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 description is essentially a placeholder that provides no useful information about the skill's capabilities, use cases, or triggers. It fails on every dimension because it only states the skill's name and invocation command without describing what it does or when it should be used.
Suggestions
Add concrete actions describing what the adaptive-coordinator actually does (e.g., 'Coordinates multi-step workflows across agents, delegates subtasks, and manages dependencies between parallel work streams').
Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when the user needs to orchestrate multiple tasks, coordinate parallel workstreams, or manage complex multi-agent workflows').
Replace the generic 'Agent skill for' phrasing with a third-person description of specific capabilities to make the skill distinguishable from other agent or coordination skills.
| 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 conflict with virtually any coordination or agent-related skill. There is nothing distinctive to differentiate 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 overly ambitious, verbose document that reads more like a conceptual architecture whitepaper than an actionable skill for Claude. The Python code blocks are non-executable pseudocode with undefined methods, the MCP commands lack integration context, and the entire content is crammed into a single monolithic file. The skill explains many concepts Claude already understands (ML, load balancing, topology patterns) while failing to provide concrete, executable guidance for actual coordination tasks.
Suggestions
Replace all pseudocode Python classes with actual executable commands or concrete MCP tool invocations that Claude can directly use, removing conceptual class definitions entirely.
Reduce content by 70%+ by removing explanations of concepts Claude already knows (what topologies are, ML basics, generic best practices) and focusing only on the specific decision criteria and commands needed.
Add concrete validation checkpoints with actual commands: e.g., after a topology switch, specify the exact MCP command to verify performance improved and the threshold for rollback.
Split content into a concise SKILL.md overview (~50 lines) with references to separate files for topology decision matrix, MCP command reference, and adaptation algorithms.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~350+ lines. Contains extensive Python class definitions that are pseudocode/conceptual (not executable), explains concepts Claude already knows (what topologies are, what load balancing is, what reinforcement learning is), and includes lengthy KPI descriptions and best practices that are generic advice rather than actionable skill content. | 1 / 3 |
Actionability | Despite containing many code blocks, nearly all Python code is pseudocode with undefined methods (e.g., self.collect_performance_metrics(), self.initialize_ml_model()). The bash MCP commands appear concrete but lack context on when/how to actually invoke them in a real workflow. The skill describes concepts rather than providing executable, copy-paste-ready instructions. | 1 / 3 |
Workflow Clarity | The 'Topology Transition Protocols' section provides a phased migration process and the rollback mechanism describes trigger conditions, which shows some workflow awareness. However, there are no concrete validation checkpoints with actual commands, and the overall sequencing of when to apply which topology is described abstractly through decision matrices rather than clear step-by-step instructions with verification. | 2 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text with no references to external files. All content—from architecture diagrams to Python classes to best practices—is inlined in a single massive document. There is no bundle structure to support progressive disclosure, and the content would greatly benefit from being split 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/claude-flow
- Commit
d29d87f
- 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.