mintlify

Build and maintain documentation sites with Mintlify. Use when creating docs pages, configuring navigation, adding components, or setting up API references.

1.07x

Quality

—

Does it follow best practices?

Impact

97%

1.07x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

87%

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

The body is concise, highly actionable, and well-organized with clear external-reference deferral. Its main gap is workflow clarity: validation/checkpoint steps exist as standalone tools but are not embedded as feedback loops in the configure, document-API, and deploy workflows.

Suggestions

Embed validation checkpoints into workflows — e.g., after editing docs.json or before deploy, instruct: run `mint validate` then `mint broken-links`, fix errors, and only proceed when both pass.

Add an explicit validate→fix→retry feedback loop to the 'Document APIs' and 'Deploy' sections, since these involve config-affecting and outward-facing operations.

Sequence the migration edge case as numbered steps with a verification step (e.g., run `mint broken-links` after converting content to MDX) rather than a single conditional paragraph.

Dimension	Reasoning	Score
Conciseness	Lean, well-structured content using terse tables and bullets ('JSX components need explicit import, MDX components don't'); it avoids re-explaining concepts Claude already knows and every section earns its place.	3 / 3
Actionability	Provides copy-paste-ready specifics — CLI commands ('npm i -g mint', 'mint validate'), config snippets ('"openapi": ["openapi.yaml"]', '"redirects": [{"source": "/old", "destination": "/new"}]'), import syntax, and a file-structure tree — matching the fully-executable score-3 anchor.	3 / 3
Workflow Clarity	Content is organized by domain with decision tables, but validation tools (mint validate, mint broken-links, mint a11y) sit in a quick-reference list rather than woven into the deploy/configure/API workflows as explicit validate-then-fix checkpoints; per the rubric, missing validation steps in config/deploy operations caps this at 2.	2 / 3
Progressive Disclosure	No bundle files exist; the body is a well-organized overview that defers exhaustive detail to clearly signaled one-level-deep external references (mintlify.com/docs, docs.json schema), with clean section navigation — meeting the well-organized-overview bar for score 3.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 concise, third-person, and clearly states both capabilities and explicit 'Use when' triggers. It distinguishes the Mintlify niche well and lists several concrete actions.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'Build and maintain documentation sites', 'creating docs pages, configuring navigation, adding components, or setting up API references' — matching the score-3 anchor rather than the narrower score-2 'some actions'.	3 / 3
Completeness	Explicitly answers both what ('Build and maintain documentation sites with Mintlify') and when ('Use when creating docs pages, configuring navigation, adding components, or setting up API references') with an explicit 'Use when' trigger.	3 / 3
Trigger Term Quality	Covers natural terms users would actually say — 'documentation sites', 'docs pages', 'navigation', 'components', 'API references' — giving good coverage per the score-3 anchor, though it omits a few variations like 'Mintlify' or 'MDX'.	3 / 3
Distinctiveness Conflict Risk	The 'with Mintlify' qualifier plus specific triggers (navigation, components, API references) carve a clear niche unlikely to conflict with unrelated skills.	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
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: Arize-ai/phoenix
Commit: 27a4ecc

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.