CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

nightshift-design

Use when designing, building, writing, OR validating any nightshift interface, marketing page, doc, slide, mock, prototype, or brand asset — covers the night-sky dark theme, terracotta accent, Inter + JetBrains Mono type, design tokens, React UI-kit components, the technical no-hype brand voice, and a runnable adherence gate (token-drift + WCAG-AA contrast + lint). Trigger on "nightshift", "design with the brand", "terminal/pipeline UI", "ships while you sleep", "check brand adherence", "validate nightshift design".

74

Quality

93%

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.

The body is an exemplary design-system digest: highly actionable with exact token values, commands, and component APIs, and a well-structured read-on-demand reference layer. The main gaps are a missing explicit fix-and-revalidate feedback loop in the build workflow and a file index that references many paths absent from the provided bundle.

Suggestions

Add an explicit error-recovery step to the build workflow (e.g., "If npm run validate fails, fix the flagged token/contrast issue and re-run until it passes") so the gate is a true feedback loop rather than a one-shot check.

Align the file index with the shipped bundle: either include the cited templates/, tokens/, components/, ui_kits/, styles.css, _ds_manifest.json, and package.json, or mark them as external/not distributed so workflow steps 3–4 don't depend on files the bundle doesn't carry.

Trim the "File index" section, which largely restates the reference table and component inventory, to cut duplicated tokens.

DimensionReasoningScore

Conciseness

The body is a dense, skill-specific digest (token aliases, voice rules, signature moves) with no explanations of concepts Claude already knows. It falls short of lean-perfect because the "File index" section repeats paths already given in the reference table, and the Button props/variants detail duplicates what references/components.md is cited as covering. Not 3 because there is no generic padding or over-explanation anywhere.

4 / 5

Actionability

Guidance is executable and specific: runnable commands ("npm run validate", "npm run check:tokens"), exact values (cubic-bezier(.22,1,.36,1), 4px spacing scale, px type scale), a copy-paste JSX snippet, and precise file paths for every need. Covers the common cases without guesswork; matches the fully-executable anchor.

5 / 5

Workflow Clarity

"Build workflow — follow every time" gives a clear 4-step sequence with an explicit validation gate ("run npm run validate... then walk references/adherence-checklist.md. Every box passes or is deliberately N/A") plus two-mode decision guidance. Not 5 because there is no explicit fix-and-re-validate feedback loop for when the gate fails — error recovery is only implied by "fails the build"; not 3 because checkpoints are explicit, not missing.

4 / 5

Progressive Disclosure

A clean need→file table maps each task to a one-level-deep reference, and all cited references/*.md, scripts/*.mjs, and assets files exist in the bundle. However the file index and workflow also point to templates/page-starter.html, _ds_manifest.json, package.json, styles.css, tokens/, components/, guidelines/, ui_kits/, and README.md, none of which are present in the provided bundle — and workflow steps 3–4 depend on some of them. Not 5 because of these dangling paths; not 3 because structure, signaling, and the primary reference layer are all strong.

4 / 5

Total

17

/

20

Passed

Description

100%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 a strong example: it states concrete capabilities across artifact types, explicitly declares both what it covers and when to use it, and supplies a list of natural trigger phrases. It stays in third-person/declarative style with no fluff or over-claims.

DimensionReasoningScore

Specificity

Lists four concrete actions ("designing, building, writing, OR validating any nightshift interface, marketing page, doc, slide, mock, prototype, or brand asset") and enumerates coverage areas ("night-sky dark theme, terracotta accent, Inter + JetBrains Mono type, design tokens, React UI-kit components... adherence gate (token-drift + WCAG-AA contrast + lint)"). Matches the comprehensive multiple-concrete-actions anchor; not 4 because there are no meaningful coverage gaps.

5 / 5

Completeness

Both halves are explicit: what ("covers the night-sky dark theme... design tokens, React UI-kit components, the technical no-hype brand voice, and a runnable adherence gate") and when ("Use when designing, building, writing, OR validating..." plus a concrete "Trigger on" phrase list). Matches the anchor that clearly answers both what and when with concrete triggers; not 4 because neither half is merely implied or generic.

5 / 5

Trigger Term Quality

Explicit trigger list — "nightshift", "design with the brand", "terminal/pipeline UI", "ships while you sleep", "check brand adherence", "validate nightshift design" — covers the natural phrases a user would say, including validation and building variations. Not 4 because synonym/variation coverage is complete rather than missing a few natural terms.

5 / 5

Distinctiveness Conflict Risk

A clearly niched brand design system keyed to a unique brand name with brand-specific triggers ("nightshift", "check brand adherence", "validate nightshift design"), so overlap with other skills is minimal. Not 4 because no closely related skill would collide on these triggers.

5 / 5

Total

20

/

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

.claude/skills/nightshift-design/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.