Name: shadcn
Rating: 60 (1 reviews)
Author: administrakt0r

shadcn

Manages shadcn/ui components and projects, providing context, documentation, and usage patterns for building modern design systems.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/shadcn/SKILL.md

The canonical home for this skill is shadcn in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

85%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 highly actionable with executable commands, concrete code patterns, and well-sequenced workflows that include validation checkpoints and approval guards. Its main weakness is progressive disclosure: the SKILL.md signals detailed rule and CLI files that are not present in the bundled skill.

Suggestions

Bundle the referenced detail files (rules/styling.md, rules/forms.md, rules/composition.md, rules/base-vs-radix.md, rules/icons.md, cli.md, customization.md) so the signaled one-level-deep references actually resolve.

Trim the minor overlap between the Critical Rules bullets and the Key Patterns code block to tighten conciseness toward a lean 5.

Consider a short pointer at the top of the body confirming which referenced files are bundled versus fetched on demand, so navigation expectations match the actual bundle.

Dimension	Reasoning	Score
Conciseness	The body is dense with one-line rules, executable commands, and a needs→component table rather than padding with basics Claude already knows; minor redundancy between Critical Rules and Key Patterns keeps it just below the lean-every-token-earns-its-place level of 5.	4 / 5
Actionability	It provides copy-paste-ready commands ("npx shadcn@latest add button --diff button.tsx", "--dry-run") and concrete code patterns (FieldGroup+Field, data-icon, gap-, size-) covering the common cases, matching the fully-executable anchor.	5 / 5
Workflow Clarity	The 9-step Workflow and the Updating Components section sequence steps with explicit validation checkpoints (--dry-run, --diff, per-file diff decisions) and a feedback loop with a hard guard ("Never use --overwrite without the user's explicit approval"), satisfying the explicit-validation + feedback-loop anchor rather than the checkpoint-missing level of 4.	5 / 5
Progressive Disclosure	The overview is well-designed with clearly signaled one-level-deep references (./rules/styling.md, ./rules/forms.md, ./cli.md, ./customization.md), but scoring against the actual bundle shows those referenced files are absent (only assets/ PNGs are bundled), so the promised navigation resolves nowhere and the disclosure is not actually fulfilled.	3 / 5
	Total	17 / 20 Passed

Description

57%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 clearly identifies the shadcn/ui niche and what the skill provides, but its action language is abstract and it entirely lacks a "Use when..." trigger clause. Adding explicit trigger phrases and concrete verbs (add, install, configure, customize) would raise specificity, trigger quality, and completeness.

Suggestions

Add an explicit "Use when..." trigger clause naming natural user phrases (e.g., "Use when adding, installing, or customizing shadcn/ui components, or when working with shadcn registries or design system presets.").

Replace abstract actions ("providing context, documentation, and usage patterns") with concrete verbs ("add, configure, update, and document shadcn/ui components").

Include registry/CLI trigger terms users actually say ("registry", "preset", "npx shadcn") to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	"Manages shadcn/ui components and projects, providing context, documentation, and usage patterns" names the domain and lists several actions, but those actions ("providing context", "documentation", "usage patterns") are abstract rather than concrete verbs like add/install/extract, so it sits at the domain+actions-but-not-comprehensive level rather than the multi-concrete-action level of 4.	3 / 5
Completeness	The "what" is clear ("Manages shadcn/ui components and projects, providing context, documentation, and usage patterns"), but there is no "Use when..." clause or equivalent explicit trigger guidance, which the rubric caps at 3; not 4 because the "when" is absent rather than merely under-specified.	3 / 5
Trigger Term Quality	It includes the strong proper-noun trigger "shadcn/ui" plus "components" and "design systems", but omits the natural action phrases users actually say ("add a component", "install", "registry") and their common variations, leaving keyword coverage incomplete rather than comprehensive.	3 / 5
Distinctiveness Conflict Risk	The "shadcn/ui" proper noun carves out a clear, distinct niche with minimal conflict risk against generic skills; not below 5 because the trigger is unambiguous despite the broad "design systems" phrasing.	5 / 5
	Total	14 / 20 Passed

Validation

87%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 14 missing	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/shadcn/SKILL.md
Commit: 57c135b

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

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.