markdown-viewer

Create rich diagrams, data visualizations, technical architecture views, and editorial content cards directly in Markdown using the Markdown Viewer Agent Skills pack. Use for Mermaid-like diagram requests, PlantUML architecture diagrams, Vega charts, JSON Canvas maps, infographics, UML, cloud/network/security/data/IoT diagrams, and polished Markdown documentation visuals.

Quality

86%

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

78%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 body is a well-organized routing skill that maps user goals to specific renderers, gives concrete fence rules, and validates syntax before delivery. Its main gaps are the absence of any inline example diagram and a missing explicit fix→retry loop in the validation step.

Suggestions

Add one minimal inline example per major renderer (e.g., a short plantuml block and a vega-lite block) so the output rules are copy-paste ready.

Turn the step-5 syntax check into an explicit feedback loop: "If validation fails, fix the fence/JSON/YAML and re-check before delivery."

Trim the editorial framing sentences ("opinionated skill pack for AI coding agents" and the closing "The value of this skill is that...") to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is lean, well-sectioned, and assumes Claude's competence (no explanations of what diagrams/renderers are), with only minor editorial padding such as "opinionated skill pack for AI coding agents" and "The value of this skill is that..." that could be trimmed.	4 / 5
Actionability	Concrete guidance throughout — a goal→renderer selection table, explicit code-fence rules (vega-lite, infographic, canvas, plantuml/puml), and an executable setup command — but no inline example diagram block, leaving a minor gap versus copy-paste-ready completeness.	4 / 5
Workflow Clarity	A clear 6-step sequence with an explicit syntax-validation checkpoint ("Check syntax before delivery: matching fences, valid JSON/YAML... PlantUML starts and ends correctly"), but it lacks an explicit validate→fix→retry loop; the operation is non-destructive so the destructive-cap does not apply.	4 / 5
Progressive Disclosure	A clean overview (Setup, Skill Selection, Output Rules, Workflow, Delivery) that delegates detailed syntax to well-signaled, one-level-deep references to the upstream pack's SKILL.md, with no nested or buried references and easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

95%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 clearly states what the skill produces, when to use it, and covers a comprehensive set of natural trigger terms and renderer names. The only minor weakness is that the action verbs are broad categories rather than granular operations.

Dimension	Reasoning	Score
Specificity	Lists several specific actions ("rich diagrams, data visualizations, technical architecture views, and editorial content cards"), but they are broad output categories under a single verb rather than the granular distinct operations of the 5-anchor, so minor coverage gaps remain.	4 / 5
Completeness	Explicitly answers both "what" ("Create rich diagrams... directly in Markdown using the Markdown Viewer Agent Skills pack") and "when" ("Use for Mermaid-like diagram requests...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural terms including synonyms and tool names ("Mermaid-like", "PlantUML architecture diagrams", "Vega charts", "JSON Canvas maps", "infographics", "UML", "cloud/network/security/data/IoT diagrams"), matching the 5-anchor's breadth.	5 / 5
Distinctiveness Conflict Risk	A clear niche (Markdown-native visuals via specific renderers) with distinct triggers (Mermaid/PlantUML/Vega/JSON Canvas/UML/cloud/network/security), giving minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 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 — 13 / 16 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: EKKOLearnAI/hermes-studio
Path: packages/skills/markdown-viewer/SKILL.md
Commit: c990be4

Reviewed: ~8 hours 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.