agent-adaptive-coordinator
Agent skill for adaptive-coordinator - invoke with $agent-adaptive-coordinator
40
6%
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 is an extremely weak description that provides essentially no useful information beyond the invocation command. It fails on every dimension: it describes no concrete capabilities, includes no natural trigger terms, answers neither 'what' nor 'when', and is completely indistinguishable from any other generic agent skill.
Suggestions
Add concrete actions describing what the adaptive-coordinator actually does (e.g., 'Coordinates multi-step workflows by dynamically routing tasks to specialized agents').
Add an explicit 'Use when...' clause with natural trigger terms that describe the situations where this skill should be selected (e.g., 'Use when the user needs to orchestrate complex tasks across multiple domains or when a request requires dynamic task decomposition').
Remove the invocation instruction ('invoke with $agent-adaptive-coordinator') from the description and replace it with functional content that helps Claude distinguish this skill from others.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for adaptive-coordinator' is entirely abstract and gives 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 invocation command, providing no functional or contextual information. | 1 / 3 |
Trigger Term Quality | The only keyword is 'adaptive-coordinator', which is technical jargon and not something a user would naturally say. There are no natural trigger terms that would help Claude match user requests to this skill. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it could apply to virtually anything. 'Adaptive-coordinator' gives no clear niche, and without any specifics, there's no way to distinguish it from other skills. | 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 an over-engineered conceptual document that reads more like a software architecture whitepaper than an actionable skill for Claude. It contains extensive pseudocode classes with undefined methods, verbose explanations of ML concepts Claude already knows, and generic best practices that add no operational value. The actual guidance for what Claude should do when invoked as an adaptive coordinator is almost entirely absent.
Suggestions
Replace conceptual Python pseudocode classes with actual executable commands or concrete decision trees Claude can follow step-by-step when coordinating tasks.
Reduce content to under 100 lines by removing the KPI lists, best practices, ML optimization tips, and architecture diagrams—focus on the specific MCP commands and decision logic Claude needs.
Add a clear operational workflow: 'When you receive a task, do step 1, then step 2...' with explicit validation checkpoints and concrete examples of inputs/outputs.
Split advanced content (rollback mechanisms, predictive scaling, ML integration details) into separate referenced files, keeping SKILL.md as a concise overview with quick-start guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~350+ lines. Contains extensive Python class definitions that are conceptual pseudocode (not executable), lengthy YAML descriptions, and explanatory content about ML concepts Claude already understands. The ASCII architecture diagram, KPI lists, and best practices sections are largely generic padding that don't provide actionable value. | 1 / 3 |
Actionability | Despite containing many code blocks, almost none are executable. The Python classes are conceptual illustrations (e.g., `self.initialize_ml_model()`, `self.collect_performance_metrics()`) with undefined methods. The bash MCP commands appear to reference specific tool APIs but lack context on actual invocation patterns, expected outputs, or error handling. The skill describes rather than instructs. | 1 / 3 |
Workflow Clarity | The Topology Transition Protocols section provides a 4-phase migration process with some validation steps, and the rollback mechanism is described. However, the actual workflow for when and how to coordinate is buried in conceptual code. There's no clear step-by-step operational workflow for Claude to follow when receiving a task, and validation checkpoints are described abstractly rather than concretely. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files. All content—from topology decision matrices to ML integration to rollback mechanisms to KPIs—is inlined in a single massive document. There's no separation of quick-start from advanced content, and no navigation aids or cross-references. | 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
ccb062f
- 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.