CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

find

Recommend the best Cult UI components for a described need, with docs links and install commands.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 exemplar command specification: lean, fully executable, and sequenced with explicit fallback and verification checkpoints for every failure mode (missing catalog, empty input, no matches, unconfirmed fit). No improvements identified.

DimensionReasoningScore

Conciseness

Every step is pure instruction with no explanations of concepts Claude already knows; even the parentheticals ('since the component may be newer than the catalog', 'which can differ from the docs slug') carry decision-relevant information. Lean and efficient throughout.

5 / 5

Actionability

Commands are copy-paste ready: 'Grep -n "^## "', '-A 2', 'curl -sL https://www.cult-ui.com/llms.txt', 'npx shadcn@latest add @cult-ui/<install-name>', plus a concrete Glob fallback pattern and a worked keyword example ('file upload' → upload, dropzone, file, drag) covering the common case.

5 / 5

Workflow Clarity

Seven unambiguous, well-sequenced steps with explicit error recovery: Glob fallback when the catalog path fails (step 1), empty-argument handling (step 2), live-index fallback on zero matches (step 4), and a WebFetch confirmation checkpoint that the top candidate fits before recommending (step 5).

5 / 5

Progressive Disclosure

The ~18-line body is a lean procedure that offloads the bulky catalog to a one-level-deep reference ('skills/cult-ui/references/components.md') that is clearly signaled, with a Glob fallback for navigation. No content that belongs in a separate file is inlined.

5 / 5

Total

20

/

20

Passed

Description

70%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 states concrete actions and is anchored to a distinctive brand niche, but it lacks any explicit 'Use when...' trigger clause, capping completeness at 3. Adding a trigger clause with a few natural synonyms would make it fully self-describing.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for a Cult UI component, mentions cult-ui.com, or wants an animated/interactive React widget for their app.'

Include natural synonyms such as 'React components', 'shadcn registry', or 'UI widgets' so the description matches the phrasings users actually employ when describing the need.

DimensionReasoningScore

Specificity

Explicitly states three concrete deliverables — 'Recommend the best Cult UI components', 'with docs links and install commands' — which matches 'several specific actions; minor gaps'. Not 5 because the ranked-shortlist output format and live-index fallback are not mentioned.

4 / 5

Completeness

The 'what' is clear (recommend components with docs links and install commands), but there is no 'Use when...' clause or equivalent trigger guidance; 'for a described need' only weakly implies when, so completeness is capped at 3.

3 / 5

Trigger Term Quality

Contains the natural terms users of this library would say — 'Cult UI components', 'install commands', 'docs' — giving good keyword coverage. Not 5 because common variations such as 'React components', 'shadcn registry', or 'widget' are absent.

4 / 5

Distinctiveness Conflict Risk

'Cult UI components' names a specific brand, giving a clear niche with distinct triggers and minimal conflict risk with generic UI-component or install-helper skills.

5 / 5

Total

16

/

20

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.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository

freightCognition/linehaulai-claude-marketplace

Path

plugins/cult-ui/skills/find/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.