agent-sync-coordinator
Agent skill for sync-coordinator - invoke with $agent-sync-coordinator
42
13%
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 provides virtually no useful information for skill selection. It only states the skill's internal name and invocation command, without describing any capabilities, use cases, or trigger conditions. It fails on every dimension of the rubric.
Suggestions
Describe what the skill actually does with concrete actions (e.g., 'Synchronizes file changes across branches, resolves merge conflicts, coordinates parallel edits').
Add an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user needs to sync files, resolve conflicts, or coordinate changes across multiple sources').
Remove the invocation instruction ('invoke with $agent-sync-coordinator') from the description and replace it with functional information that helps Claude decide when to select this skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for sync-coordinator' is entirely abstract with no indication of what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states it's an agent skill and how to invoke it, providing no functional or contextual information. | 1 / 3 |
Trigger Term Quality | The only keyword is 'sync-coordinator' which is a technical internal name, not a natural term a user would say. There are no natural language trigger terms like 'synchronize', 'coordinate', 'merge', etc. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it's impossible to distinguish from any other agent or coordination skill. 'Sync-coordinator' could overlap with file syncing, data synchronization, team coordination, or many other domains. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is excessively verbose with significant redundancy—swarm initialization is shown 4+ times, tool lists are duplicated, and abstract strategy objects add no actionable value. While it demonstrates familiarity with the tooling surface area, most code examples contain placeholders rather than executable content, and the path separators appear corrupted ($ instead of /). The entire document should be condensed to roughly 1/4 its current size with concrete examples and split into supporting files for advanced topics.
Suggestions
Reduce the document to ~80 lines by eliminating duplicate swarm init patterns, removing the tools list (already in frontmatter), and cutting abstract strategy/metrics sections that don't contain executable guidance.
Replace placeholder content like '[aligned package.json]' and '[synchronized content]' with realistic, minimal but complete examples that demonstrate actual synchronization logic.
Add explicit validation checkpoints with conditional error handling (e.g., 'if npm test fails → revert branch → report error') rather than describing error recovery abstractly.
Split advanced swarm coordination, conflict resolution, and metrics into separate referenced files to improve progressive disclosure and reduce the main document's cognitive load.
| 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 with minor variations, and sections like 'Synchronization Strategies' and 'Best Practices' contain abstract configuration objects and bullet points that add no actionable value. Concepts like version alignment and documentation sync are explained repeatedly. | 1 / 3 |
Actionability | Provides concrete tool invocations and code patterns, but most examples use placeholder content like '[aligned package.json]', '[synchronized content]', and '[GitHub modes documentation]' rather than real executable code. The gh CLI commands have structural issues (using $ instead of / in paths), and the JavaScript examples mix pseudocode patterns with actual API calls in ways that aren't directly executable. | 2 / 3 |
Workflow Clarity | The batch synchronization example shows a reasonable sequence (read state → push files → run tests → track progress → store state), and validation via npm test is included. However, there are no explicit validation checkpoints with conditional branching (e.g., 'if tests fail, rollback'). The error handling section describes recovery conceptually but doesn't provide actual feedback loops or concrete rollback commands. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files despite the content being 300+ lines. Everything is inlined—strategies, metrics, error handling, advanced features—when much of this could be split into separate reference documents. No bundle files are provided, and no external references are made, resulting in an overwhelming single document. | 1 / 3 |
Total | 6 / 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
619b263
- 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.