CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-hierarchical-coordinator

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

55

9.66x
Quality

33%

Does it follow best practices?

Impact

87%

9.66x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-hierarchical-coordinator/SKILL.md

The canonical home for this skill is agent-hierarchical-coordinator in ruvnet/claude-flow

SKILL.md
Quality
Evals
Security

Quality

Content

38%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 a verbose, monolithic coordinator spec built around unverifiable mcp__claude-flow__ tool calls rendered as non-executable pseudocode, with sequenced phases but no validation checkpoints for its batch/destructive operations. It inlines everything rather than splitting detail into referenced bundle files.

Suggestions

Tighten the body: cut the role-play framing, ASCII art, and generic best-practices prose; keep only the coordination protocol, memory key schema, and concrete commands Claude would not already know.

Make the memory-coordination examples executable: either show real tool-call syntax or clearly label them as pseudocode templates, and define the exact key/value schema once instead of repeating five near-identical blocks.

Add validation checkpoints to the workflow (e.g., verify a worker reported status before reassigning, confirm memory keys were stored before proceeding) and move worker-type catalogs and the MCP tool reference into separate referenced files under references/.

DimensionReasoningScore

Conciseness

The body is padded with role-play framing ('You are the Queen'), ASCII org charts, and generic best-practices prose about delegation and metrics that Claude already knows, fitting 'noticeably verbose; several unnecessary explanations or padded sections'.

2 / 5

Actionability

It provides command-shaped guidance, but the 'MANDATORY' memory blocks use pseudocode syntax ('mcp__claude-flow__memory_usage { action: "store", ... }') that is neither valid JavaScript nor a documented tool call, and the assign_task Python is pseudocode calling undefined helpers, matching 'some concrete guidance but incomplete; pseudocode instead of executable code'.

3 / 5

Workflow Clarity

The three phases give a sequence, but there are no validation checkpoints and the operations are batch/destructive (spawning/tearing down swarms, overwriting shared memory keys), so per the destructive/batch cap workflow_clarity cannot exceed 3; it sits at 'steps listed but validation gaps; checkpoints missing'.

3 / 5

Progressive Disclosure

No references/, scripts/, or assets/ bundle files exist and the entire content is inlined in one file; worker catalogs, MCP tool reference, and metrics that belong in separate files are all inlined with no navigation, matching 'minimal structure; content that clearly belongs in separate files is inlined'.

2 / 5

Total

10

/

20

Passed

Description

28%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.

The description is a generic invocation stub that names the domain but states no concrete capabilities and provides no use-when trigger guidance. It fails to tell a user or Claude when to invoke the skill or what it concretely does.

Suggestions

Replace the boilerplate with concrete actions, e.g., 'Decompose complex objectives into sub-tasks, spawn specialized worker agents, and coordinate a hierarchical swarm to deliver them.'

Add an explicit use-when clause with natural trigger phrases, e.g., 'Use when coordinating multi-agent work, delegating tasks across specialized workers, or running a hierarchical swarm.'

Drop the redundant invocation token from the description; keep the description focused on what/when so it is distinguishable from other coordination skills.

DimensionReasoningScore

Specificity

The description names the domain ('hierarchical-coordinator') but gives no concrete actions, only an invocation instruction ('invoke with $agent-hierarchical-coordinator'), matching the anchor 'Names the domain but actions are minimal or generic'.

2 / 5

Completeness

It offers a vague 'what' ('Agent skill for hierarchical-coordinator') and no 'when'/use-when clause; the guideline caps completeness at 3 for missing triggers, and this is below that with only a vague what and absent when.

2 / 5

Trigger Term Quality

It provides only the invocation token and domain name, missing natural phrases a user would actually say (e.g., 'coordinate a swarm', 'delegate tasks to agents'), fitting 'one or two generic keywords; missing the natural phrases users say'.

2 / 5

Distinctiveness Conflict Risk

The coordinator domain is somewhat niche, but the description is generic agent-skill boilerplate that does not differentiate via distinct triggers, so it could overlap with similar coordination skills.

3 / 5

Total

9

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/ruflo
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.