agent-sync-coordinator
Agent skill for sync-coordinator - invoke with $agent-sync-coordinator
37
6%
Does it follow best practices?
Impact
87%
1.61xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-sync-coordinator/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 is an extremely weak description that fails on every dimension. It provides no information about what the skill does, when it should be used, or what user requests should trigger it. It reads more like a label than a functional description, making it essentially useless for skill selection among multiple options.
Suggestions
Add concrete actions describing what 'sync-coordinator' actually does (e.g., 'Synchronizes files between directories, resolves merge conflicts, coordinates multi-source data updates').
Add an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user asks to sync, synchronize, coordinate, or merge data across sources').
Replace the invocation instruction ('invoke with $agent-sync-coordinator') with functional details — invocation syntax belongs in the skill body, not the description used for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description provides no concrete actions whatsoever. 'Agent skill for sync-coordinator' is entirely vague and abstract, giving no indication of what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states it's an 'agent skill' and how to invoke it, providing no functional or contextual information. | 1 / 3 |
Trigger Term Quality | The only keyword is 'sync-coordinator', which is technical jargon and not a natural term a user would say. There are no natural language trigger terms that would help Claude match user requests to this skill. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so generic ('agent skill') that it provides no distinguishing characteristics. Without knowing what it does, it could conflict with any number of other skills or fail to be selected when needed. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
12%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is excessively verbose and repetitive, with swarm initialization and agent spawning patterns duplicated across nearly every section. The code examples are largely non-executable due to placeholder content, inconsistent syntax, and malformed paths using '$' instead of '/'. While it attempts to show a multi-step workflow, the lack of concrete validation checkpoints and actionable error recovery undermines its utility as a practical coordination guide.
Suggestions
Reduce content by 60-70%: eliminate duplicate tool listings, consolidate the repeated swarm_init/agent_spawn patterns into a single reusable template, and remove the non-actionable 'Synchronization Strategies' config objects
Make code examples executable: replace all placeholder content like '[aligned package.json]' with realistic minimal examples, fix path separators from '$' to '/', and use consistent syntax (either MCP tool call format or JavaScript, not a mix)
Add explicit validation checkpoints with error recovery: after each destructive or batch operation, include a concrete check (e.g., 'If npm test fails, revert branch with `gh api ...`') rather than abstract descriptions of spawning recovery agents
Split into multiple files: move Advanced Swarm Features, Error Handling, and Monitoring/Metrics into separate referenced documents, keeping SKILL.md as a concise overview with the core sync workflow
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines with massive redundancy. The tools list is duplicated from frontmatter, swarm initialization patterns are repeated 4+ times, and sections like 'Synchronization Strategies' contain non-executable pseudocode config objects that add no real value. Concepts like version alignment and documentation sync are over-explained. | 1 / 3 |
Actionability | Despite containing many code blocks, almost none are truly executable. Examples use placeholder content like '[aligned package.json]', '[synchronized content]', and pseudo-JavaScript that mixes MCP tool calls with async/await syntax inconsistently. The gh CLI examples use ':owner/:repo' placeholders and '$' instead of '/' in paths, making them non-functional. The 'Synchronization Strategies' section contains JavaScript config objects that aren't actionable instructions. | 1 / 3 |
Workflow Clarity | The 'Complete Package Sync Workflow' section does present a sequential multi-step process (read state → push files → run tests → track progress → store state), and the batch synchronization includes validation via npm test. However, there are no explicit validation checkpoints with error recovery feedback loops — if tests fail, there's no guidance on what to do. The error handling section describes spawning agents but provides no concrete recovery steps. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files. All content — from basic usage patterns to advanced swarm features, error handling, metrics, and best practices — is crammed into a single document. There's significant repetition across sections (swarm init patterns appear in nearly every code block). Content should be split into separate reference files for advanced features, strategies, and error handling. | 1 / 3 |
Total | 5 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- ruvnet/ruflo
- Commit
0f7c750
- 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.