agent-v3-queen-coordinator
Agent skill for v3-queen-coordinator - invoke with $agent-v3-queen-coordinator
36
0%
Does it follow best practices?
Impact
100%
6.25xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-v3-queen-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 virtually no useful information. It fails on every dimension: it names no concrete actions, includes no natural trigger terms, answers neither 'what' nor 'when', and is indistinguishable from any other generic agent skill. It reads more like a stub or placeholder than a functional skill description.
Suggestions
Replace the entire description with concrete actions the skill performs (e.g., 'Coordinates task distribution across multiple agents, manages work queues, and tracks completion status').
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 needs to orchestrate parallel tasks, manage agent workflows, or coordinate multi-step processes').
Remove the invocation syntax ('invoke with $agent-v3-queen-coordinator') from the description and focus on communicating the skill's purpose and capabilities so Claude can make informed selection decisions.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for v3-queen-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 it's an 'agent skill' and how to invoke it, providing no functional or contextual information. | 1 / 3 |
Trigger Term Quality | There are no natural keywords a user would say. 'v3-queen-coordinator' is an internal/technical identifier, not a term any user would naturally use when requesting help. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that Claude would have no basis to distinguish this skill from any other. The only distinguishing element is the opaque name 'v3-queen-coordinator', which conveys no meaning about the skill's purpose. | 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 reads as a project management overview or README rather than an actionable skill for Claude. It describes a 15-agent coordination topology and 14-week timeline but provides zero concrete instructions on how to actually perform coordination — no commands for creating/assigning GitHub issues, no protocols for inter-agent communication, no decision trees for task prioritization, and no validation steps. The hooks in the frontmatter reference tools (agentic-flow, gh) but the body never explains how to use them.
Suggestions
Replace the high-level phase descriptions with concrete, executable workflows: e.g., 'To assign work to Agent #7: `gh issue create --title "ADR-005: Memory Unification" --assignee agent-7 --label v3-phase2`' with validation steps.
Add actionable coordination protocols: how to check agent status, handle blocked agents, resolve conflicts between agents, and verify deliverables before phase transitions.
Remove or drastically condense the ASCII topology diagram and success metrics — these are informational context, not instructions. Replace with a brief agent roster table and link to a separate TOPOLOGY.md if needed.
Add concrete examples of coordination decisions: 'When Agent #7 reports AgentDB migration complete, verify by running `npm test -- --filter=agentdb` before unblocking Agent #10 for integration work.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is heavily padded with organizational context, project management details, and high-level descriptions that Claude doesn't need. The ASCII topology diagram, phase breakdowns, and success metrics are informational but not actionable — they describe a project plan rather than teaching Claude how to do something. Much of this reads like a project README, not a skill. | 1 / 3 |
Actionability | There are no concrete commands, executable code, or specific step-by-step instructions for Claude to follow. The content describes what agents should do at a high level ('Security architecture, CVE remediation') but never tells Claude how to actually coordinate agents, create issues, assign work, or perform any specific task. It's entirely descriptive rather than instructive. | 1 / 3 |
Workflow Clarity | While phases are listed with week ranges, there is no actionable workflow — no sequenced steps Claude should execute, no validation checkpoints, no error recovery, and no concrete coordination protocol. The phases describe project milestones, not executable workflows for the agent to follow. | 1 / 3 |
Progressive Disclosure | The content is a monolithic block with no references to supporting files, no links to ADR documents, no pointers to agent-specific skill files, and no bundle files. For a skill claiming to coordinate 15 agents across 10 ADRs, there should be extensive references to detailed materials, but none exist. | 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/claude-flow
- Commit
e6dc21f
- 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.