design-spec

How to author a DESIGN.md file — the machine-readable design-token + human-rationale format that must exist before any UI is built. YAML front-matter token schema (colors, typography, spacing, rounded, components), type system, token references, and canonical section order.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/design-spec/SKILL.md

Quality

Content

80%

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

The body is concise, concrete, and well-structured as a specification, but its workflow lacks explicit validation checkpoints and it leans heavily on a referenced collection.md that is not bundled.

Suggestions

Add an explicit validation/verification step to the Workflow (e.g., 'Confirm no duplicate section headings and that all token references resolve to a primitive') referencing the §6 consumer-behavior rules.

Bundle collection.md or replace the 'ALWAYS read collection.md first' instruction with self-contained guidance so the skill is not dependent on a missing file.

Clarify the status of the referenced .agents/rules/design-rules.md gate so Claude knows whether to expect it.

Dimension	Reasoning	Score
Conciseness	The body is lean — tables for the type system, sections, and consumer behavior plus compact token-schema and minimal-example blocks — with no padding or explanation of concepts Claude already knows, matching the 'every token earns its place' anchor.	3 / 3
Actionability	Gives concrete, copy-paste-ready guidance: exact YAML property names, value formats, a full minimal example, and a numbered workflow, fitting the 'fully executable / specific examples' anchor for an instruction/spec skill.	3 / 3
Workflow Clarity	The Workflow section lists a clear 5-step sequence, but contains no explicit validation checkpoint or feedback loop (e.g., confirm token references resolve, check for duplicate section headings), fitting the 'sequence present but checkpoints missing or implicit' anchor rather than the level above.	2 / 3
Progressive Disclosure	Sections are well organized and collection.md is signaled as a one-level-deep reference, but the skill directs Claude to "ALWAYS read collection.md first" and that bundle file does not exist, so the promised navigation is broken, fitting the 'references present but navigation compromised' level rather than 3.	2 / 3
	Total	10 / 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 occupies a distinct niche, but its trigger guidance is implicit rather than an explicit 'Use when' clause and it omits common natural variations of the trigger terms.

Suggestions

Add an explicit "Use when ..." clause naming concrete triggers (e.g., "Use when creating or updating a DESIGN.md, defining design tokens, or starting any UI build").

Broaden trigger keywords to include natural phrases like "design system", "brand colors", and "style guide".

Keep the enumerated capability list but lead with the action verb in third person so the trigger reads naturally.

Dimension	Reasoning	Score
Specificity	Enumerates concrete specifics — "YAML front-matter token schema (colors, typography, spacing, rounded, components), type system, token references, and canonical section order" — matching the anchor for listing multiple specific concrete items.	3 / 3
Completeness	Clearly states what the skill does (authoring a DESIGN.md format) but lacks an explicit "Use when..." clause; the "must exist before any UI is built" phrasing is a requirement, not a trigger, so per the guideline completeness caps at 2.	2 / 3
Trigger Term Quality	Contains relevant terms ("DESIGN.md", "design-token", "UI") that practitioners would say, but misses common variations like "design system", "brand colors", or "style guide", fitting the 'some relevant keywords but missing variations' anchor.	2 / 3
Distinctiveness Conflict Risk	DESIGN.md authoring is a clear, narrow niche with distinct triggers unlikely to collide with other 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 missing	Warning

	Total	13 / 16 Passed

Repository: vudovn/ag-kit
Path: .agents/skills/design-spec/SKILL.md
Commit: 04514f0

Reviewed: about 13 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.