agent-crdt-synchronizer
Agent skill for crdt-synchronizer - invoke with $agent-crdt-synchronizer
41
11%
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
7%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 extremely minimal and essentially non-functional as a skill selector. It provides no information about what the skill does, when to use it, or what user requests should trigger it. The only marginally positive aspect is the unique name 'crdt-synchronizer' which provides some distinctiveness.
Suggestions
Add concrete actions describing what the skill does, e.g., 'Synchronizes data across distributed nodes using conflict-free replicated data types (CRDTs), handles merge conflicts, and maintains eventual consistency.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user needs to synchronize distributed state, resolve merge conflicts in replicated data, or work with CRDTs.'
Remove the invocation instruction ('invoke with $agent-crdt-synchronizer') from the description as it wastes space that should be used for capability and trigger information.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains 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 it's an 'agent skill' and how to invoke it, 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 user-facing terms. A user would not naturally say 'crdt-synchronizer' when seeking help with conflict-free replicated data types or synchronization tasks. | 1 / 3 |
Distinctiveness Conflict Risk | The specific name 'crdt-synchronizer' is somewhat distinctive and unlikely to conflict with many other skills, but the lack of any description of what it does means Claude cannot reliably distinguish when to use it versus other data synchronization or collaboration skills. | 2 / 3 |
Total | 5 / 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 dump of standard CRDT algorithm implementations that Claude already knows, with no clear workflow guidance on when or how to apply them. It references fictional MCP tools and undefined dependencies, making the code illustrative rather than actionable. The content would benefit enormously from being condensed to a concise decision guide with project-specific conventions, splitting detailed implementations into separate reference files.
Suggestions
Replace full CRDT implementations with a concise decision table (which CRDT type for which use case) and project-specific configuration/conventions that Claude wouldn't already know.
Add a clear workflow section with numbered steps for setting up CRDT synchronization, including validation checkpoints for verifying convergence and error recovery.
Split detailed implementations into separate reference files (e.g., GCOUNTER.md, ORSET.md) and keep SKILL.md as a brief overview with navigation links.
Remove or replace references to fictional MCP tools (neural_patterns, metrics_collect) with real, executable integration patterns.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~700+ lines of code. Most of this is standard CRDT implementation that Claude already knows (G-Counter, OR-Set, LWW-Register, RGA are well-documented algorithms). The skill dumps full class implementations rather than providing concise, project-specific guidance. | 1 / 3 |
Actionability | The code examples are relatively complete JavaScript implementations, but they reference undefined dependencies (VectorClock, SyncScheduler, PNCounter, ORMap) and fictional MCP tools (memory_usage, metrics_collect, neural_patterns). The code is illustrative rather than truly executable or copy-paste ready. | 2 / 3 |
Workflow Clarity | There is no clear workflow or step-by-step process for when/how to use these CRDTs. The skill presents class implementations without explaining when to choose which CRDT type, how to set up synchronization, or any validation/verification steps. No feedback loops for error recovery in synchronization. | 1 / 3 |
Progressive Disclosure | Monolithic wall of code with no references to external files. All CRDT implementations are inlined in a single massive document. Content should be split into separate reference files for each CRDT type, with the main skill providing a concise overview and decision guide. | 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
ccb062f
- 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.