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

77%

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 ./.agents/skills/sync-shadcn/SKILL.md

Quality

Content

62%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 delivers excellent workflow sequencing, explicit gates, and copy-paste-ready commands, but at ~1200 lines it is a monolith: the stop-for-review template is duplicated verbatim, per-command policy and durable-decision lists belong in reference files, and external skill/script links use machine-specific absolute paths. Strong on execution clarity, weak on token economy and file structure.

Suggestions

Split the per-command reference (the full `status`, `apply`, `dashboard`, `review` sections) and the Durable Policy document list into `references/` files, keeping SKILL.md as an overview with one-level-deep links.

Deduplicate the "## 5. Stop For User Review" block and the near-identical "## Output" section into a single canonical stop-point template.

Replace machine-specific absolute skill links (`/Users/zbeyens/git/plate/.agents/skills/...`) with repo-relative paths so the instructions are executable outside the original author's checkout.

Dimension	Reasoning	Score
Conciseness	The body is roughly 1200 lines with noticeably padded and duplicated sections — the entire "## Output" block near the end repeats the "## 5. Stop For User Review" template verbatim, and the planning-mode may/must-not boundaries are restated across "Autogoal Dependency", "User Review Boundary", and "Hard Rules". Much of the per-command policy detail is accurate but could be substantially tightened or offloaded.	2 / 5
Actionability	Highly executable: exact bash commands (git fetch/rev-parse/diff pipelines), exact JSON shapes for `status.json`, decision taxonomies, and a full plan template. Falls short of 5 because links to `$autogoal` and `$task` use machine-specific absolute paths (`/Users/zbeyens/git/plate/...`), and referenced scripts/templates (`check-complete.mjs`, `docs/plans/templates/sync-shadcn.md`) are not part of this bundle, so a fresh environment cannot run them as-is.	4 / 5
Workflow Clarity	Clear multi-phase sequence (numbered sections 1-7: establish refs, create run dir, classify, plan, stop for review, delegate, update status) with explicit validation checkpoints: Start Gates, Completion Gates, staleness verdicts with evidence tables, verification requirements per merge class, and a hard plan-then-stop-then-execute boundary. Mutating operations (patching `apps/www`, advancing the baseline) are guarded by explicit acceptance and full-accounting conditions.	5 / 5
Progressive Disclosure	Section headers are well organized and navigation within the file is possible, but the skill is a single monolithic ~1200-line SKILL.md with no `references/`, `scripts/`, or `assets/` bundle. Content that clearly belongs in separate files — the per-command reference (status/apply/dashboard/review), the Durable Policy document list, and the full plan template — is inlined. Not 2 because structure is strong, not 4 because none of the heavy content is split out.	3 / 5
	Total	14 / 20 Passed

Description

92%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 description: comprehensive concrete capabilities, an explicit trigger clause, third-person voice, and a highly distinctive niche. The only weakness is reliance on internal jargon ("Autogoal-backed", "lane") in the opening, which slightly dilutes the natural trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete, distinct capabilities — "planning, status, review, dashboard, apply, and tracking" — each tied to a named command and specific operations such as comparing "`../shadcn/apps/v4` with `apps/www`" and updating the sync baseline. Coverage is comprehensive with no generic filler.	5 / 5
Completeness	Explicitly answers both questions: the "what" opens with the concrete capability list, and an explicit "Use when the user asks for..." clause enumerates concrete trigger phrases including commands and decision verbs (adopt, fork, defer, exclude). Matches the anchor example structure closely.	5 / 5
Trigger Term Quality	Good keyword coverage including natural phrases users would say ("to sync shadcn docs", "audit newer shadcn docs changes") and exact command invocations, but "Autogoal-backed", "scoped ... lane", and "sync baseline" are internal jargon a user would not naturally say. Not 5 because a few natural synonyms are crowded out by that jargon; not 3 because command names and everyday phrasings are present.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (shadcn-to-Plate docs sync) with distinct triggers (the `sync-shadcn` command family, specific repos and paths). Minimal conflict risk with other skills; no generic vocabulary.	5 / 5
	Total	19 / 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: babb3c2

Reviewed: 2 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.