CtrlK
BlogDocsLog inGet started
Tessl Logo

pajamas

GitLab Pajamas Design System expert for building UIs with Pajamas components and patterns. Use when: (1) implementing UI that should follow GitLab's Pajamas design system, (2) selecting or configuring Pajamas/GlComponent components (GlButton, GlAlert, GlModal, etc.), (3) translating Figma designs into Pajamas-compliant code, (4) questions about Pajamas component usage, variants, categories, or accessibility, (5) building GitLab-style interfaces, or (6) the user mentions "Pajamas", "GitLab UI", "Gl components", or "design system" in a GitLab context. Works hand-in-hand with the implement-design skill and Figma MCP tools.

73

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A highly actionable, well-structured skill with clear sequenced workflows and validation checkpoints, and good one-level-deep progressive disclosure via reference tables. The main weakness is redundancy — duplicated init commands and overlapping component/token sections — that bloats the token budget without adding guidance.

Suggestions

Deduplicate the initialization commands: state them once in INITIALIZATION and have 'Updating References' cross-reference that section instead of repeating the three-line block verbatim.

Merge or clearly differentiate the 'Component import reference' table and the 'Component Selection Guide' table, which both enumerate GlButton/GlAlert/GlModal etc. — keep one as a quick catalog and the other purely as a need→component decision aid.

Consolidate the token guidance spread across 'CRITICAL RULE', 'When encountering absolute values', 'Token usage priority', and 'Token reference files' into a single rule plus a lookup procedure pointing at token-map.md, removing the restated examples.

DimensionReasoningScore

Conciseness

Mostly efficient dense reference material, but it could be tightened: the three init commands are repeated verbatim in both 'INITIALIZATION' and 'Updating References', the 'Component import reference' table and 'Component Selection Guide' table overlap heavily, and token guidance is restated across the CRITICAL RULE, 'When encountering absolute values', 'Token usage priority', and 'Token reference files' sections.

2 / 3

Actionability

Fully executable guidance throughout — concrete bash commands ('npm info @gitlab/ui peerDependencies --json', the init scripts), a runnable import code block, exact token examples ('var(--gl-color-blue-500)'), and a need→component→SSoT-reference table that is effectively copy-paste ready.

3 / 3

Workflow Clarity

Clear sequenced workflows with explicit validation: the scaffold flow ends with 'Verify after install: confirm there are no ERESOLVE... Resolve any conflicts before writing component code' (a validate→fix loop), the Component Lookup Workflow is a 4-step sequence, the Figma match chain is an explicit 5-step lookup, and INITIALIZATION checks for the references directory before proceeding.

3 / 3

Progressive Disclosure

SKILL.md acts as a clear overview pointing one level deep to references/pajamas-docs/{file} and the token files, with well-signaled navigation via the 'Token reference files' table and the SSoT Reference columns in the component and pattern tables; the generating scripts (update-refs.sh, build-index.py, build-token-map.py) are present and the gitignored references/ structure is documented rather than left implicit.

3 / 3

Total

11

/

12

Passed

Description

100%

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: specific, third-person, with an explicit numbered 'Use when' trigger clause covering both task-based and user-mention scenarios. Distinctively scoped to GitLab Pajamas with good natural trigger terms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'implementing UI', 'selecting or configuring Pajamas/GlComponent components', 'translating Figma designs into Pajamas-compliant code', and answering questions on 'variants, categories, or accessibility' — matching the anchor for multiple specific concrete actions.

3 / 3

Completeness

Clearly answers both what (Pajamas Design System expert for building UIs) and when via an explicit 'Use when: (1)…(6)' clause, including a user-mention trigger; written in third person ('GitLab Pajamas Design System expert').

3 / 3

Trigger Term Quality

Covers natural terms users would say — 'Pajamas', 'GitLab UI', 'Gl components', 'design system', 'Figma designs', plus concrete component names 'GlButton, GlAlert, GlModal' — giving good coverage of natural trigger language.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (GitLab Pajamas design system) with distinct, scoped triggers such as 'the user mentions "Pajamas"... in a GitLab context'; unlikely to fire for unrelated skills despite the acknowledged hand-in-hand use with implement-design.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 11 missing, 7 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 34 missing, 19 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository
gitlabhq/orbit-knowledge-graph
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.