agent-crdt-synchronizer
Agent skill for crdt-synchronizer - invoke with $agent-crdt-synchronizer
39
7%
Does it follow best practices?
Impact
97%
2.93xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-crdt-synchronizer/SKILL.mdQuality
Discovery
0%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 with an invocation command, providing no useful information about what the skill does, when to use it, or what problems it solves. It fails on every dimension because it contains no concrete actions, no natural trigger terms, no 'when to use' guidance, and insufficient detail for disambiguation. This is among the weakest possible skill descriptions.
Suggestions
Add concrete actions describing what the skill does, e.g., 'Synchronizes data across distributed nodes using CRDTs (Conflict-free Replicated Data Types), resolves merge conflicts automatically, and maintains eventual consistency.'
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 mentions CRDTs.'
Remove the invocation instruction ('invoke with $agent-crdt-synchronizer') from the description field, as it wastes space that should be used for capability and trigger information.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description provides no concrete actions whatsoever. 'Agent skill for crdt-synchronizer' is entirely vague—it doesn't describe what the skill does, only names itself. There are no listed capabilities. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. There is no 'Use when...' clause and no explanation of functionality—only an invocation command. | 1 / 3 |
Trigger Term Quality | The only potentially relevant term is 'crdt-synchronizer', which is a technical/internal name rather than a natural keyword a user would say. No natural language trigger terms like 'sync', 'conflict resolution', 'real-time collaboration', or 'CRDT' are provided. | 1 / 3 |
Distinctiveness Conflict Risk | While 'crdt-synchronizer' is a unique name, the description is so vague that Claude would have no basis to distinguish when to use this skill versus any other. The lack of described functionality makes it impossible to properly differentiate. | 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 extremely verbose code dump of CRDT implementations that provides little actionable guidance beyond what Claude already knows about CRDTs. It lacks any workflow structure, validation steps, or progressive disclosure, and references undefined dependencies and fabricated MCP tools. The content would benefit enormously from being condensed to a concise overview with clear usage workflows and references to separate implementation files.
Suggestions
Reduce the content to a concise overview (under 100 lines) covering when to use each CRDT type, with a quick-start example, and move full implementations to separate reference files (e.g., GCOUNTER.md, ORSET.md).
Add a clear workflow section with numbered steps for setting up CRDT synchronization, including validation/verification checkpoints (e.g., verifying convergence after sync).
Remove or replace references to fabricated MCP tools (mcpTools.memory_usage, mcpTools.neural_patterns) with real, documented integration points.
Eliminate boilerplate code patterns (observer setup, trivial getters) that Claude can generate on its own, and focus on the non-obvious aspects like conflict resolution edge cases and merge semantics.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~700+ lines of code. The skill dumps full class implementations for G-Counter, OR-Set, LWW-Register, RGA, Delta-State CRDT, CausalTracker, CRDTComposer, CompositeCRDT, and CRDTConsensusIntegrator. Much of this is standard CRDT theory that Claude already knows, and the implementations include obvious boilerplate (observer patterns, getters/setters) that waste tokens. | 1 / 3 |
Actionability | The code examples are relatively complete JavaScript class implementations, but they reference undefined dependencies (VectorClock, SyncScheduler, PNCounter, ORMap) and use pseudo-MCP tools (mcpTools.memory_usage, mcpTools.neural_patterns) that appear fabricated. The code is illustrative rather than truly executable or copy-paste ready in any real environment. | 2 / 3 |
Workflow Clarity | There is no clear workflow or step-by-step process for when/how to use this synchronizer. The skill is a code dump of class implementations without sequencing, validation checkpoints, or guidance on how to orchestrate CRDT synchronization in practice. No error recovery or verification steps are defined. | 1 / 3 |
Progressive Disclosure | The entire content is a monolithic wall of code with no references to external files and no layered organization. All CRDT implementations are inlined rather than being split into separate reference files. The sheer volume makes it difficult to navigate or find specific information. | 1 / 3 |
Total | 5 / 12 Passed |
Validation
90%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
398f7c2
- Reviewed
Table of Contents
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.