docs-creator

Create or update Plate docs with conversational voice, lane-aware structure, explicit ownership, and code-backed accuracy. This is the source of truth for Plate docs style and workflow. Use for plugin pages, guides, install docs, serialization docs, API docs, and specs — anywhere both humans and agents need a clear, readable source of truth.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%

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 and exceptionally well-sequenced, with concrete commands, exact paths, per-lane templates, and a verification checklist that encodes real feedback loops. Its main weakness is conciseness — recurring guidance across overlapping voice/anti-slop sections adds length — and the absence of any bundle files leaves a large monolithic body where some material could be split into referenced files for better progressive disclosure.

Suggestions

Consolidate the recurring 'no placeholder comments' and voice rules into one authoritative section (e.g. Voice) and have Code Example Rules, Anti-Slop Rules, and the Verification Checklist reference it instead of restating it, to cut length and reduce drift risk.

Move the eight Lane Templates and/or the Writing Voice Examples into separate reference files (e.g. references/lane-templates.md, references/voice-examples.md) linked from the body, so SKILL.md stays a lean overview with one-level-deep references.

Tighten the shadcn-style and anti-slop lists, which overlap in banned openings, marketing adjectives, and demo-faking rules, into a single deduplicated guidance block.

Dimension	Reasoning	Score
Conciseness	The ~700-line body is dense and mostly earns its place, but guidance recurs across overlapping sections — e.g. 'no placeholder comments' appears in Voice, Code Example Rules, Anti-Slop Rules, and the Verification Checklist, and voice rules split across 'Voice', 'Shadcn Style Layer', and 'Writing Voice Examples'. It is efficient in places but could be tightened to remove repetition. Matches the score-2 anchor of mostly efficient with some unnecessary restatement, not the lean score-3.	2 / 3
Actionability	Provides fully concrete, copy-paste-ready guidance — exact commands like 'pnpm --filter www build:source' and 'pnpm --filter www check:docs', exact paths like 'content/docs/meta.json' and 'apps/www/src/registry/registry-kits.ts', real MDX component names, and per-lane required-shape templates. Matches the score-3 anchor for executable, specific, copy-paste-ready instructions.	3 / 3
Workflow Clarity	Includes an explicit 11-step Workflow and a Verification Checklist with concrete validation checkpoints (MDX parse, check:docs parity, route render proof, source-parity regeneration). The Source Of Truth section encodes a fix→regenerate→verify feedback loop for output drift. Matches the score-3 anchor for a clear sequence with explicit validation steps and error-recovery loops.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the entire doctrine lives inline in one ~700-line file with no external file references. Sections are well-organized, but at this length content like the eight Lane Templates and Writing Voice Examples could be split into separate reference files rather than kept monolithic. Matches the score-2 anchor of some structure with content that should be separate kept inline, not the score-3 well-signaled one-level-deep split.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 concise yet specific, naming concrete capabilities and an explicit 'Use for' trigger that enumerates the doc types it owns. It cleanly answers both what the skill does and when to invoke it, with a distinct Plate-docs niche that minimizes conflict risk. No vague fluff or over-claims are present.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'create or update Plate docs', 'conversational voice, lane-aware structure, explicit ownership, and code-backed accuracy' — rather than vague language. Matches the score-3 anchor that names several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ('Create or update Plate docs with conversational voice...') and when ('Use for plugin pages, guides, install docs... anywhere both humans and agents need a clear, readable source of truth'). Matches the score-3 anchor with an explicit 'Use when/Use for' trigger clause.	3 / 3
Trigger Term Quality	Covers natural terms users would say — 'plugin pages, guides, install docs, serialization docs, API docs, and specs' plus 'Plate docs' — giving good coverage rather than technical jargon. Matches the score-3 anchor for good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	Scoped narrowly to Plate docs style/workflow with distinct, domain-specific triggers, making it unlikely to fire for unrelated skills. Uses consistent third-person voice; no first/second-person penalty applies. Matches the score-3 clear-niche anchor.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (725 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

	Total	13 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/docs-creator/SKILL.md
Commit: 45116fd

Reviewed: about 14 hours 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.