design-md

Create and manage DESIGN.md files. Useful for capturing design direction, tokens, and visual rules in a single source of truth.

Quality

44%

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/design-md/SKILL.md

Quality

Content

36%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 lightweight catalogue stub that advertises the skill and points off-site rather than providing the actual workflow, code, or references, leaving it short but thin on actionable guidance and sequence.

Suggestions

Inline a minimal concrete workflow (e.g. a sample DESIGN.md template or a create/update command sequence) so the skill is usable without fetching the upstream bundle.

Replace the non-executable `open https://...` with actual shell commands (e.g. `git clone`, install path, invocation command) for actionability.

Add explicit numbered steps with at least a basic verification checkpoint so the install-and-invoke sequence is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is short and mostly unpadded, but it restates the frontmatter description, repeats the upstream URL, and spends lines explaining catalogue mechanics that add little new information, so it is mostly efficient with some slack.	3 / 5
Actionability	Guidance is high-level: it tells the agent to inspect an upstream README and 'ask the agent to invoke' the skill, with only a single non-executable `open` command, so it gives hints but not the concrete steps to actually run the workflow.	2 / 5
Workflow Clarity	A rough install-then-invoke sequence is present but steps are poorly defined with no commands, paths, or validation; it does not rise to anchor 3 because there are no concrete listed steps, and it does not fall to 1 because a rough order exists.	2 / 5
Progressive Disclosure	It has clear section headers and points to one external resource (the upstream repo), but the detailed workflow lives entirely off-site with no local references, scripts, or assets, so structure exists but the substantive material is not locally disclosed.	3 / 5
	Total	10 / 20 Passed

Description

53%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 clearly identifies its niche (DESIGN.md authoring for design systems) but stops short of listing concrete actions and omits an explicit 'Use when...' trigger clause, leaving it competent yet incomplete.

Suggestions

Add concrete actions (e.g. 'Create, update, and validate DESIGN.md files') to raise specificity toward anchor 5.

Append an explicit 'Use when...' clause naming natural trigger scenarios (design system setup, token capture, visual rule documentation).

Include common synonyms like 'design system', 'brand tokens', or '.md design doc' to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (DESIGN.md files) and one concrete action ("capturing design direction, tokens, and visual rules"), but offers no specific operations like create, update, parse, or validate, so it sits between anchor 3 and the more comprehensive anchor 4.	3 / 5
Completeness	It gives a clear "what" but no "Use when..." clause equivalent; the "when" is only weakly implied via the trigger phrases, so per the guideline a missing explicit trigger guidance caps completeness at 3.	3 / 5
Trigger Term Quality	Includes relevant terms ("design.md", "design tokens doc", "visual rules doc") but lacks common natural variations and synonyms users might say (e.g. "design system", "brand tokens"), fitting the anchor where some relevant keywords are missing.	3 / 5
Distinctiveness Conflict Risk	"DESIGN.md files" plus design-tokens/visual-rules framing carves a clear niche distinct from generic design skills, with only minor overlap risk against broader design-system skills, matching anchor 4.	4 / 5
	Total	13 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: skills/design-md/SKILL.md
Commit: 1a7a23d

Reviewed: about 5 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.