CtrlK
BlogDocsLog inGet started
Tessl Logo

modular-ds-base-components

Use when: building or evaluating unstyled Primer React primitives, especially accessibility primitives or low-level behavior that other components should build on. Covers when to create a base component instead of baking behavior into a styled component, the unstyled CSS-reset convention, deciding which parts need a base equivalent, and consolidating ARIA Authoring Practices Guide patterns.

65

Quality

78%

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 ./.github/skills/modular-ds-base-components/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 concise, well-organized instruction skill that assumes Claude's competence and gives concrete design directives. Its main weakness is workflow clarity, since it presents principles rather than a sequenced process with validation checkpoints.

Suggestions

Add a short decision checklist or sequenced flow for the 'when to create a base component' judgment (e.g., identify the part -> check for accessibility behavior -> reuse existing base or create one -> surface the decision) to give the workflow clearer sequence and checkpoints.

Tighten the intro and 'Relationship to hooks' paragraphs by dropping comparative framing ('similar in spirit to Base UI or Radix Primitives', 'Both are first-class') unless it changes a decision.

Consider a one-line 'Validation' note for the CSS reset guidance (e.g., confirm the :where() wrapped selector yields the intended 0,1,0 specificity) so the most error-prone instruction has an explicit checkpoint.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (no explaining what React, A11y, or ARIA is), but a few sentences carry non-essential framing ('similar in spirit to Base UI or Radix Primitives', 'Both are first-class') that could be trimmed, placing it above 3 yet short of the every-token-earns-its-place 5.

4 / 5

Actionability

Concrete directives like 'ship flat named exports', 'ship a minimal CSS reset using :where() selectors', and 'build on a shared primitive such as ButtonBase' give actionable guidance with only minor gaps; per the instruction-skill note the absence of copy-paste code is not penalized because the guidance is specific.

4 / 5

Workflow Clarity

This is design guidance rather than a sequenced operational workflow, so steps and validation checkpoints are largely implicit; the one soft checkpoint ('surface the decision explicitly') prevents a lower score, but there is no clear sequence to reach a 4 or 5.

3 / 5

Progressive Disclosure

At ~46 lines with no bundle files needed, the body is organized into clear, well-signaled sections (When to use, What a base component covers, Deciding which parts, CSS reset, Relationship to hooks) with inline one-level references to sibling skills and ADRs, matching the simple-skill exception for progressive disclosure.

5 / 5

Total

16

/

20

Passed

Description

83%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, well-structured description that explicitly pairs a 'Use when' trigger with a concrete coverage list and stays in third person. It is comprehensive on what the skill covers, with only slight overlap risk against sibling modular-ds skills and a few missing natural trigger synonyms.

DimensionReasoningScore

Specificity

Names the domain plus several concrete topics ('unstyled CSS-reset convention', 'deciding which parts need a base equivalent', 'consolidating ARIA Authoring Practices Guide patterns') with only minor coverage gaps, sitting above the 3 anchor but not quite the comprehensive multi-action list of a 5.

4 / 5

Completeness

It clearly and explicitly answers both what ('Covers ... the unstyled CSS-reset convention, deciding which parts need a base equivalent, and consolidating ARIA Authoring Practices Guide patterns') and when ('Use when: building or evaluating ...') with concrete trigger phrases, matching the top anchor; voice is third person with no penalty.

5 / 5

Trigger Term Quality

An explicit 'Use when:' clause surfaces natural phrases like 'building or evaluating unstyled Primer React primitives' and 'accessibility primitives', giving good keyword coverage, though some terms lean internal-jargon and a few natural synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (unstyled Primer React base primitives, ARIA consolidation, CSS reset convention) with minimal conflict risk, but the named sibling skills imply minor overlap with closely related design-system skills rather than the near-zero overlap of a 5.

4 / 5

Total

17

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
primer/react
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.