CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

core-components

Core component library and design system patterns. Use when building UI, using design tokens, or working with the component library.

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/core-components/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 a well-organized, code-first reference: lean token tables, concrete correct/wrong examples, and an unambiguous core directive make it highly actionable. Weaknesses are minor — some redundant anti-pattern examples, a vacuous closing 'When to Use' line, a few undocumented components used in examples, and everything inlined in one file rather than split into reference files.

DimensionReasoningScore

Conciseness

The body is dominated by lean token tables and copy-paste code examples with almost no explanation of concepts Claude already knows. Minor trimmable padding remains: the vacuous closer 'This skill is applicable to execute the workflow or actions described in the overview', and the Anti-Patterns section repeats WRONG/CORRECT pairs already shown in the token sections. This is 'Efficient; minor instances of over-explanation that could be trimmed', not level 5 where every token earns its place.

4 / 5

Actionability

Concrete TSX examples with correct/wrong pairs cover tokens, components, and layout patterns, and the Component Props Pattern shows a complete typed component. Minor gaps: the import path ('components/core') appears only in an anti-pattern snippet, and Icon, Avatar, Heading, and Screen are used in examples without any prop documentation. Fits 'Mostly executable guidance; concrete code or commands with minor gaps' rather than the fully copy-paste-ready level 5.

4 / 5

Workflow Clarity

This is a reference-style skill, so no multi-step sequence is needed; the core directive ('NEVER hard-code values. Always use design tokens.') is unambiguous, stated up front, and reinforced by the anti-pattern correct/wrong pairs, and no destructive or batch operations require validation checkpoints. It is not a simple single-action skill — it spans tokens, several components, and layout patterns — so the simple-skill 5 exception does not apply, and component discovery beyond the listed examples is left implicit. Level 4 fits: clear, unambiguous guidance with minor gaps.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are all absent), so all content lives in a single well-sectioned ~260-line file with a clear header hierarchy (tokens → components → patterns → anti-patterns) that is easy to navigate. There are no buried or nested references to penalize, but the full token tables and per-component documentation are natural candidates for a one-level-deep reference file if the library grows, keeping this at 'Good structure; minor organization gaps' rather than level 5's clean overview-plus-references split.

4 / 5

Total

16

/

20

Passed

Description

53%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 has a clear structure (domain statement plus an explicit 'Use when...' trigger clause) but the what-clause names no concrete capabilities, leaving it a domain label rather than an action summary. Trigger keywords are relevant but thin on synonyms, and the broad 'building UI' trigger creates overlap risk with other UI-related skills.

Suggestions

Replace the noun-phrase what-clause with concrete actions, e.g. 'Build UI with the core component library (Box, Text, Button, Input, Card) and apply design tokens for spacing, color, and typography instead of hard-coded values.'

Broaden trigger terms with natural synonyms users would say, e.g. 'design system', 'styling', 'theming', 'component variants', or 'screen layout'.

Narrow the overly broad 'building UI' trigger to reduce conflict risk with sibling skills like react-ui-patterns, e.g. 'when composing screens or components from the core library or applying design tokens'.

DimensionReasoningScore

Specificity

The description names the domain ("Core component library and design system patterns") but lists no concrete actions — the what-clause is a bare noun phrase, and activities only appear inside the trigger clause. This matches the anchor 'Names the domain but actions are minimal or generic' rather than level 3, which requires 1–2 explicitly named concrete actions.

2 / 5

Completeness

Both parts are present: a what ('Core component library and design system patterns') and an explicit when ('Use when building UI, using design tokens, or working with the component library'). The what is weak (a domain label rather than action statement) and the when could be more specific, so it sits at level 4 rather than the fully concrete level 5.

4 / 5

Trigger Term Quality

Trigger terms 'building UI', 'using design tokens', and 'working with the component library' are natural phrases a user might say, but common variations and synonyms ('design system', 'styling', 'theming', 'components') are missing. Fits 'Some relevant keywords but missing common variations or synonyms'; not level 4, which expects only a few natural terms missing.

3 / 5

Distinctiveness Conflict Risk

'Building UI' is broad and would overlap with any general UI or styling skill, though 'design tokens' and 'component library' narrow the niche. It could still be confused with sibling skills like the referenced 'react-ui-patterns', matching 'Somewhat specific but could still overlap with similar skills'.

3 / 5

Total

12

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

skills/core-components/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.