Tessl • The management layer for AI agent skills

SkillPublic

interface-design

This skill is for interface design — dashboards, admin panels, apps, tools, and interactive products. NOT for marketing design (landing pages, marketing sites, campaigns).

Quality

61%

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 ./.agents/skills/frontend-design/SKILL.md

Quality

Content

48%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 contains genuinely useful craft guidance and a clear workflow with validation checkpoints, but it is weighed down by verbose motivational essays and references three files that are not present in the bundle. Trimming the prose and providing the referenced files would materially improve it.

Suggestions

Move the essay-style sections ("Where Defaults Hide", "Sameness Is Failure", "The Problem") into a reference file or compress them to bullet points so SKILL.md stays lean.

Provide the referenced files (references/principles.md, references/validation.md, references/critique.md) or remove the Deep Dives links to avoid broken references.

Front-load the concrete templates (checkpoint block, required outputs, suggest+ask format) above the philosophical framing so actionable guidance is immediately reachable.

Dimension	Reasoning	Score
Conciseness	Large essay-style sections ("The Problem", "Where Defaults Hide", "Sameness Is Failure", "Intent Must Be Systemic") repeat motivational themes and could be substantially tightened without losing guidance, matching the 'noticeably verbose; several padded sections' anchor rather than the mostly-efficient anchor at 3.	2 / 5
Actionability	Concrete templates exist (the Before-Writing-Each-Component checkpoint block, the required four exploration outputs with minimums, the suggest+ask format) but they are interleaved with abstract philosophical direction; as an instruction-only skill code absence is not penalized, yet the guidance is only partially executable.	3 / 5
Workflow Clarity	The 'If No system.md' section gives a clear sequence (explore → propose → confirm → build → evaluate → save) with the Mandate checks as an explicit validation checkpoint before presenting output, matching the 'clear sequence with most checkpoints' anchor.	4 / 5
Progressive Disclosure	The Deep Dives section signals one-level-deep references (principles.md, validation.md, critique.md) clearly, but those files do not exist in any references/ directory and much of the philosophical content that could be split out remains inline, so structure is only partially realized.	3 / 5
	Total	12 / 20 Passed

Description

56%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 draws a clear boundary between interface and marketing design and uses natural trigger terms, but it lacks concrete action verbs and an explicit 'Use when' trigger clause. Tightening it to name specific actions and add trigger phrasing would raise the capped completeness score.

Suggestions

Replace the static 'This skill is for interface design' framing with concrete action verbs (e.g., 'Design and build dashboards, admin panels, and interactive product UIs').

Add an explicit 'Use when...' clause with trigger phrases users would naturally say (e.g., 'Use when building dashboards, admin panels, SaaS tools, or data interfaces').

Narrow the broad 'apps, tools' scope or tie it to interface-specific contexts to reduce overlap with general frontend/design skills.

Dimension	Reasoning	Score
Specificity	The description names the domain and product categories ("interface design — dashboards, admin panels, apps, tools, and interactive products") but lists no concrete actions, matching the 'names domain but actions minimal' anchor rather than the multi-action anchor at 3.	2 / 5
Completeness	It states a clear 'what' (interface design for interactive products) but provides no explicit 'Use when...' trigger clause, and the guideline caps completeness at 3 when such explicit trigger guidance is missing.	3 / 5
Trigger Term Quality	Natural terms a user would say — "dashboards", "admin panels", "apps", "tools", "interactive products" — give good keyword coverage, though a few common synonyms are missing, placing it above the generic-keyword anchor at 3 but short of comprehensive coverage at 5.	4 / 5
Distinctiveness Conflict Risk	The explicit exclusion ("NOT for marketing design (landing pages, marketing sites, campaigns)") creates a clear boundary and minimal conflict risk, though the included scope ("apps, tools") remains somewhat broad, keeping it just below the clear-niche anchor at 5.	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
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: divaltor/starlight
Path: .agents/skills/frontend-design/SKILL.md
Revision: 3b609a5

Reviewed: 1 month ago

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.

interface-design

Table of Contents

Is this your skill?