yjs

Apply Epicenter’s Yjs 14 patterns for row documents, transactions, persistence, and synchronization. Use when working with `@y/y`, CRDTs, collaborative editing, awareness, or Yjs storage and providers.

Quality

86%

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

86%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 dense, well-structured knowledge skill that assumes competence and splits detail into real reference files. The main weakness is that the reference files still teach the retired Yjs 13 API (Y.Map/Y.Array/getMap) that the body explicitly retires, an inconsistency that slightly undercuts actionability.

Suggestions

Update references/document-design.md and references/debugging.md to the v14 single-shared-type model (Y.Type via doc.get) so the bundle matches the body's retirement of Y.Map/Y.Array/Y.Text.

Add a short copy-paste-ready snippet for the most common write path (table.update + reading the content node) beyond the single illustrative example, to lift actionability.

Make the hydration-order sequence an explicit numbered workflow with a validation/failure-loud checkpoint so the persistence guidance reads as a checklist rather than prose.

Dimension	Reasoning	Score
Conciseness	Lean and information-dense with no preamble explaining concepts Claude already knows; assumes competence and every line earns its place.	5 / 5
Actionability	Provides concrete API calls, pinned file paths, and an illustrative TS snippet, but a substantial share of guidance is anti-pattern/principle statements rather than copy-paste-ready code covering the common cases.	4 / 5
Workflow Clarity	Topic-organized with explicit sequencing where it matters (e.g. hydrate before attaching the updateV2 listener) and built-in failure-loudness, though it is a reference skill rather than a linear multi-step workflow with explicit validation checkpoints.	4 / 5
Progressive Disclosure	Overview body points to two real one-level-deep reference files (document-design.md, debugging.md) with clearly signaled inline cues, and content is appropriately split for navigation.	5 / 5
	Total	18 / 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, specific description with concrete capabilities and an explicit trigger clause. Minor keyword-synonym gaps keep specificity and trigger quality just below full marks.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities ('row documents, transactions, persistence, and synchronization') rather than vague language, but the coverage of Yjs operations is not exhaustive.	4 / 5
Completeness	Clearly states what the skill does (Yjs 14 patterns for row documents, transactions, persistence, synchronization) and gives an explicit 'Use when' clause listing concrete triggers.	5 / 5
Trigger Term Quality	Includes natural trigger terms ('CRDTs, collaborative editing, awareness') and the @y/y package name, though common synonyms a user might say (e.g. 'real-time sync', file extensions) are absent.	4 / 5
Distinctiveness Conflict Risk	A clear niche (Yjs 14 / @y/y for Epicenter) with distinct, specific triggers that are unlikely to fire for unrelated skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 5 suspicious	Warning

	Total	15 / 16 Passed

Repository: EpicenterHQ/epicenter
Path: .agents/skills/yjs/SKILL.md
Commit: ecba024

Reviewed: 6 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.