enhance-prompt

Improve prompts with design specs and UI/UX vocabulary. Useful for design-to-code workflows and clarifying requests for visual output.

Quality

53%

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/enhance-prompt/SKILL.md

Quality

Content

53%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 lean and well-structured as a catalogue entry that points to an upstream bundle, with clean sections and a clearly signaled external reference. Its main weakness is actionability: it gives high-level pointers and a browser-open command instead of an executable install path or concrete prompt-enhancement guidance.

Suggestions

Provide the actual install command (e.g. a git clone or package-manager command into the skills directory) instead of only 'open'ing the upstream README, so the user can execute the setup directly.

Add a brief, concrete example of what the skill does once invoked (e.g. a before/after prompt snippet showing design specs and UI/UX vocabulary injected), so the body is actionable on its own.

Either bundle the key upstream references locally and link to them one level deep, or explicitly state that the upstream README is the authoritative source for steps, to make the off-site dependency clearer.

Dimension	Reasoning	Score
Conciseness	The body is short and free of padding about concepts Claude already knows, with clear sections and only minor redundancy (the 'What it does' section restates the frontmatter description verbatim), matching 'efficient; minor instances of over-explanation that could be trimmed'. It is not 5 because that verbatim repeat and the prose 'How to use' paragraph could be tightened further.	4 / 5
Actionability	Concrete executable guidance is minimal: rather than an install command or prompt-enhancement steps, it offers a high-level hint ('install the upstream bundle into your active agent's skills directory') and a command that only opens a browser ('open https://github.com/google-labs-code/skills'), fitting 'minimal concrete guidance; high-level hints but missing the specific steps to execute'. It is above 1 because at least one concrete command and a named invocation path are given.	2 / 5
Workflow Clarity	A rough two-step sequence is present (install the upstream bundle, then invoke by name or trigger phrase), but the install step is undefined with no command or checkpoint, matching 'steps listed but validation gaps; sequence present but checkpoints missing or implicit'. The operation is non-destructive so the destructive cap does not apply; it is not 4 because the key install step lacks specifics.	3 / 5
Progressive Disclosure	The body is well organized into clear sections (What it does, Source, How to use) and signals a single one-level-deep reference (the upstream repo URL), matching 'good structure; most content is appropriately placed; references mostly clear'. It is not 5 because all real content lives off-site at an external URL rather than in bundled local references, which is less ideal than one-level-deep local files.	4 / 5
	Total	13 / 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 is concise and names a clear, fairly distinct niche, but its actions are generic and the 'when' guidance is a soft 'Useful for' rather than an explicit 'Use when' clause. Trigger-term coverage is moderate, missing common natural phrasings a user might say.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggering situations, e.g. 'Use when the user asks to refine or rewrite a prompt for UI/design output, design-to-code generation, or visual artifact creation.'

Replace generic verbs ('Improve', 'clarifying') with more specific actions, e.g. 'Injects design-system specs, UI/UX terminology, and visual-output constraints into prompts.'

Broaden trigger terms with natural synonyms users actually say, such as 'refine prompt', 'rewrite prompt', 'design prompt', 'UI prompt', and 'make my prompt more visual'.

Dimension	Reasoning	Score
Specificity	The description names the domain ('design specs and UI/UX vocabulary') and two actions ('Improve prompts', 'clarifying requests for visual output'), but the verbs are generic rather than concrete, matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor. It sits below 4 because the actions lack specific, varied coverage and above 2 because two distinct actions and a clear domain are present.	3 / 5
Completeness	It states the 'what' ('Improve prompts with design specs and UI/UX vocabulary') and a soft 'when' ('Useful for design-to-code workflows and clarifying requests for visual output'), but the trigger guidance uses 'Useful for' rather than an explicit 'Use when...' clause and the scenarios are somewhat generic, matching 'clear what but when is only weakly implied'. It is not 4 because the when-clause is not in canonical 'Use when' form and could be more explicit and specific.	3 / 5
Trigger Term Quality	Relevant keywords appear ('prompts', 'design specs', 'UI/UX', 'design-to-code workflows', 'visual output'), but common natural variations a user might say ('refine prompt', 'rewrite prompt', 'make my prompt better for UI') are missing, fitting 'some relevant keywords but missing common variations or synonyms'. It does not reach 4 because the term set is moderate and slightly jargon-leaning rather than broad.	3 / 5
Distinctiveness Conflict Risk	The niche is clear and fairly distinct (design/UI/UX prompt enhancement for design-to-code workflows), with minor overlap risk only against closely related design or prompt-engineering skills, matching 'mostly distinct; minor overlap risk'. It is not 5 because the trigger phrasing is not maximally distinct and could still brush against general prompt-improvement skills.	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/enhance-prompt/SKILL.md
Commit: 1a7a23d

Reviewed: about 4 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.