hex

Search Hex projects and ask Hex Threads questions. Use when the user explicitly references Hex, Hex projects, Hex dashboards, Hex data apps, Hex Threads, or asks to search an existing Hex workspace asset.

Quality

100%

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

Quality

Content

100%Weight 40%Scale 1-3

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 concise, well-structured routing-and-tool skill: a numbered workflow with explicit confirmation and polling checkpoints for writes, concrete tool names, realistic example prompts, and clearly separated negative cases. No bundle files are needed and none are missing.

Dimension	Reasoning	Score
Conciseness	The body is lean and never explains concepts Claude already knows; it assumes competence and each section (Workflow, Good Fits, Negative Cases, Safety) earns its place. Minor routing-rule repetition across the opening, step 1, and Negative Cases is reinforcing rather than padding.	3 / 3
Actionability	Names concrete, callable tools — search_projects, get_thread, create_thread, continue_thread — with the connector link, plus concrete example prompts in Good Fits. Guidance is specific and copy-paste usable rather than abstract.	3 / 3
Workflow Clarity	A clearly numbered 5-step sequence with an explicit write checkpoint: 'tell the user what prompt will be sent... ask for confirmation' and a feedback loop of polling get_thread 'until the thread is complete'. Write operations are not left ungated.	3 / 3
Progressive Disclosure	A compact single-file skill with no need for external references; content is organized into well-signaled sections (Workflow, Good Fits, Negative Cases, Safety), satisfying the simple-skill allowance for a top score.	3 / 3
	Total	12 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 tight, well-constructed description: it states two concrete capabilities, gives an explicit 'Use when' trigger enumerating the natural Hex terms a user would say, and carves out a distinct niche. Third-person voice is maintained throughout.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions tied to specific Hex surfaces — 'Search Hex projects' and 'ask Hex Threads questions' — rather than vague abstractions.	3 / 3
Completeness	Explicitly answers both what (search projects, ask Threads questions) and when via a 'Use when the user explicitly references...' trigger clause.	3 / 3
Trigger Term Quality	Covers natural terms a user would actually say — 'Hex projects', 'Hex dashboards', 'Hex data apps', 'Hex Threads', and 'search an existing Hex workspace asset'.	3 / 3
Distinctiveness Conflict Risk	Targets a clearly named product with product-specific triggers, making collision with generic analytics/data skills unlikely.	3 / 3
	Total	12 / 12 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
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: openai/plugins
Path: plugins/hex/skills/hex/SKILL.md
Commit: 11c74d6

Reviewed: 17 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.