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

79%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/docs-creator/SKILL.md

Quality

Content

71%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.

A highly actionable, well-structured doctrine skill with executable commands, exact file paths, and good/bad examples, plus a real workflow and verification checklist. Its weaknesses are length and repetition (~725 lines where tighter editing could cut a third) and a complete absence of progressive disclosure — lane templates and examples are prime candidates for reference files that would shrink the always-loaded body.

Suggestions

Move the eight 'Lane Templates' sections into a references/ file (e.g. references/lane-templates.md) and keep a one-line lane map in SKILL.md pointing to it — this alone would cut the body by roughly a third.

Deduplicate repeated rules (placeholder comments, 'ComponentPreview' demo checks, banned marketing adjectives) by consolidating them into the single 'Anti-Slop Rules' or 'Code Example Rules' section and removing the duplicates from 'Voice' and 'Demos and Previews'.

Add explicit error-recovery feedback loops to the Workflow or Verification Checklist — e.g. 'if build:source fails, fix MDX syntax and re-run before proceeding' — so validation acts as a checkpoint sequence rather than a passive checklist.

Dimension	Reasoning	Score
Conciseness	The body is dense rule content rather than padded prose, but at ~725 lines it includes notable redundancy: placeholder-comment bans appear in both 'Voice' and 'Code Example Rules', 'ComponentPreview' rules appear in both 'Demos and Previews' and 'Anti-Slop Rules', banned openings repeat across sections, and the goal-template section repeats three near-identical bash blocks. Not a 2 because there is little explanation of concepts Claude already knows — nearly every line is project-specific doctrine — but it could be tightened considerably.	3 / 5
Actionability	Fully executable guidance throughout: copy-paste commands ('node .agents/skills/autogoal/scripts/create-goal-scratchpad.mjs --template docs ...', 'pnpm --filter www build:source', 'pnpm --filter www check:docs'), exact file paths ('content/docs/meta.json', 'apps/www/src/registry/registry-kits.ts', 'registry-kits.ts'), explicit MDX component usage rules, and concrete bad/good writing examples. This covers the common cases for a style/workflow skill.	5 / 5
Workflow Clarity	An explicit 11-step 'Workflow' sequence plus a thorough 'Verification Checklist' with concrete validation commands (MDX parse check, docs parity check, route check). Not a 5 because error-recovery feedback loops are not spelled out — the checklist says what to verify but not what to do when a check fails, and validation lives in a separate section from the workflow steps rather than being interleaved.	4 / 5
Progressive Disclosure	The skill is a single monolithic file with no bundle files (no references/, scripts/, or assets/) and no one-level-deep pointers — everything, including eight detailed lane templates and the shadcn corpus list, is inlined in SKILL.md. It is well-structured with clear headings, which keeps it above a 2 (navigation is possible), but content that clearly belongs in separate reference files (lane templates, writing voice examples, verification checklist) is inlined.	3 / 5
	Total	15 / 20 Passed

Description

87%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: it states what the skill does, gives an explicit 'Use for' trigger clause with concrete page-type surfaces, and is tightly scoped to Plate docs. The main weakness is light use of internal jargon ('lane-aware', 'code-backed accuracy') and a few missing natural synonyms for documentation work.

Dimension	Reasoning	Score
Specificity	Lists several specific actions and qualities — 'Create or update Plate docs with conversational voice, lane-aware structure, explicit ownership, and code-backed accuracy' — naming concrete dimensions of the work. Falls short of 5 because terms like 'lane-aware structure' and 'code-backed accuracy' are jargon that assumes prior knowledge of this repo's docs system rather than fully concrete actions.	4 / 5
Completeness	Clearly answers both 'what' (create or update Plate docs with voice, structure, ownership, and accuracy guarantees) and 'when' with an explicit 'Use for' clause enumerating concrete trigger surfaces (plugin pages, guides, install docs, serialization docs, API docs, specs). Not below 5 since neither half is vague or merely implied.	5 / 5
Trigger Term Quality	Good natural keyword coverage: 'plugin pages, guides, install docs, serialization docs, API docs, and specs' are phrases a user working on Plate docs would plausibly say. Missing common variations like 'documentation', 'docs page', 'changelog', 'README', or 'write/update the docs' phrasing users often use.	4 / 5
Distinctiveness Conflict Risk	Scoped tightly and repeatedly to 'Plate docs' — a clear niche with distinct triggers unlikely to fire for unrelated skills. A generic docs skill would conflict, but the Plate qualifier plus the specific page-type list makes overlap risk minimal.	5 / 5
	Total	18 / 20 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: 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.