SKILL.md body and improve navigation.

Dimension	Reasoning	Score
Conciseness	The body is mostly concrete commands, but the 'Complete Example' section repeats Steps 4-5 nearly verbatim (~80 duplicated lines) and 'Image Resolution and Quality' restates Step 5's critical notes, so it could be meaningfully tightened. This matches anchor 3 rather than 4 because the duplication is substantial, and is above anchor 2 since most content is actionable rather than padded explanation.	3 / 5
Actionability	Every step ships copy-paste-ready bash: exact curl pipelines, URL construction with a fully worked example, complete agent-browser commands with session handling, and base64-to-PNG conversion. This matches anchor 5 (fully executable, covers common cases).	5 / 5
Workflow Clarity	A clear 6-step sequence with an upfront availability check (which agent-browser) and a troubleshooting section with fallback defaults and error recovery. It falls short of anchor 5 because validation is not embedded as checkpoints in the flow — e.g., there is no step verifying the saved PNG is non-empty/valid before reporting success, and Step 6 explicitly forbids further verification.	4 / 5
Progressive Disclosure	A single ~320-line monolithic file with no bundle files (references/scripts/assets absent); the complete worked example and troubleshooting are inlined where splitting them into reference files would aid navigation. This fits anchor 3 (some structure, content that could be separate is inline) rather than 4, since the length makes the organization gaps more than minor.	3 / 5
	Total	15 / 20 Passed

Description

82%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 strong: it clearly states what the skill does, when to use it, and where output is saved, with natural trigger phrases. The main weakness is specificity — it names only the single core action rather than enumerating capabilities.

Dimension	Reasoning	Score
Specificity	The description names the domain ('code snippet images using ray.so') and one concrete action (generate images) plus where they are saved, but does not list several specific actions or comprehensive coverage, matching anchor 3. It is above anchor 2 because the action is concrete rather than generic.	3 / 5
Completeness	It explicitly answers both 'what' ('Generate beautiful code snippet images using ray.so... Saves images locally') and 'when' ('This skill should be used when the user asks to create a code image, code screenshot...'), with concrete trigger phrases matching anchor 5. Not 4 because the 'when' clause is fully explicit, not just implied or partial.	5 / 5
Trigger Term Quality	Good natural keyword coverage including 'code image', 'code screenshot', 'code snippet image', and 'make their code look pretty for sharing'. A few natural variants (e.g., sharing code on social media, pretty code photo) are missing, so it fits anchor 4 rather than 5's comprehensive synonym/extension coverage.	4 / 5
Distinctiveness Conflict Risk	A clear niche (ray.so code snippet image generation) with distinct, specific trigger phrases and minimal overlap risk with other skills, matching anchor 5. Not 4 since the triggers are unlikely to pull in a wrong skill.	5 / 5
	Total	17 / 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: intellectronica/agent-skills
Path: plugins/ray-so-code-snippet/skills/SKILL.md
Commit: 9b0e00a

Reviewed: 5 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.