x-card

Use when building AI-driven UIs with @ant-design/x-card — covers XCard.Box, XCard.Card, A2UI v0.9 commands, data binding, catalogs, actions, and streaming patterns.

Quality

85%

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

81%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 well-organized, highly actionable skill body with a clear workflow and good progressive-disclosure signaling. It is held back from a top score by missing bundle reference files and the absence of explicit validation checkpoints in the workflow.

Suggestions

Add the referenced reference/*.md files (USAGE.md, COMMANDS.md, DATA_BINDING.md, ACTIONS.md, CATALOG.md, API.md) to the bundle so the signaled progressive-disclosure links resolve.

Add an explicit validation checkpoint in the Recommended Workflow — e.g. validate the catalog/component tree before mounting, or check command versioning — with a fix-and-retry loop for command rejection.

Trim or move the inline ActionPayload JSDoc and architecture ASCII tree into API.md to reduce token cost for the common path.

Dimension	Reasoning	Score
Conciseness	Largely efficient with focused prop tables and a copy-paste example, but the inline TypeScript interfaces, architecture ASCII tree, and the verbose ActionPayload doc comment add some over-explanation that could be trimmed or moved to API.md.	4 / 5
Actionability	Provides a fully executable minimal example plus concrete exports, prop interfaces, install command, and a decision table pointing to specific reference files — copy-paste ready and covering common cases.	5 / 5
Workflow Clarity	A clear 5-step Recommended Workflow sequence exists with the minimal example illustrating it, but there are no explicit validation/verification checkpoints or error-recovery feedback loops (e.g. validating a catalog or command before rendering).	4 / 5
Progressive Disclosure	Well-structured overview with a quick-start decision table and clearly signaled one-level-deep reference links (reference/*.md), but the referenced files do not actually exist in the bundle, so navigation lands on missing resources.	4 / 5
	Total	17 / 20 Passed

Description

88%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 that is specific, complete, and clearly distinct from sibling skills, anchored by an explicit 'Use when...' trigger tied to a concrete package. Slightly more natural-language synonyms would push trigger_term_quality to a perfect score.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — XCard.Box, XCard.Card, A2UI commands, data binding, catalogs, actions, and streaming — with comprehensive coverage rather than generic phrasing.	5 / 5
Completeness	Explicitly answers 'what' (covers the listed capabilities) and 'when' ('Use when building AI-driven UIs with @ant-design/x-card') with a concrete trigger phrase.	5 / 5
Trigger Term Quality	Includes natural terms like 'building AI-driven UIs', 'streaming patterns', and the package name, but omits common synonyms users might say (e.g. 'chat UI', 'agent UI', 'card') and file extension forms.	4 / 5
Distinctiveness Conflict Risk	The narrow @ant-design/x-card package scope and specific A2UI terminology create a clear niche with minimal overlap risk against sibling x-* skills.	5 / 5
	Total	19 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 14 missing	Warning

	Total	14 / 16 Passed

Repository: modelscope/ms-agent
Path: .agents/skills/x-card/SKILL.md
Commit: a56afcc

Reviewed: 2 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.