agent-orchestrator-task

Agent skill for orchestrator-task - invoke with $agent-orchestrator-task

1.32x

Quality

—

Does it follow best practices?

Impact

82%

1.32x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

20%

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 conceptual overview of an orchestrator agent's capabilities rather than actionable operational instructions: it is padded with concepts Claude already knows and a duplicate YAML block, provides no executable guidance, and sequences tasks only abstractly without validation checkpoints. It is well-sectioned but monolithic with no progressive disclosure.

Suggestions

Remove the duplicate YAML frontmatter block and the conceptual bullets Claude already knows; keep only operational guidance Claude would not infer.

Replace abstract behavior descriptions with concrete, executable steps (e.g. specific TodoWrite usage, memory_store commands, or a concrete decomposition procedure).

Add validation checkpoints to the task patterns (e.g. verify subtask outputs before aggregation) so the workflow has feedback loops for batch operations.

Dimension	Reasoning	Score
Conciseness	The body explains concepts Claude already knows ('Analyzes complex objectives', 'Creates dependency graphs', parallel vs sequential execution) and even carries a duplicate YAML frontmatter block (lines 6-28) that is pure noise, so it is padded with unnecessary context.	1 / 3
Actionability	It describes behavior in the abstract ('Real-time task status tracking', 'Aggregates outputs from multiple agents') and offers natural-language usage prompts and abstract pattern labels, but no executable code, commands, or concrete operational guidance for Claude to follow.	1 / 3
Workflow Clarity	Sequenced steps are present in the task patterns (e.g. '1. Requirements Analysis (Sequential) 2. Design + API Spec (Parallel)'), but they are abstract labels with no executable actions and no validation/verification checkpoints for batch coordination work, which caps clarity below 3.	2 / 3
Progressive Disclosure	The document is a single well-sectioned file with no bundle files present and no deeply nested references, but at 100+ lines the conceptual content is inline monolithically with no external references signaled, fitting the 'some structure, content that should be separate is inline' anchor rather than the well-split level.	2 / 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 generic boilerplate that identifies the skill by name and invocation token but does not state concrete capabilities, natural trigger terms, or when to use it. It reads as an auto-generated stub rather than a user-facing trigger.

Suggestions

Rewrite the description to list concrete actions, e.g. 'Breaks down complex objectives into subtasks, plans parallel/sequential execution, and synthesizes agent results.'

Add an explicit trigger clause such as 'Use when coordinating multi-step work across agents or when the user asks to decompose and orchestrate a complex task.'

Replace the internal invocation token with natural terms users would actually say ('task decomposition', 'agent coordination', 'execution planning').

Dimension	Reasoning	Score
Specificity	The description only states 'Agent skill for orchestrator-task' and 'invoke with $agent-orchestrator-task'; it names no concrete actions (e.g. decompose tasks, plan execution), matching the vague/abstract anchor rather than the domain+actions level.	1 / 3
Completeness	It gives only a weak 'what' ('Agent skill for orchestrator-task') and the invocation is not a 'when'; there is no 'Use when...' trigger guidance, so it fails both the what and when requirements rather than just capping at 2.	1 / 3
Trigger Term Quality	The only terms are the internal skill name 'orchestrator-task' and the invocation token '$agent-orchestrator-task', which are technical identifiers a user would not naturally say, not natural keywords like 'break down tasks' or 'coordinate agents'.	1 / 3
Distinctiveness Conflict Risk	It is tied to the specific skill name 'orchestrator-task', making it somewhat distinguishable, but the boilerplate 'Agent skill for X - invoke with $X' pattern is generic and could overlap with other orchestration skills since it carries no distinct trigger content.	2 / 3
	Total	5 / 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.