Name: tray
Rating: 54.400000000000006 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

tray

Tray integration. Manage data, records, and automate workflows. Use when the user wants to interact with Tray data.

Quality

61%

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 ./skills/tray/SKILL.md

Quality

Content

61%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 skill body is actionable and well-structured with strong CLI examples, but it is padded with an unnecessary platform intro and its workflow sequencing has a broken step reference plus missing validation for destructive proxy calls. It is solidly above the midpoint with clear room to tighten and harden.

Suggestions

Cut the introductory paragraph describing Tray.io's audience and purpose; assume Claude knows the platform or link the official docs already cited.

Fix the broken "skip to Step 2" reference by numbering the workflow steps explicitly (1. connect, 2. search, 3. run).

Add an explicit validation checkpoint after destructive proxy requests (e.g. verify the response status and resulting resource state before proceeding) to satisfy the destructive-operation feedback-loop requirement.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with code blocks and a flag table, but the opening paragraph explaining what Tray.io is and who uses it ("business users and IT professionals...marketing, sales, and customer support") plus editorializing like "so you can focus on the integration logic rather than auth plumbing" is unnecessary padding.	3 / 5
Actionability	Provides mostly executable, copy-paste-ready commands for install, login, connection, action list/run, and proxy requests with a clear flag table, but placeholders (CONNECTION_ID, actionId, QUERY) require substitution and a few inputs like --clientName=<agentType> are left vague.	4 / 5
Workflow Clarity	A rough sequence exists with a real feedback loop for connection polling (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR), but the body references a "Step 2" that is never labeled, and destructive proxy operations (DELETE/PUT) plus action runs lack explicit result-validation checkpoints.	3 / 5
Progressive Disclosure	The content is well-organized into clearly headed sections (Overview, Working with Tray, Install, Auth, Connecting, Searching, Running, Proxy, Best practices) with no nested references, though some inline detail (the clientAction object breakdown, the proxy flag table) could plausibly live in a separate reference file.	4 / 5
	Total	14 / 20 Passed

Description

62%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 third-person, covers both what and when, and is clearly tied to the Tray platform, but its action language is generic and the trigger terms lack synonyms and breadth. It sits comfortably above the midpoint but below the strongest anchor examples.

Suggestions

Replace generic verbs ("Manage data, records") with concrete Tray-specific actions such as "create and run workflows", "manage workflow versions", or "configure connectors".

Broaden the trigger clause to surface natural variations users would say, e.g. "Use when the user mentions Tray.io, workflow automation, integrations, or connectors".

Add a concrete trigger phrase tied to intent (e.g. "when automating SaaS integrations") to push completeness toward a 5.

Dimension	Reasoning	Score
Specificity	Names the domain ("Tray integration") and a couple of actions ("Manage data, records, and automate workflows"), but the actions are generic rather than concrete like extracting or filling; coverage is not comprehensive.	3 / 5
Completeness	Both a "what" (manage data, records, automate workflows) and an explicit "when" ("Use when the user wants to interact with Tray data") are present, but the trigger phrasing is narrow and could be more specific.	4 / 5
Trigger Term Quality	Relevant keywords ("Tray", "Tray data", "workflows", "records") appear in the trigger clause, but common variations, synonyms, and file/connector terms users might say are missing.	3 / 5
Distinctiveness Conflict Risk	The Tray platform niche is clear and distinct, but the generic "Manage data, records" wording creates minor overlap risk with other data-management skills.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/tray/SKILL.md
Commit: f484c82

Reviewed: 4 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.