ray-skill

Use when user says "send to Ray," "show in Ray," "debug in Ray," "log to Ray," "display in Ray," or wants to visualize data, debug output, or show diagrams in the Ray desktop application.

Quality

80%

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 ./config/claude/skills/ray-skill/SKILL.md

Quality

Content

78%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.

A highly actionable, copy-paste-ready reference for Ray's HTTP API with concrete examples for every payload type. It is slightly held back by duplication between the per-type sections and the summary table, and by the absence of any progressive disclosure to separate reference files.

Suggestions

Move the full "Payload Type Reference" table (or the per-type JSON blocks) into a separate references file and keep only a quick-start example plus a pointer in SKILL.md to reduce duplication and context cost.

Add a brief feedback loop for failed requests (e.g., check the availability endpoint, retry, or surface the HTTP status) to strengthen workflow clarity.

Trim the redundant "Example: Complete Request" section or fold it into "Combining Multiple Payloads" to remove the one notable duplication.

Dimension	Reasoning	Score
Conciseness	The body is lean reference material (JSON payloads and tables) that assumes Claude's competence and avoids explaining concepts, but the final "Payload Type Reference" table and the "Complete Request" curl example duplicate the per-type sections, so it is not fully tight.	4 / 5
Actionability	Fully executable, copy-paste-ready JSON payloads for every payload type plus a complete curl example and a concrete availability-check endpoint, covering the common cases.	5 / 5
Workflow Clarity	The single action (POST to localhost:23517) is unambiguous and the availability check acts as a pre-flight checkpoint, but there is no error-recovery feedback loop for failed requests, keeping it below 5.	4 / 5
Progressive Disclosure	No bundle files exist and the entire ~340-line API reference is inlined in one file with good section headers; the large payload-type reference could be split into a separate reference file, so it is structured but not progressively disclosed.	3 / 5
	Total	16 / 20 Passed

Description

81%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 with excellent, natural trigger phrases and a clear niche. Its main weakness is that the "what" is expressed as goals (visualize/debug/show) rather than the concrete action of sending HTTP requests to Ray's local server.

Suggestions

Lead with a concrete action clause, e.g. "Sends data to Ray's local HTTP server to display values, HTML, tables, and diagrams," so the what is explicit rather than implied by triggers.

Keep the strong "Use when..." trigger list but ensure the action statement is distinct from the trigger list.

Dimension	Reasoning	Score
Specificity	Names the Ray domain and a few actions ("visualize data, debug output, or show diagrams") but these are outcome-oriented rather than concrete operations like sending HTTP payloads, so it sits at the domain-plus-1-2-actions anchor rather than a 4.	3 / 5
Completeness	An explicit "Use when..." clause covers the when thoroughly, and the what is present (visualize/debug/show in the Ray desktop app) but stated as outcomes rather than a distinct concrete action, so it is not quite the fully explicit what-and-when of a 5.	4 / 5
Trigger Term Quality	Comprehensive natural trigger phrases ("send to Ray," "show in Ray," "debug in Ray," "log to Ray," "display in Ray") plus synonyms users would naturally say, matching the full-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	The Ray-specific triggers and named desktop application give it a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: freekmurze/dotfiles
Path: config/claude/skills/ray-skill/SKILL.md
Commit: a7899fe

Reviewed: 3 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.