agent-orchestrator-task

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

1.32x

Quality

10%

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

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 verbose conceptual design doc that describes an orchestrator agent's role with abstract capability lists and generic best practices rather than executable instruction. It has clearly sequenced task patterns but lacks validation checkpoints and any external reference structure.

Suggestions

Cut generic conceptual padding (definitions of task decomposition, common pitfalls, basic best practices) that Claude already knows; keep only guidance specific to this orchestrator.

Add concrete, executable guidance — specific commands, TodoWrite usage patterns, or code — instead of abstract phase names in the task patterns.

Add validation/verification checkpoints to the task patterns (e.g., 'Verify subtask outputs before marking dependencies complete') and consider splitting detailed patterns into referenced files.

Dimension	Reasoning	Score
Conciseness	Quotes: 'Analyzes complex objectives', 'Identifies logical subtasks and components', 'Maximize parallelization opportunities'. The body is padded with generic orchestration concepts and best-practice advice Claude already knows, describing an agent role rather than adding new information, matching the 'verbose; explains concepts Claude knows' anchor.	1 / 3
Actionability	Quotes: 'Real-time task status tracking', 'Critical path optimization'. Guidance is abstract capability description with no executable code or commands; the task patterns are phase-name lists ('Requirements Analysis (Sequential)') rather than concrete actions, matching the 'describes rather than instructs' anchor.	1 / 3
Workflow Clarity	Quotes: '1. Requirements Analysis (Sequential) 2. Design + API Spec (Parallel)...'. Sequences are clearly listed, but no validation/verification checkpoints appear for batch orchestration operations, which caps the score at 2 per the destructive/batch-operations guideline rather than reaching the level-3 feedback-loop anchor.	2 / 3
Progressive Disclosure	Quotes: '## Core Functionality', '## Task Patterns', '## Advanced Features'. The single file is well-sectioned but monolithic with no external references, and content such as task patterns and integration points is inline rather than split out, matching the 'some structure but content that should be separate is inline' anchor.	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 boilerplate metadata that names no concrete capabilities, includes only technical invocation syntax rather than natural trigger terms, and omits any 'Use when...' guidance. It is generic and indistinguishable from other agent skills.

Suggestions

Replace the description with concrete actions the skill performs (e.g., 'Decomposes objectives into subtasks, plans parallel/sequential execution across agents, and synthesizes their results').

Add an explicit 'Use when...' clause with natural trigger terms users would actually say (e.g., 'Use when coordinating multi-step work across multiple agents or breaking down a complex feature').

Drop the '$agent-orchestrator-task' invocation token from the description; keep triggers user-natural rather than command syntax.

Dimension	Reasoning	Score
Specificity	Quotes: 'Agent skill for orchestrator-task - invoke with $agent-orchestrator-task'. No concrete actions are named; it only labels the skill and gives invocation syntax, matching the 'vague or no actions' anchor rather than the level-2/3 anchors that name domain actions.	1 / 3
Completeness	Quotes: 'Agent skill for orchestrator-task'. The 'what' is circular metadata and the 'when' (Use when...) is entirely absent; both are weak/missing, matching the 'missing what OR when, or both very weak' anchor and below the level-2 cap for a missing Use-when clause.	1 / 3
Trigger Term Quality	Quotes: 'orchestrator-task', 'invoke with $agent-orchestrator-task'. These are technical invocation tokens, not natural terms a user would say, matching the 'technical jargon or overly generic' anchor; it lacks the common variations a level-3 example would cover.	1 / 3
Distinctiveness Conflict Risk	Quotes: 'Agent skill for orchestrator-task - invoke with $agent-orchestrator-task'. This is generic boilerplate with no distinct triggers and would conflict with many similar 'Agent skill for X' skills, matching the 'very generic; would conflict' anchor.	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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Path: .agents/skills/agent-orchestrator-task/SKILL.md
Commit: 26c35b5

Reviewed: about 7 hours 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.