CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

shadcn

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

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/shadcn/SKILL.md
SKILL.md
Quality
Evals
Security

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 content is an exemplary prescriptive skill: executable commands, explicit validation and confirmation checkpoints, and hard rules that capture non-obvious project conventions. Its two weaknesses are a redundant Key Patterns section and — more seriously — heavy reliance on rule/reference files that are absent from the bundle, breaking progressive disclosure.

Suggestions

Ship the referenced bundle files (rules/*.md, cli.md, customization.md) with the skill — 7 referenced paths resolve to nothing in the current bundle, so the Incorrect/Correct code pairs and CLI field reference the body leans on are unavailable.

Cut the "Key Patterns" section or fold it into the Critical Rules sections it duplicates (gap vs space-y, size vs w/h, data-icon, Badge semantics appear in both).

The embedded `!`npx shadcn@latest info --json`` command in "Current Project Context" depends on harness behavior that is never explained; document its fallback behavior explicitly when no project exists.

DimensionReasoningScore

Conciseness

The body is dense with project-specific, non-obvious rules (data-icon, gap vs space-y, Field composition, base-vs-radix) and spends almost no tokens explaining concepts Claude already knows. It is not a 5 because the "Key Patterns" section repeats rules already stated verbatim in "Critical Rules" (gap-* vs space-y-*, size-* vs w/h, data-icon, Badge vs raw colors), which is trimming opportunity.

4 / 5

Actionability

Fully executable throughout: exact CLI commands with flags (`npx shadcn@latest add <component> --dry-run`, `--diff <file>`, `init --preset <code> --force --reinstall`), copy-paste TSX snippets, a component-selection table, and precise instructions like "rewrite the imports accordingly" with a concrete alias example. This matches anchor 5 — specific, runnable guidance covering the common cases.

5 / 5

Workflow Clarity

The 8-step workflow is clearly sequenced with explicit validation checkpoints for risky operations: check installed components before add, --dry-run/--diff previews before updates, "always read the added files and verify they are correct" after adds, and hard guards ("Never use --overwrite without the user's explicit approval", "do not guess the registry", ask reinstall/merge/skip). The Updating Components section adds a per-file diff decision loop. This matches anchor 5 including feedback loops for batch/destructive operations.

5 / 5

Progressive Disclosure

The SKILL.md itself is a well-organized overview with clearly signaled, one-level-deep references (each Critical Rules section links to its rule file, plus a consolidated "Detailed References" section). However, scoring against the actual bundle structure, none of the seven referenced files (rules/styling.md, forms.md, composition.md, icons.md, base-vs-radix.md, cli.md, customization.md) exist in the bundle — only assets/ is present — so the disclosed detail layer is broken. The structure design merits 5, but the missing files undermine navigation; this lands between anchors 3 and 4, and since the references resolve to nothing, 3 is the better fit.

3 / 5

Total

17

/

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 identifies its niche unambiguously via "shadcn/ui" but is a "what"-only description: the actions are abstract, there is no "Use when..." trigger guidance, and natural trigger terms (Tailwind, registry, add/init a component) are missing. It sits just above the midpoint of the scale.

Suggestions

Add an explicit trigger clause, e.g. "Use when adding, styling, or debugging shadcn/ui components, initializing a project, or when the user mentions shadcn, Tailwind UI components, or component registries."

Replace abstract phrasing ("providing context, documentation, and usage patterns") with concrete actions: add/update components via the CLI, search registries, initialize projects, apply theming presets.

Include natural trigger keywords users actually say: "shadcn", "add a component", "component registry", "Tailwind".

DimensionReasoningScore

Specificity

"Manages shadcn/ui components and projects" names the domain, and "providing context, documentation, and usage patterns" gestures at actions, but those actions are abstract — it never states concrete operations like adding, installing, updating, or theming components. This matches anchor 3 (clear domain, weakly concrete actions) rather than 4, which requires several specific actions.

3 / 5

Completeness

The "what" is clear (manages shadcn/ui components and projects), but there is no "Use when..." clause or any equivalent trigger guidance — per the rubric this caps completeness at 3. It is above anchor 2 because the "what" is specific rather than vague, but below anchor 4, which requires an explicit "when".

3 / 5

Trigger Term Quality

"shadcn/ui", "components", and "design systems" are relevant keywords, but common natural phrases users would say — Tailwind, component registry, add/install a component, init — are absent. Some relevant keywords with missing variations matches anchor 3, not 4, which expects good coverage with only a few terms missing.

3 / 5

Distinctiveness Conflict Risk

"shadcn/ui" is a highly distinctive niche with minimal wrong-skill trigger risk, but the tail phrase "building modern design systems" is generic and could overlap with general UI/design-system skills. Mostly distinct with minor overlap risk matches anchor 4; not 5 because a clear niche alone doesn't offset the generic design-system framing.

4 / 5

Total

13

/

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

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

skills/shadcn/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.