CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

70

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

The risk profile of this skill

SKILL.md
Quality
Evals
Security

Quality

Content

71%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured design system skill that effectively serves as an overview document with clear pointers to detailed references. Its main strengths are excellent progressive disclosure, a clear build workflow with validation gates, and actionable component examples. The primary weakness is moderate verbosity — the overview section, audience description, and some inline token tables could be trimmed since Claude doesn't need the product pitch context repeated, and exact values are deliberately deferred to reference files anyway.

Suggestions

Trim the Overview section to remove product description/audience details that Claude doesn't need (e.g., 'senior devs who live in the terminal and smell marketing instantly') — keep only the design principles that affect output.

Add an explicit error recovery step to the build workflow: what specific actions to take when `npm run validate` fails (e.g., 'If token-drift errors: check hex values against _ds_manifest.json; if contrast errors: adjust text/bg pairing').

DimensionReasoningScore

Conciseness

The skill is fairly comprehensive but includes some unnecessary explanation (e.g., describing what nightshift is and its audience in detail that Claude doesn't need repeated). The token quick-reference tables are useful but the inline repetition of values that exist in reference files adds bulk. Some sections like 'Common mistakes' and 'Signature moves' are well-condensed, but overall it could be tighter.

3 / 5

Actionability

The skill provides concrete guidance: a clear build workflow with specific commands (`npm run validate`), JSX component examples, specific token alias names, and file paths. The two output modes are well-defined. Minor gaps include no complete executable example of building a page end-to-end, and the validation step references `npm run validate` without showing expected output or error handling.

4 / 5

Workflow Clarity

The 4-step build workflow is clearly sequenced with a validation gate ('npm run validate' + adherence checklist). It includes the instruction to load references first and gate before done. However, there's no explicit error recovery loop (what to do if validation fails beyond 'every box passes or is deliberately N/A'), and the relationship between the two output modes and the workflow steps could be more explicit.

4 / 5

Progressive Disclosure

Excellent progressive disclosure structure. The SKILL.md serves as a clear overview with a well-organized reference table pointing to specific files for deeper detail. The file index at the bottom provides comprehensive navigation. References are one level deep and clearly signaled. The deliberate choice to not inline exact hex values ('they live once in tokens/colors.css') demonstrates good content splitting discipline.

5 / 5

Total

16

/

20

Passed

Description

100%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.

This is an excellent skill description that comprehensively covers what the skill does (design, build, validate nightshift brand assets with specific theme elements and an adherence gate) and when to use it (explicit trigger phrases and a 'Use when' clause). It is highly distinctive due to the specific brand name and unique design tokens, and includes rich natural trigger terms that users would actually say.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions and assets: designing/building/validating interfaces, marketing pages, docs, slides, mocks, prototypes, brand assets. It also specifies concrete elements like night-sky dark theme, terracotta accent, Inter + JetBrains Mono type, design tokens, React UI-kit components, brand voice guidelines, and a runnable adherence gate with specific checks (token-drift, WCAG-AA contrast, lint).

5 / 5

Completeness

Explicitly answers both 'what' (designing, building, writing, validating nightshift interfaces and brand assets with specific theme elements, type system, components, and adherence checks) and 'when' (opens with 'Use when...' and closes with explicit 'Trigger on' phrases). Both are concrete and detailed.

5 / 5

Trigger Term Quality

Includes comprehensive natural trigger terms explicitly listed: 'nightshift', 'design with the brand', 'terminal/pipeline UI', 'ships while you sleep', 'check brand adherence', 'validate nightshift design'. Also includes natural keywords throughout like 'marketing page', 'prototype', 'mock', 'brand asset', 'dark theme', 'React UI-kit'. Covers both brand-specific and general design terms users would naturally say.

5 / 5

Distinctiveness Conflict Risk

Highly distinctive due to the specific brand name 'nightshift', unique design tokens (terracotta accent, night-sky dark theme, Inter + JetBrains Mono), and the specific adherence gate. This is clearly a niche brand design system skill that would not conflict with generic design or UI skills.

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
whimzyLive/nightshift-ai
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.