agent-adaptive-coordinator

Agent skill for adaptive-coordinator - invoke with $agent-adaptive-coordinator

1.51x

Quality

—

Does it follow best practices?

Impact

100%

1.51x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

27%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an expansive, concept-heavy overview dominated by non-executable illustrative code and ASCII diagrams. It offers some concrete MCP commands and a phased process, but lacks executable examples, explicit validation checkpoints, and any progressive-disclosure structure.

Suggestions

Cut the conceptual ML exposition and ASCII art that Claude already knows; keep only the actionable topology-switching thresholds and MCP command recipes.

Replace the illustrative Python class shells with either fully executable code or concrete prose instructions, and add explicit validation/rollback checkpoints ('verify switch improved performance before committing') to the migration workflow.

Split the detailed command catalogs and reference matrices into files under references/ and link to them from a concise overview, so the main SKILL.md is a lean entry point.

Dimension	Reasoning	Score
Conciseness	The ~400-line body is padded with ASCII art diagrams, buzzwords ('intelligent orchestrator', 'emergent behaviors', 'reinforcement learning'), and conceptual ML explanations Claude already knows, far exceeding what the task requires.	1 / 3
Actionability	The bash MCP commands (e.g. 'mcp__claude-flow__neural_train coordination --epochs=50') offer some concrete guidance, but the Python blocks are illustrative class shells calling undefined methods (self.measure_complexity, self.predict_performance) rather than executable, copy-paste-ready code.	2 / 3
Workflow Clarity	The four-phase Topology Transition Protocol and rollback triggers provide a recognizable sequence, but validation checkpoints are only implicit and the underlying operations are abstract rather than concrete verify-then-proceed steps.	2 / 3
Progressive Disclosure	The content is a monolithic wall of text with no bundle files present (references/, scripts/, assets/ are all absent) and no one-level-deep references signaled, so everything is inlined in one file.	1 / 3
	Total	6 / 12 Passed

Description

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is pure boilerplate that identifies the skill and its invocation token without describing any capability or usage trigger. It fails on all four dimensions because it conveys nothing a user or Claude could act on.

Suggestions

Replace the boilerplate with a concrete statement of what the coordinator does, e.g. 'Dynamically switches swarm topology and rebalances agent workloads based on real-time performance metrics.'

Add an explicit 'Use when...' clause with natural trigger terms users would say, such as 'Use when coordinating multi-agent swarms, optimizing agent load distribution, or switching between hierarchical/mesh/ring topologies.'

Use third-person action voice ('Switches', 'Rebalances') and avoid the invocation-syntax filler that adds no information.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for adaptive-coordinator - invoke with $agent-adaptive-coordinator' names no concrete actions at all, only the skill's existence and invocation syntax, matching the 'vague or no actions' anchor.	1 / 3
Completeness	It states neither what the skill does nor when to use it; there is no 'Use when...' clause or equivalent trigger guidance, so both 'what' and 'when' are missing.	1 / 3
Trigger Term Quality	It contains only the skill name 'adaptive-coordinator' and the invocation token '$agent-adaptive-coordinator' — technical jargon a user would never say naturally, with no keyword coverage of what the skill actually does.	1 / 3
Distinctiveness Conflict Risk	The text is generic meta-boilerplate ('Agent skill for ...') that could apply to any skill and provides no distinct niche or triggers, so it would conflict with many skills.	1 / 3
	Total	4 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Commit: 03d4f84

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.