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

73%

Does it follow best practices?

Impact

89%

1.34x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-coordination/SKILL.md

Quality

Content

62%Weight 40%Scale 1-5

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

The body is concise and its commands are copy-paste executable, but it reads as a command catalog rather than a coordination playbook: there is no end-to-end workflow, no sequencing of the routing codes into an ordered process, and no validation or verification steps for batch agent operations. Adding a worked example workflow with explicit checkpoints would address the weakest dimension.

Suggestions

Add a step-by-step coordination workflow (e.g. spawn routed agents -> assign task -> monitor via 'agent metrics' -> stop when done) so the routing codes translate into an ordered sequence rather than a static mapping.

Include validation/verification checkpoints for batch and pool operations — e.g. check 'agent status' or metrics output before and after scaling a pool, and define what to do when an agent fails or stalls.

Provide one end-to-end worked example (a bug fix using routing code 1) showing the actual commands run in order, to complement the currently isolated command snippets.

Dimension	Reasoning	Score
Conciseness	The body is lean and list-based, and the agent-type catalog is claude-flow-specific data Claude would not already know, so it earns its tokens. Not 5 because the 'Purpose' section merely restates the description and a few bare lists could be tightened. Not 3 — there is no over-explanation of concepts Claude already knows.	4 / 5
Actionability	Commands are fully executable and copy-paste ready (e.g. 'npx claude-flow agent spawn --type coder --name my-coder') covering spawn, list, status, metrics, stop, and pool operations. Not 5 because there is no end-to-end worked example or expected-output guidance connecting the commands to a real coordination task.	4 / 5
Workflow Clarity	No multi-step sequence exists anywhere: the routing table maps tasks to agent sets but never orders them (spawn -> route -> monitor -> collect), and pool/batch agent operations have no validation checkpoints. A rough implicit mapping exists via the routing codes, so above the 'steps missing entirely' anchor, but steps are poorly defined and validation is absent. Not 3 because even implicit checkpoints are missing for batch operations.	2 / 5
Progressive Disclosure	No bundle files exist and the single file has clear, well-organized sections; the agent-type catalog is compact enough to justify inlining. Not 5 because the file is over 50 lines and the agent-type catalog and routing table could plausibly live in a separate reference file to keep SKILL.md a tighter overview.	4 / 5
	Total	14 / 20 Passed

Description

83%Weight 40%Scale 1-5

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

A strong description that explicitly covers what the skill does, when to use it, and when not to use it, with natural trigger phrases and a distinct multi-agent niche. The main improvement opportunities are enumerating more concrete capabilities and adding common trigger synonyms like 'subagents' or 'orchestrate'.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Agent spawning, lifecycle management, and coordination patterns' plus 'Manages 60+ agent types' — with only minor coverage gaps. Not 5 because the actions are stated at domain level rather than as enumerated concrete capabilities (spawn, list, stop, pool management appear only as general phrasing).	4 / 5
Completeness	Explicitly answers both 'what' (spawning, lifecycle management, coordination, 60+ agent types) and 'when' with a concrete 'Use when:' clause, plus a 'Skip when' boundary clause. Clearly matches the top anchor; the when-clause is fully explicit with concrete trigger phrases, so not 4.	5 / 5
Trigger Term Quality	'Use when: spawning agents, coordinating multi-agent tasks, managing agent pools' provides good natural-term coverage a user would actually say. Not 5 because common synonyms such as 'subagents', 'delegate', 'orchestrate', or tool-specific keywords are missing.	4 / 5
Distinctiveness Conflict Risk	'Multi-agent tasks', 'agent pools', and '60+ agent types' carve a distinct niche with clear triggers, but there is minor overlap risk with generic task-delegation or orchestration skills. Not 5 because the phrase 'coordination patterns' is somewhat broad.	4 / 5
	Total	17 / 20 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/ruflo
Path: .agents/skills/agent-coordination/SKILL.md
Commit: b14c79e

Reviewed: 3 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.