agent-adaptive-coordinator
Agent skill for adaptive-coordinator - invoke with $agent-adaptive-coordinator
36
0%
Does it follow best practices?
Impact
100%
1.51xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-adaptive-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 zero functional content. It fails on every dimension: it does not describe what the skill does, when to use it, or include any natural trigger terms. It would be indistinguishable from any other generic agent skill in a multi-skill environment.
Suggestions
Add concrete actions describing what the adaptive-coordinator actually does (e.g., 'Coordinates multi-step workflows by delegating subtasks to specialized agents and synthesizing results').
Add an explicit 'Use when...' clause with natural trigger terms that describe scenarios where this skill should be selected (e.g., 'Use when the user requests a complex task requiring multiple coordinated steps or parallel agent execution').
Remove the invocation instruction ('invoke with $agent-adaptive-coordinator') 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 adaptive-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 the skill's name and how to invoke it, providing no functional or contextual information. | 1 / 3 |
Trigger Term Quality | No natural keywords a user would say are present. 'adaptive-coordinator' is internal jargon, and 'invoke with $agent-adaptive-coordinator' is a technical invocation instruction, not a trigger term. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it could apply to virtually anything. 'Adaptive-coordinator' gives no clear niche, making it impossible to distinguish from other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
0%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 aspirational design document rather than an actionable skill file. It contains extensive pseudocode classes and conceptual frameworks that describe what an adaptive coordinator *could* do, but provides no executable instructions Claude can actually follow. The content is extremely verbose, filled with undefined method calls and hypothetical ML integrations, and lacks any concrete workflow with validation steps.
Suggestions
Replace all pseudocode Python classes with actual executable MCP commands or concrete step-by-step instructions that Claude can follow to perform topology switching.
Reduce content to under 100 lines by removing the KPI lists, best practices, ML optimization tips, and conceptual architecture—focus only on the specific commands and decision logic Claude needs.
Add a clear, numbered workflow with explicit validation checkpoints (e.g., 'Check swarm_status output before proceeding to topology switch') since topology changes are potentially destructive operations.
Extract reference material (topology decision matrix, rollback mechanisms, performance metrics) into separate linked files and keep SKILL.md as a concise operational guide.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~350+ lines. Contains extensive Python class definitions that are conceptual pseudocode (not executable in the MCP context), lengthy YAML descriptions of topology switching conditions, and detailed explanations of ML concepts Claude already understands. The ASCII architecture diagram, KPI lists, and best practices sections add significant bulk without actionable value. | 1 / 3 |
Actionability | Despite containing code blocks, almost none of it is executable. The Python classes (WorkloadAnalyzer, TopologyOptimizer, AdaptiveAgentAllocator, PredictiveLoadManager, TopologyRollback) are all pseudocode with undefined methods like self.collect_performance_metrics() and self.initialize_ml_model(). The MCP commands in bash blocks appear to be hypothetical API calls with no verification they actually exist. There's no concrete, copy-paste-ready workflow Claude can follow. | 1 / 3 |
Workflow Clarity | While there's a 4-phase 'Seamless Migration Process' in YAML, it's entirely abstract with no concrete commands or validation checkpoints. The actual sequence of operations Claude should perform is never clearly defined. For a coordinator that performs destructive topology switches, there are no real validation steps—just conceptual rollback classes with undefined methods. | 1 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files. All content—from architecture diagrams to Python classes to KPI definitions to best practices—is crammed into a single document. There's no clear hierarchy of what's essential vs. reference material, and no navigation aids or links to supplementary documentation. | 1 / 3 |
Total | 4 / 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.