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 findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-orchestrator-task/SKILL.md

Quality

Content

7%Scale 1-3

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

This skill reads as a high-level architectural description or product overview rather than an actionable skill for Claude. It describes what a task orchestrator does conceptually but never provides concrete instructions, executable code, specific tool usage patterns, or validation steps. Nearly all content explains concepts Claude already understands (parallelization, dependency management, task decomposition) without adding novel, actionable guidance.

Suggestions

Replace abstract descriptions with concrete, executable workflows—e.g., show exactly how to use TodoWrite for task tracking, how to invoke sub-agents, and what memory_store/memory_search calls to make at each step.

Remove sections that describe concepts Claude already knows (what task decomposition is, what parallel execution means) and replace with specific decision criteria and examples (e.g., 'If tasks share no files, execute in parallel by spawning agents X and Y').

Add validation checkpoints to workflows—e.g., after task decomposition, verify all dependencies are resolvable; after agent execution, check exit status before proceeding.

Provide at least one complete end-to-end example showing input objective → decomposed tasks → agent invocations → result synthesis with actual commands and tool calls.

Dimension	Reasoning	Score
Conciseness	The content is verbose and largely describes abstract concepts Claude already understands (task decomposition, dependency management, parallelization). Most of the content reads like a product description rather than actionable instructions. Sections like 'Core Functionality' enumerate capabilities without adding executable value.	1 / 3
Actionability	There is no executable code, no concrete commands, and no specific implementation guidance. The 'Task Patterns' are abstract outlines (e.g., 'Requirements Analysis (Sequential)') without any actual steps, tool invocations, or examples of what to run. The 'Usage Examples' section just lists natural language prompts, not actionable procedures.	1 / 3
Workflow Clarity	While task patterns list phases, they lack concrete steps, validation checkpoints, error handling, or feedback loops. There is no clear sequence of actual operations Claude should perform—just high-level labels like 'Reproduce + Analyze (Sequential)' with no detail on what those steps entail or how to verify success.	1 / 3
Progressive Disclosure	The content is organized into logical sections with headers, which provides some structure. However, it's a monolithic document with no references to external files, and several sections (Integration Points, Advanced Features) could be split out. No bundle files exist to reference, but the inline content is overly long for what it conveys.	2 / 3
	Total	5 / 12 Passed

Description

0%Scale 1-3

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

This is an extremely weak description that fails on every dimension. It provides no information about what the skill does, when it should be used, or how it differs from other skills. It reads as a placeholder or auto-generated stub rather than a functional skill description.

Suggestions

Replace the entire description with concrete actions the skill performs, e.g., 'Breaks down complex tasks into subtasks and coordinates their execution across multiple agents.'

Add an explicit 'Use when...' clause with natural trigger terms that describe scenarios where this skill should be selected, e.g., 'Use when the user needs to coordinate multi-step workflows, delegate subtasks, or manage parallel task execution.'

Remove the invocation instruction ('invoke with $agent-orchestrator-task') from the description, as it is not useful for skill selection and adds noise.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Agent skill for orchestrator-task' is entirely abstract and gives no indication of what the skill actually does.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states a label and an invocation command, with no functional or contextual information.	1 / 3
Trigger Term Quality	There are no natural keywords a user would say. 'orchestrator-task' is internal jargon, and 'invoke with $agent-orchestrator-task' is a technical invocation instruction, not a trigger term.	1 / 3
Distinctiveness Conflict Risk	The description is so generic and vague that it provides no distinguishing characteristics. 'Orchestrator-task' could overlap with virtually any task-management or workflow skill.	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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Path: .agents/skills/agent-orchestrator-task/SKILL.md
Commit: 913f9ea

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.