Tessl • The management layer for AI agent skills

SkillPublic

design

Autonomous design partner for frontend interfaces. Scans the project, writes audit reports, reviews the findings, then fixes the interface itself and verifies the result, across every visual discipline: color, typography, layout, motion, interaction, accessibility, responsive behavior, voice, and surface.

1.77x

Quality

81%

Does it follow best practices?

Impact

78%

1.77x

1 of 3 eval scenarios. Add 2 more for a full score.

Securityby

Passed

No findings from the security scan

Quality

Content

81%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.

A highly actionable, workflow-driven body with excellent sequencing, verification gates, and a real one-level-deep reference bundle. Its main weakness is length: large philosophy sections inline material that already lives in dedicated reference files, and a few generic sections add padding.

Suggestions

Move the detailed discipline heuristics from "The Design Philosophy" sections (Color, Type, Layout, Motion, Interaction, Responsive, Copy) into their existing reference files, keeping only a one-line summary plus the reference link in SKILL.md.

Trim or delete the generic "Quality control: Perfect execution principles" section, whose items ("understand the current state", "test functionality") restate standard practice Claude already follows.

Consolidate the "Blank project behavior" examples (four near-identical lines) into a single sentence to cut redundancy.

Dimension	Reasoning	Score
Conciseness	The opinionated numeric house rules (60-76ch measure, 1-4-9 rhythm, viewport gauntlet) earn their place, but the body inlines large discipline philosophy sections that duplicate dedicated reference files (color.md, layout.md, motion.md, interaction.md, responsive.md), and the generic "Quality control" section ("Never make random spacing decisions", "weird compositions") restates what Claude already knows — matching the 3 anchor of mostly efficient with unnecessary material that could be tightened.	3 / 5
Actionability	Exact artifact paths (.design-agent/*-report.md), a 19-tool table mapping each tool to its reference, precise numeric rules, and an exact final-response format ("Implemented N jobs.") provide fully concrete, executable guidance throughout — the instruction-only equivalent of copy-paste-ready code.	5 / 5
Workflow Clarity	The autonomous sweep is a clearly sequenced Scan → Report → Review → Work → Final-response pipeline with explicit verification before continuing each job, failure recovery ("do not repeat an unchanged failing command"), stale-audit re-run gates, and precise stop conditions — matching the 5 anchor's explicit validation steps and feedback loops.	5 / 5
Progressive Disclosure	All 26 cited reference files exist, are one level deep, and are well-signaled via the tools table and discipline reference list; however, the substantial inline philosophy sections duplicate content owned by those reference files, so content is not appropriately split — matching the 4 anchor rather than the 5.	4 / 5
	Total	17 / 20 Passed

Description

71%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.

A strong, action-rich description in third person with excellent specificity and good natural keywords, undermined by the complete absence of an explicit "Use when..." trigger clause. Adding when-to-use guidance with common synonyms would lift it to the top anchor level.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to improve, redesign, audit, or polish an interface's visual design, or mentions colors, fonts, spacing, accessibility, or responsive behavior."

Include natural synonyms users actually say ("redesign", "restyling", "UI", "look and feel", "design review") alongside the discipline enumeration.

Consider naming the report/audit deliverables (e.g. ".design-agent/ reports") to further differentiate from generic frontend-development skills.

Dimension	Reasoning	Score
Specificity	"Scans the project, writes audit reports, reviews the findings, then fixes the interface itself and verifies the result" lists multiple specific concrete actions, and the enumerated discipline list ("color, typography, layout, motion, interaction, accessibility, responsive behavior, voice, and surface") gives comprehensive coverage of the domain, matching the 5 anchor.	5 / 5
Completeness	The "what" is explicit and concrete, but there is no "Use when..." clause or any equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines — clear what, missing when.	3 / 5
Trigger Term Quality	Natural trigger terms users would say are present ("design", "color", "typography", "layout", "motion", "accessibility", "responsive", "frontend interfaces"), giving good keyword coverage; it falls short of the 5 anchor because common synonyms and phrasings (e.g. "redesign", "UI", "visual polish") are missing, but is clearly above the 3 anchor's partial coverage.	4 / 5
Distinctiveness Conflict Risk	"Autonomous design partner for frontend interfaces" with the visual-discipline enumeration carves a mostly distinct niche with dedicated trigger terms, matching the 4 anchor; it is not a 5 because the discipline keywords overlap somewhat with general frontend/UI development skills.	4 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: administrakt0r/commandcode-design-skills
Path: SKILL.md
Revision: 020233c

Reviewed: 15 days 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.

design

Table of Contents

Is this your skill?