agent-orchestrator

Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks

Quality

58%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./public/skills/aatmaan1/agent-orchestrator/SKILL.md

Quality

Content

50%

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

This skill provides a reasonable high-level framework for multi-agent orchestration with a clear six-phase workflow and useful structural patterns. However, it suffers from referencing scripts and files that don't exist in the bundle, pseudocode rather than executable implementations, and insufficient error handling/validation feedback loops for what is inherently a complex, failure-prone orchestration process. The content is moderately verbose with some guidance Claude wouldn't need.

Suggestions

Provide the referenced scripts (create_agent.py, dissolve_agents.py) and reference files (sub-agent-templates.md, communication-protocol.md) in the bundle, or inline the critical parts needed for execution.

Add explicit error recovery feedback loops: what happens when an agent's status.json shows 'failed', how to retry, and concrete validation checks for agent outputs before consolidation.

Replace pseudocode functions (read_json, validate_outputs, glob patterns) with actual executable Python code or real tool invocations that Claude can directly use.

Trim the decomposition principles and best practices sections — these are general project management advice Claude already knows — and use that space for concrete implementation details.

Dimension	Reasoning	Score
Conciseness	The skill is moderately efficient but includes some unnecessary explanation. The decomposition principles and best practices sections contain guidance Claude already knows (e.g., 'minimize inter-agent dependencies', 'log everything'). The example section adds useful context but the overall content could be tightened by ~30%.	2 / 3
Actionability	Provides a mix of concrete and pseudocode guidance. The Task tool invocation is specific and useful, but scripts like `create_agent.py` and `dissolve_agents.py` are referenced without being provided. The Python snippets are illustrative pseudocode (e.g., `read_json`, `validate_outputs`) rather than executable code. Key implementation details are missing.	2 / 3
Workflow Clarity	The six-phase workflow is clearly sequenced and logically ordered with a good dependency example. However, validation checkpoints are weak — Phase 5 mentions 'validate deliverables' but provides no concrete validation logic or error recovery feedback loop. There's no explicit guidance on what to do when an agent fails or produces invalid output, which is critical for an orchestration workflow.	2 / 3
Progressive Disclosure	References to `references/sub-agent-templates.md` and `references/communication-protocol.md` are well-signaled and one level deep, which is good structure. However, no bundle files are provided, meaning these references point to non-existent files. The main SKILL.md also includes substantial inline content (the full example, all templates listed) that could be better split.	2 / 3
	Total	8 / 12 Passed

Description

67%

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 excels at specificity and distinctiveness, clearly articulating a unique multi-agent orchestration capability with concrete actions. However, it falls short on completeness by lacking an explicit 'Use when...' clause, and the trigger terms lean heavily toward technical jargon rather than natural user language, which could reduce discoverability when users describe their needs in plain terms.

Suggestions

Add an explicit 'Use when...' clause describing user scenarios, e.g., 'Use when the user has a complex task that benefits from being broken into parallel or sequential subtasks, or when they ask to divide work across multiple agents.'

Include more natural-language trigger terms that users would actually say, such as 'break this into smaller tasks', 'run these in parallel', 'divide and conquer', 'handle multiple things at once', alongside the technical terms.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion.	3 / 3
Completeness	The 'what' is well-covered with specific actions, but the 'when' is presented only as a list of trigger keywords rather than an explicit 'Use when...' clause describing the situations or user needs that should activate this skill. The mandatory triggers list is not a proper 'when' guidance.	2 / 3
Trigger Term Quality	The 'MANDATORY TRIGGERS' section lists many terms, but they are mostly technical jargon ('meta-agent', 'agent factory', 'spawn agents') rather than natural phrases a user would say. A user is more likely to say 'break this into smaller tasks' or 'run multiple things at once' than 'spawn agents' or 'agent coordination'.	2 / 3
Distinctiveness Conflict Risk	This skill occupies a very clear niche — meta-agent orchestration and sub-agent spawning — that is highly distinct and unlikely to conflict with other skills. The specific terminology around agent coordination and task decomposition creates a unique identity.	3 / 3
	Total	10 / 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: Demerzels-lab/elsamultiskillagent
Commit: f45fcb5

Reviewed: about 1 month 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.