claude-design

Design one-off HTML artifacts (landing, deck, prototype).

Quality

55%

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/creative/claude-design/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 content is a well-organized, actionable design doctrine with a strong workflow and feedback loop, but it is lengthy for a single SKILL.md and would benefit from externalizing detail into reference files while trimming restated truisms.

Suggestions

Externalize the long doctrine blocks (e.g. the ten slop tells, the seven surfaces, typography/color/motion) into reference files and leave concise pointers, reducing the body's token load.

Trim sections that re-explain design concepts Claude already knows (anti-slop list, motion-as-discipline) to one-line rules, cutting redundancy between "Anti-Slop Rules" and "Slop Diagnostic".

Add at least one complete minimal HTML artifact skeleton so the executable guidance is copy-paste ready rather than only rule-based.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and actionable, but at ~640 lines it re-states design truisms Claude already knows (generic SaaS tropes, gradient/glassmorphism warnings, motion-as-discipline) and repeats the same anti-slop guidance across multiple sections, fitting anchor 3 (mostly efficient with some tightening possible).	3 / 5
Actionability	It gives concrete, executable guidance throughout — the seven-surface taxonomy with explicit rules, slop self-audit with a 10-tell scoring procedure, deck/prototype/variation rules with specific defaults (1920×1080, 44px hit targets, localStorage) — with only minor gaps (no full HTML scaffolding example), fitting anchor 4.	4 / 5
Workflow Clarity	The numbered Workflow and Slop Diagnostic sections give a clear sequence with an explicit validate/re-score feedback loop ("Diagnose first, treat second... Re-score after repairing") and a Verification section with checkpoints; only minor validation gaps keep it from anchor 5.	4 / 5
Progressive Disclosure	No bundle files exist and the skill is a single self-contained SKILL.md with clear section headers, but the long inlined doctrine (surfaces, slop tells, typography/color/motion) is content that could reasonably live in reference files, and all references are to sibling skills rather than internal detail files, fitting anchor 3.	3 / 5
	Total	14 / 20 Passed

Description

50%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 short and names concrete artifact types, but it omits any explicit "Use when..." trigger guidance and under-specifies the range of design actions, leaving it at the midpoint across all dimensions.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks for a one-off designed HTML artifact — landing page, prototype, deck, or component exploration — in a CLI/API environment."

Broaden action verbs beyond "Design" (e.g. "Design, prototype, and verify one-off HTML artifacts") and add common synonyms like mockup, dashboard, or deck/slide presentation.

Sharpen distinctiveness by contrasting with sibling skills in the description, e.g. "...not for matching a known brand (use popular-web-designs) or authoring a token spec (use design-md)."

Dimension	Reasoning	Score
Specificity	The description names the domain and concrete artifact types ("landing, deck, prototype") but offers only one action verb ("Design") with no broader coverage of what the skill actually does, matching anchor 3.	3 / 5
Completeness	It has a clear "what" (design one-off HTML artifacts) but no "Use when..." clause or equivalent trigger guidance, so per the rubric cap a missing "when" holds it at anchor 3.	3 / 5
Trigger Term Quality	"landing, deck, prototype" are natural terms users say, but coverage is limited to three keywords with no synonyms, related surfaces (prototype, mockup, dashboard), or file extensions, matching anchor 3 rather than the comprehensive 4-5 anchors.	3 / 5
Distinctiveness Conflict Risk	"design one-off HTML artifacts" is somewhat specific but overlaps with sibling design skills (popular-web-designs, design-md) that the body itself acknowledges, fitting anchor 3 rather than the clearly-distinct 4-5 anchors.	3 / 5
	Total	12 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (651 lines); consider splitting into references/ and linking	Warning
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	12 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/creative/claude-design/SKILL.md
Commit: fcbd107

Reviewed: about 19 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.