agent-adaptive-coordinator
Agent skill for adaptive-coordinator - invoke with $agent-adaptive-coordinator
47
Quality
17%
Does it follow best practices?
Impact
100%
1.51xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-adaptive-coordinator/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is critically deficient across all dimensions. It functions only as an invocation reference rather than a skill description, providing no information about capabilities, use cases, or trigger conditions. Claude would have no basis for selecting this skill appropriately from a skill library.
Suggestions
Add concrete actions describing what the adaptive-coordinator actually does (e.g., 'Orchestrates multi-step workflows', 'Coordinates between multiple agents', 'Dynamically routes tasks based on complexity').
Include a 'Use when...' clause with natural trigger terms that describe scenarios where this skill should be selected (e.g., 'Use when tasks require coordination between multiple systems or when workflow adaptation is needed').
Specify the domain or context this coordinator operates in to distinguish it from other potential coordination skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for adaptive-coordinator' is completely abstract with no indication of what the skill actually does. | 1 / 3 |
Completeness | Missing both 'what does this do' and 'when should Claude use it'. The description only provides invocation syntax without explaining purpose or use cases. | 1 / 3 |
Trigger Term Quality | Contains only technical jargon ('adaptive-coordinator', '$agent-adaptive-coordinator') with no natural keywords a user would say. No domain-relevant terms are present. | 1 / 3 |
Distinctiveness Conflict Risk | Extremely generic - 'adaptive-coordinator' could mean anything. Without knowing what it coordinates or adapts to, it could conflict with any coordination or orchestration skill. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
35%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, treating Claude as if it needs extensive education on ML concepts, load balancing, and coordination patterns. While it contains some actionable MCP commands, the bulk consists of illustrative pseudocode classes and conceptual explanations that waste context window space. The content would benefit from aggressive trimming to focus on the specific MCP integrations and concrete decision criteria.
Suggestions
Remove the extensive Python pseudocode classes (WorkloadAnalyzer, TopologyOptimizer, etc.) and replace with concise decision tables or actual executable scripts
Cut conceptual explanations of ML, load balancing, and topology concepts - Claude knows these; focus only on this system's specific implementations
Add explicit validation checkpoints to the topology transition workflow (e.g., 'Validate performance improved by >10% before committing switch')
Split detailed algorithms and rollback procedures into separate reference files, keeping SKILL.md as a concise overview with clear navigation links
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive conceptual explanations Claude already knows (ML concepts, load balancing theory, what topologies are). The 400+ lines include massive Python class definitions that are illustrative pseudocode rather than actionable, and extensive YAML/markdown explaining obvious concepts. | 1 / 3 |
Actionability | Contains some concrete MCP commands (mcp__claude-flow__neural_patterns, etc.) that appear executable, but the Python classes are conceptual pseudocode (methods like 'self.measure_complexity' are undefined). The bash commands in hooks are specific but the main body lacks copy-paste ready implementations. | 2 / 3 |
Workflow Clarity | The 'Topology Transition Protocols' section outlines phases but lacks explicit validation checkpoints. The rollback mechanisms are described conceptually but not as executable steps. Missing concrete 'validate before proceeding' gates for topology switches which are potentially disruptive operations. | 2 / 3 |
Progressive Disclosure | Content is monolithic with no references to external files for detailed implementations. The 400+ lines could be split into separate reference files (topology algorithms, ML integration, rollback procedures). All content is inline when much could be progressively disclosed. | 2 / 3 |
Total | 7 / 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/claude-flow
- Commit
b2618f9
- 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.