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 description is essentially a label and invocation command with no substantive content. It fails on every dimension: it doesn't describe what the skill does, when to use it, or provide any natural language 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 sync-coordinator actually does (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 changes, resolve conflicts, or coordinate updates across multiple sources').
Replace the invocation instruction ('invoke with $agent-sync-coordinator') with functional description content—invocation details belong in the skill body, not the description field.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for sync-coordinator' is entirely abstract with no indication of what it 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
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 repeated across nearly every section. The code examples are largely non-executable due to placeholder content, corrupted path separators, and mixed pseudo-code/real syntax. While it attempts to show a multi-step workflow, it lacks the validation feedback loops and error recovery specifics needed for a destructive cross-repository synchronization operation.
Suggestions
Reduce content by 60-70%: eliminate duplicate tool listings, consolidate the repeated swarm_init patterns into a single reference, and remove the non-actionable 'strategies' config objects and 'metrics' sections
Make code examples executable: replace all placeholder content like '[aligned package.json]' with actual minimal but valid content, fix path separators from '$' to '/', and ensure the gh CLI commands use correct syntax
Add explicit validation checkpoints with feedback loops: after npm test steps, include 'if tests fail: revert branch, analyze failure, fix, re-run' instructions rather than just listing test commands
Split into multiple files: move Advanced Swarm Features, Error Handling, and Synchronization Strategies into separate referenced documents, keeping SKILL.md as a concise overview with quick-start patterns
| 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 config objects that add no actionable value. Concepts like version alignment and documentation sync are over-explained with decorative pseudo-code. | 1 / 3 |
Actionability | Despite appearing code-heavy, almost none of the examples are executable. Code uses placeholder content like '[aligned package.json]', '[synchronized CLAUDE.md]', and '[GitHub modes]'. The JavaScript examples mix pseudo-API calls with invented syntax (e.g., `mcp__claude_flow__swarm_init` as async functions). Path separators use '$' instead of '/' suggesting copy-paste corruption. The 'strategies' sections are just config object literals with no instructions on how to use them. | 1 / 3 |
Workflow Clarity | The 'Complete Package Sync Workflow' section does show a sequential multi-step process with validation (npm test), and the batch synchronization example has a logical flow. However, there are no explicit validation checkpoints with error handling—tests are run but there's no 'if tests fail, do X' feedback loop. The error recovery section describes spawning agents but never shows actual recovery steps. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files. All content—usage patterns, batch examples, strategies, metrics, error handling, advanced features—is crammed into a single massive document. There's significant repetition across sections (swarm init appears in nearly every code block). Content would benefit enormously from splitting into separate reference files. | 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
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.