sync-shadcn

Autogoal-backed planning, status, review, dashboard, apply, and tracking for upstream shadcn docs syncs into Plate docs. Use when the user asks for `sync-shadcn`, `sync-shadcn status`, `sync-shadcn review`, `sync-shadcn dashboard`, `sync-shadcn apply`, a scoped `sync-shadcn <feature>` lane, to sync shadcn docs, audit newer shadcn docs changes, compare `../shadcn/apps/v4` with `apps/www`, update the shadcn sync baseline, or decide what to adopt, fork, defer, or exclude from upstream shadcn.

Quality

83%

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

Quality

Content

66%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 skill is exceptionally actionable and workflow-clear with strong validation gates, but it suffers from severe verbosity and a monolithic structure that should be split into reference files. Both conciseness and progressive disclosure are weak points.

Suggestions

Extract the durable policy list, the dashboard/apply/review command specs, and the decision-classification matrix into separate reference files (e.g. references/policy.md, references/dashboard.md) and link to them one level deep from SKILL.md to cut the body to an overview.

De-duplicate rules repeated across command sections (e.g. 'must not patch apps/www', 'do not change lastSyncedCommit/lastPlannedCommit/lastPlan/partialSyncs') by stating them once in a shared constraints section and referencing it.

Remove boilerplate restating what Claude already knows (e.g. explanations of git diff/numstat behavior, status.json field meanings repeated per command) and keep only the sync-specific contract.

Dimension	Reasoning	Score
Conciseness	At ~1200 lines the body is heavily padded with repeated restatements of the same rules (e.g. micro-overlap conditions, 'must not patch apps/www' appears across status/apply/dashboard/review/planning), definitions Claude could derive, and verbose enumeration of every state/edge — clearly more than the rubric's mid-point of verbosity.	2 / 5
Actionability	Provides copy-paste-ready bash and node snippets (status checks, ref resolution, run-dir creation, inventory diffs, check-complete.mjs invocation) plus fully specified plan/output templates and decision-state contracts, covering the common cases concretely.	5 / 5
Workflow Clarity	The flow is explicitly sequenced as numbered phases (1 Establish refs → 2 Run dir → 3 Classify → 4 Plan → 5 Stop for review → 6 Delegate via task → 7 Status updates) with validation checkpoints (merge-base ancestry proof, check-complete.mjs, focused verification, stop-before-implement boundary) and explicit error-recovery (blocked-ref handling, re-validate on failure).	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) yet the body inlines an enormous monolithic policy/spec that clearly belongs in separate reference files (durable policy, dashboard spec, decision matrix), and references to external docs are buried in flat lists rather than clearly signaled one-level-deep navigation.	2 / 5
	Total	14 / 20 Passed

Description

100%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 is concrete, trigger-rich, fully answers both what and when, and carves out a clear niche with minimal conflict risk. It is among the strongest examples for this skill type.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — 'planning, status, review, dashboard, apply, and tracking', 'inventory every added/modified/deleted upstream change', 'compare ../shadcn/apps/v4 with apps/www', 'update the shadcn sync baseline' — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (Autogoal-backed planning/status/review/dashboard/apply/tracking for shadcn docs syncs into Plate docs) and 'when' ('Use when the user asks for sync-shadcn …, to sync shadcn docs, audit …, compare …, update …, or decide what to adopt, fork, defer, or exclude').	5 / 5
Trigger Term Quality	Enumerates the literal invocation strings users would type — 'sync-shadcn', 'sync-shadcn status', 'sync-shadcn review', 'sync-shadcn dashboard', 'sync-shadcn apply', 'sync-shadcn <feature>' — plus natural phrases like 'sync shadcn docs' and 'audit newer shadcn docs changes'.	5 / 5
Distinctiveness Conflict Risk	Highly specific to the Plate↔shadcn docs sync niche with distinct command triggers ('sync-shadcn' and subcommands) and unique domain objects (baseline, fork/defer/exclude), making conflict with unrelated skills minimal.	5 / 5
	Total	20 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1214 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
relative_links	Relative link issues: 2 suspicious	Warning

	Total	12 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/sync-shadcn/SKILL.md
Commit: d76efae

Reviewed: 3 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.