design-md

Author/validate/export Google's DESIGN.md token spec files.

Quality

76%

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/design-md/SKILL.md

Quality

Content

85%

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

The body is highly actionable and well-structured with executable CLI commands and a validated authoring workflow, dropping only on conciseness due to minor explanatory padding and a time-sensitive version note. It is a strong, copy-paste-ready reference.

Suggestions

Move or soften the time-sensitive "version: alpha... as of Apr 2026" note into a dedicated 'Spec version / deprecated' note so it does not penalize conciseness, or trim it to a single fact.

Tighten the opening prose (e.g. "Tokens give exact values. Prose tells agents why...") since Claude already understands the token-vs-rationale split, relying on the anatomy example to convey it.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes competence, but explanatory prose ("Tokens give exact values. Prose tells agents why...") plus time-sensitive detail ("version: alpha is the current spec version (as of Apr 2026)") in Pitfalls rather than a deprecated/old-patterns section pulls it to 'mostly efficient but could be tightened'.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands (e.g. "npx -y @google/design.md lint DESIGN.md" and the export/diff/spec variants) plus a concrete anatomy example, matching the 'fully executable code/commands' anchor.	3 / 3
Workflow Clarity	The authoring workflow is a numbered sequence with an explicit validation checkpoint (step 4: "Lint it... Fix any broken references or WCAG failures before returning") forming a fix-before-return feedback loop, matching the 'clear sequence with explicit validation steps' anchor.	3 / 3
Progressive Disclosure	Content is organized into clear, navigable sections (When to use, File anatomy, Token types, Canonical section order, Workflows, Pitfalls, Spec source of truth) with clearly signaled one-level external source-of-truth links and no nested reference chains; no bundle files are needed.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 specific and clearly niche but omits any explicit trigger guidance and under-covers natural user phrasings, which together cap it below the top level. Adding a Use-when clause and more vernacular terms would raise it.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks for a DESIGN.md file, design tokens, a design system spec, or WCAG/contrast validation on a color palette.'

Broaden trigger terms to natural phrasings users actually say: 'design system', 'design tokens', 'brand/UI tokens', 'lint a design spec', 'export Tailwind/DTCG tokens'.

Keep the third-person imperative voice (already correct) while folding in the trigger terms so both what and when fit one concise line.

Dimension	Reasoning	Score
Specificity	Quotes three concrete actions — "Author/validate/export" — applied to a named domain ("DESIGN.md token spec files"), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly states what the skill does but provides no "Use when..." trigger guidance, so per the guideline a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	Has relevant keywords ("DESIGN.md", "token spec") but misses common user phrasings like "design system", "design tokens", "lint", or "WCAG/accessibility", so it lands at 'some relevant keywords but missing common variations' rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	"Google's DESIGN.md token spec files" is a narrow, format-specific niche unlikely to trigger for unrelated skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 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: NousResearch/hermes-agent
Path: skills/creative/design-md/SKILL.md
Commit: 5be99b6

Reviewed: about 14 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.