CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

designing-in-patterns

Use when designing, planning or auditing UI against a component library — naming surfaces with the repo's pattern vocabulary, deciding reuse versus extend versus new, exploring compositions, or writing the reuse table (component-plan.md, a spec's `## Reuse`, a UI audit). Carries the design method; the repo's own vocabulary, bundle and board rules come from project-context and the designer override.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 dense, disciplined method document: token-efficient definition blocks and tables, a clear numbered decision procedure with an approval gate, and clean delegation of repo-specific values. The gaps are minor — a few actions rely on external tokens whose format is not shown, and there is no explicit error-recovery loop.

DimensionReasoningScore

Conciseness

The body is extremely lean: terse `:=` definition blocks, tables for the reuse-table columns and anti-patterns, and zero padding or explanation of concepts Claude already knows. Every token earns its place, matching anchor 5 rather than 4 (there is no over-explanation left to trim).

5 / 5

Actionability

Concrete, executable guidance throughout: exact table columns, "Grep the app's UI paths for the pattern", "ls/Grep, never by reading component source", explicit extend/new decision rules, and a specific pointer for repo-specific values. Not 5 because a few steps (e.g., "the `Component review` token serves them", the vocabulary file's format) are delegated to external files rather than specified.

4 / 5

Workflow Clarity

Sections 1-5 form a clear numbered sequence (name surfaces → two tests → extend/new → explore → reuse table) with an explicit gating checkpoint ("A `new` row with no Story is an open question; the spec cannot be approved with it") and a human-chooses-before-merge loop. Not 5 because there is no explicit error-recovery feedback loop and the sequence is implied by section numbering rather than stated as steps.

4 / 5

Progressive Disclosure

No bundle files exist or are referenced; the ~85-line body is well organized into seven numbered sections and deliberately keeps repo-specific values one level deep in project context. Good structure and easy navigation, but it sits above the under-50-line simple-skill threshold for a reference-free 5, so anchor 4 fits best.

4 / 5

Total

17

/

20

Passed

Description

87%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 description: it leads with an explicit trigger clause, enumerates concrete capabilities with named artifacts, and carves out a distinct niche with explicit boundary delegation. The only weaknesses are the slightly abstract "exploring compositions" and a few missing natural trigger synonyms.

DimensionReasoningScore

Specificity

Lists several concrete actions — "naming surfaces with the repo's pattern vocabulary", "deciding reuse versus extend versus new", "exploring compositions", "writing the reuse table (component-plan.md, a spec's `## Reuse`, a UI audit)" — with named artifacts. Not 5 because "exploring compositions" is abstract and the trailing meta sentence adds no capability; not 3 since coverage goes well beyond 1-2 actions.

4 / 5

Completeness

Opens with an explicit "Use when..." clause carrying concrete trigger phrases, and states clearly what it does (naming surfaces, deciding reuse/extend/new, exploring compositions, writing the reuse table). Both what and when are explicit and specific, matching anchor 5 rather than 4 where the 'when' would be weaker.

5 / 5

Trigger Term Quality

Good natural-term coverage: "designing, planning or auditing UI", "component library", "UI audit", plus concrete file triggers (component-plan.md, a spec's `## Reuse`). A few natural variations a user might say ("screen", "board", "spec review") are absent, keeping it below the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (design method against a component library) with distinct triggers, and explicitly fences off overlap by delegating repo-specific vocabulary, bundle and board rules to project-context and the designer override. Minimal conflict risk with other skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

whimzyLive/nightshift-ai

Path

plugins/sdlc/skills/designing-in-patterns/SKILL.md

Reviewed

Table of Contents

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.