agent-collective-intelligence-coordinator
Agent skill for collective-intelligence-coordinator - invoke with $agent-collective-intelligence-coordinator
39
7%
Does it follow best practices?
Impact
94%
1.74xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-collective-intelligence-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 doesn't describe what the skill does, when to use it, or provide any natural trigger terms. Claude would have no basis for selecting this skill appropriately from a list of available skills.
Suggestions
Add concrete actions describing what the skill does (e.g., 'Coordinates multi-agent brainstorming sessions, aggregates diverse perspectives, synthesizes consensus from multiple viewpoints').
Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when the user wants to gather multiple perspectives, run a brainstorming session, or synthesize ideas from different angles').
Remove the invocation command from the description and replace it with functional content — invocation syntax belongs in the skill body, not the description field used for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for collective-intelligence-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 invocation command, providing no functional or contextual information. | 1 / 3 |
Trigger Term Quality | The only keyword is 'collective-intelligence-coordinator', which is technical jargon and not something a user would naturally say. There are no natural trigger terms like specific tasks or domains. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it's impossible to distinguish it from other skills. 'Collective intelligence coordinator' could overlap with collaboration, brainstorming, aggregation, or any number of other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a conceptual architecture document than an actionable skill for Claude. It is filled with abstract descriptions of distributed systems concepts (Byzantine fault tolerance, split-brain scenarios, mesh topology) without providing concrete, executable guidance on how to actually perform any of these operations. The code examples use incorrect syntax for MCP tool calls and the majority of sections contain vague bullet points rather than specific instructions.
Suggestions
Replace abstract descriptions (e.g., 'Apply weighted voting based on expertise', 'Resolve conflicts through Byzantine fault tolerance') with concrete, executable code examples showing exactly how to perform each operation using actual MCP tool call syntax.
Add a clear sequential workflow with numbered steps and explicit validation checkpoints, e.g., 'Step 1: Read current collective state → Step 2: Validate quorum (check N agents responded) → Step 3: If quorum met, store consensus decision → Step 4: If not, retry with timeout'.
Remove verbose conceptual explanations that Claude already knows (distributed systems concepts, what consensus means) and focus on the specific tool calls, key names, and data formats unique to this system.
Either split detailed coordination patterns and error handling into separate referenced files, or significantly condense them into actionable checklists rather than abstract bullet points.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose and filled with abstract concepts Claude already understands (consensus building, Byzantine fault tolerance, cognitive load balancing). Much of the content reads like a design document rather than actionable instructions, with vague buzzwords like 'neural nexus of the hive mind system' and 'distributed cognitive processes' that waste tokens without adding clarity. | 1 / 3 |
Actionability | The JavaScript code blocks showing MCP tool calls provide some concrete guidance on memory operations, but they are not fully executable (using object literal syntax rather than proper function call syntax). Most sections (Consensus Building, Cognitive Load Balancing, Coordination Patterns) are abstract descriptions with no concrete commands or executable steps. | 2 / 3 |
Workflow Clarity | There is no clear sequenced workflow for how to actually coordinate collective intelligence. The 'Handoff Patterns' are vague three-step abstractions (e.g., 'Receive inputs → Build consensus → Distribute decisions') with no validation checkpoints, error recovery loops, or concrete steps. The 'EVERY 30 SECONDS' requirement has no mechanism for verification or what to do if synchronization fails. | 1 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no references to external files and no bundle files to support it. All content—from coordination patterns to error handling to quality standards—is dumped inline with no clear hierarchy or navigation structure for discovery. | 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
9d4a9ea
- 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.