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

59%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./config/claude/skills/ray-skill/SKILL.md

Quality

Content

64%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a solid, highly actionable reference skill that provides everything needed to interact with Ray's HTTP API. Its main weakness is verbosity from repeated boilerplate (origin objects in every example) and a monolithic structure that could benefit from splitting detailed payload types into a separate reference file. The workflow could be slightly improved with an explicit sequence at the top.

Suggestions

Reduce repetition by defining the origin object once and using a comment like `"origin": { /* see above */ }` in subsequent examples, saving significant tokens.

Add a brief 2-3 step workflow at the top: 1) Check availability, 2) Construct request, 3) POST to Ray — to make the overall process clearer.

Consider moving the detailed payload type examples into a separate PAYLOADS.md reference file, keeping only the most common types (log, table, custom) inline in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient as a reference document, but there's significant repetition — the origin object is repeated verbatim in every single payload example, and the payload type reference table at the end duplicates information already shown in detail above. The content could be tightened by showing origin once and using a shorthand notation.	2 / 3
Actionability	Fully actionable with concrete, copy-paste ready JSON payloads for every type, a complete curl example, and specific connection details. Claude can immediately construct and send HTTP requests to Ray without any ambiguity.	3 / 3
Workflow Clarity	The availability check is mentioned but not integrated into a clear workflow sequence (e.g., 'check availability first, then send'). The combining payloads section explains the UUID reuse concept but lacks an explicit step-by-step workflow. For a reference-style skill this is acceptable but could benefit from a brief ordered workflow at the top.	2 / 3
Progressive Disclosure	The content is well-structured with clear headers and tables, but it's a long monolithic document (~200+ lines of payload examples) with no references to external files. The detailed payload examples could be split into a separate reference file, keeping SKILL.md as a concise overview with the most common patterns.	2 / 3
	Total	9 / 12 Passed

Description

54%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is heavily weighted toward trigger terms and 'when to use' guidance but almost entirely neglects describing what the skill actually does. It reads more like a routing rule than a skill description. The trigger term coverage is strong, but the lack of concrete capability descriptions significantly weakens its overall quality.

Suggestions

Add specific capability descriptions before the trigger clause, e.g., 'Sends variables, debug output, log messages, and diagram visualizations to the Ray desktop application for inspection.'

Include concrete actions the skill performs, such as 'formats data for Ray display, generates ray() calls, renders Mermaid diagrams in Ray, logs exceptions with stack traces.'

Briefly mention supported data types or use cases (e.g., 'Supports strings, arrays, objects, Eloquent models, and custom payloads') to strengthen the 'what' dimension.

Dimension	Reasoning	Score
Specificity	The description lacks concrete actions. It does not describe what the skill actually does — there are no specific capabilities listed like 'sends variables to Ray', 'displays debug output', or 'renders diagrams'. The 'what' is almost entirely absent, replaced by vague phrases like 'visualize data' and 'debug output'.	1 / 3
Completeness	The 'when' is explicitly and thoroughly covered with multiple trigger phrases. However, the 'what' — what the skill actually does — is barely addressed. There's no explanation of the concrete actions or capabilities the skill provides, only the triggers for when to use it.	2 / 3
Trigger Term Quality	Excellent coverage of natural trigger phrases users would say: 'send to Ray,' 'show in Ray,' 'debug in Ray,' 'log to Ray,' 'display in Ray,' plus broader terms like 'visualize data,' 'debug output,' and 'show diagrams.' These are highly natural and varied.	3 / 3
Distinctiveness Conflict Risk	The repeated mention of 'Ray' and 'Ray desktop application' provides some distinctiveness. However, generic terms like 'visualize data,' 'debug output,' and 'show diagrams' could overlap with other debugging or visualization skills. The Ray-specific phrases help but the broader terms introduce conflict risk.	2 / 3
	Total	8 / 12 Passed

Validation

81%

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 — 9 / 11 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	9 / 11 Passed

Repository: freekmurze/dotfiles
Commit: ef5ffa0

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.