agent-coordination

Agent spawning, lifecycle management, and coordination patterns. Manages 60+ agent types with specialized capabilities. Use when: spawning agents, coordinating multi-agent tasks, managing agent pools. Skip when: single-agent work, no coordination needed.

1.34x

Quality

—

Does it follow best practices?

Impact

89%

1.34x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

87%

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

The content is a tight, executable command reference with strong conciseness and actionability and clean organization. Its one gap is workflow clarity: coordinating and pool operations are batch-like yet lack explicit validation or error-recovery checkpoints.

Suggestions

Add an explicit sequenced coordination workflow (e.g., spawn -> verify active via 'agent list' -> monitor with 'agent metrics' -> stop) with a validation checkpoint after spawning to confirm agents are running before proceeding.

Document error recovery for common failures (agent failed to start, stalled agent) so the spawn/status/stop loop has a feedback path.

Dimension	Reasoning	Score
Conciseness	The body is a lean reference of one-line commands (e.g., 'npx claude-flow agent spawn --type coder --name my-coder') and tables with no preamble explaining concepts Claude already knows, matching the 'lean and efficient; every token earns its place' anchor rather than the includes-unnecessary-explanation anchor at 2.	3 / 3
Actionability	Commands are fully executable with concrete flags and values ('npx claude-flow agent pool --size 5 --type coder', 'agent list --filter active') and the routing table maps codes to specific agent sets, matching the 'fully executable; copy-paste ready' anchor rather than the pseudocode anchor at 2.	3 / 3
Workflow Clarity	A loose sequence is implied (spawn, list, status, metrics, stop) but there are no explicit validation steps or feedback loops for batch-style operations like pool management and spawning, matching 'sequence present but checkpoints missing or implicit'; this is capped at 2 per the destructive/batch-operation guideline rather than reaching the explicit-validation anchor at 3.	2 / 3
Progressive Disclosure	No bundle files exist, so there are no nested-reference problems; the single self-contained file is organized into clear logical sections (Purpose, Agent Types, Commands, Routing Codes, Best Practices), fitting the well-organized-sections standard for a reference skill rather than the inline-bloat anchor at 2.	3 / 3
	Total	11 / 12 Passed

Description

85%

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 concrete, complete, and well-scoped with explicit use/skip triggers. Its main weakness is trigger-term naturalness: the keywords lean slightly technical and lack common phrasings a user would naturally say.

Suggestions

Broaden trigger terms with natural user phrasings (e.g., 'Use when: spawning multiple agents, running a swarm of agents, parallelizing work across agents, coordinating agents to solve a task').

Consider adding a layperson synonym for 'lifecycle management' (e.g., 'starting, stopping, and monitoring agents') so non-expert phrasings also trigger the skill.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('Agent spawning, lifecycle management, and coordination patterns') plus a quantified capability ('Manages 60+ agent types with specialized capabilities'), matching the 'lists multiple specific concrete actions' anchor rather than the partial-coverage anchor at 2.	3 / 3
Completeness	Explicitly answers both what ('Agent spawning, lifecycle management, and coordination patterns') and when ('Use when: spawning agents, coordinating multi-agent tasks, managing agent pools') plus a 'Skip when' clause, matching the 'clearly answers both what AND when' anchor rather than the implied-when anchor at 2.	3 / 3
Trigger Term Quality	Triggers like 'spawning agents', 'coordinating multi-agent tasks', and 'managing agent pools' are user-sayable but lean technical ('agent pools', 'lifecycle management') and lack the natural variation of the top anchor, so it fits 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	It carves a clear multi-agent coordination niche and the 'Skip when: single-agent work, no coordination needed' clause actively reduces overlap, fitting the 'clear niche with distinct triggers; unlikely to conflict' anchor rather than the could-overlap anchor at 2.	3 / 3
	Total	11 / 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.