agent-crdt-synchronizer

Agent skill for crdt-synchronizer - invoke with $agent-crdt-synchronizer

2.93x

Quality

Does it follow best practices?

Impact

97%

2.93x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-crdt-synchronizer/SKILL.md

Quality

Discovery

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is essentially a label and invocation command with no substantive content. It fails on every dimension: it does not explain what the skill does, when to use it, or provide any natural trigger terms. It would be nearly impossible for Claude to correctly select this skill from a pool of available skills.

Suggestions

Add concrete actions describing what the skill does, e.g., 'Synchronizes data structures using CRDTs (Conflict-free Replicated Data Types), resolves merge conflicts, and maintains consistency across distributed nodes.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user needs real-time data synchronization, conflict-free merging, distributed state management, or CRDT operations.'

Include file types, protocols, or domain-specific terms users might mention to improve trigger term coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description provides no concrete actions whatsoever. 'Agent skill for crdt-synchronizer' is entirely abstract and does not describe what the skill actually does.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states the invocation command, providing no functional or contextual information.	1 / 3
Trigger Term Quality	The only keyword is 'crdt-synchronizer', which is technical jargon. There are no natural language terms a user would say, such as 'sync', 'conflict resolution', 'real-time collaboration', or 'merge'.	1 / 3
Distinctiveness Conflict Risk	The description is so vague that it could overlap with any agent-based or synchronization-related skill. There are no distinct triggers or domain-specific details to differentiate it.	1 / 3
	Total	4 / 12 Passed

Implementation

14%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is an extensive but unfocused dump of CRDT implementation code that fails to provide actionable guidance for Claude. It explains concepts Claude already understands (CRDT theory, merge semantics, vector clocks) through verbose class implementations rather than providing concise, project-specific instructions. The lack of workflow guidance, validation steps, and progressive disclosure makes this more of a reference textbook than a usable skill.

Suggestions

Reduce content to a concise overview (under 100 lines) covering only project-specific CRDT usage patterns, configuration, and which CRDT types to use for which scenarios — remove textbook implementations Claude already knows.

Add a clear workflow section with numbered steps for common tasks like 'setting up a new CRDT instance', 'synchronizing with peers', and 'resolving sync failures', including explicit validation checkpoints.

Split detailed implementations into separate reference files (e.g., CRDT_TYPES.md, DELTA_SYNC.md, CONSENSUS_INTEGRATION.md) and reference them from a lean SKILL.md overview.

Replace or remove references to undefined/fictional APIs (mcpTools.neural_patterns, mcpTools.metrics_collect) or document what these actually are and how to access them.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~600+ lines of implementation code. Claude already understands CRDT concepts, data structures, and JavaScript patterns. The skill dumps full class implementations for G-Counter, OR-Set, LWW-Register, RGA, Delta-State framework, Causal Tracker, Composite CRDT, and Consensus Integration — most of which is textbook CRDT theory Claude already knows. Very little of this is project-specific or novel.	1 / 3
Actionability	The code examples are relatively complete JavaScript implementations, but they reference undefined dependencies (VectorClock, SyncScheduler, PNCounter, ORMap, sendSyncRequest, etc.) making them not truly executable. The MCP integration hooks reference fictional tool APIs (mcpTools.memory_usage, mcpTools.neural_patterns) without explaining what they actually are or how to use them.	2 / 3
Workflow Clarity	There is no clear workflow or sequence of steps for how to actually use this synchronizer. The skill presents class implementations but never explains when to use which CRDT type, how to set up synchronization, or what validation/verification steps to follow. No error recovery guidance or checkpoints for the synchronization process.	1 / 3
Progressive Disclosure	Monolithic wall of code with no references to external files and no bundle files provided. All implementations are inlined in a single massive document. Content that could be split into separate reference files (individual CRDT implementations, MCP integration, consensus integration) is all dumped into one file with no navigation structure.	1 / 3
	Total	5 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1002 lines); consider splitting into references/ and linking	Warning

	Total	10 / 11 Passed

Repository: ruvnet/ruflo
Commit: 48ca369

Reviewed: 5 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.