orchestrator

Use when delegating coding or repository work to external terminal coding agents such as the user's host Claude Code/Codex/Cursor/Gemini CLI or container-installed pal agents.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

85%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 well-structured with clear sequenced workflows, explicit validation/auth checkpoints, and clean progressive disclosure to real reference files. It is concise and actionable, with only minor repetition of agent lists.

Dimension	Reasoning	Score
Conciseness	Largely lean and assumes Claude's competence; minor verbosity from repeating the full agent list across multiple rules and sections.	4 / 5
Actionability	Provides concrete install commands, F4/F3 key guidance, exact user-relay text, and probe/smoke-task steps; agent-specific command details are deferred to reference files, a minor gap.	4 / 5
Workflow Clarity	Host and Container flows are explicitly sequenced with validation checkpoints (probe -> smoke -> auth -> confirm -> retry -> real task) and clear error-recovery guidance for TUI/menu states.	5 / 5
Progressive Disclosure	SKILL.md is a well-organized overview with a one-level-deep reference index pointing to real files (a0.md, codex.md, claude.md, etc.), keeping agent-specific detail out of the main body.	5 / 5
	Total	18 / 20 Passed

Description

83%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 clear and explicit, covering both what the skill does and when to use it with concrete agent names. It is mostly distinct and uses natural trigger phrasing, with only minor gaps in keyword and synonym coverage.

Dimension	Reasoning	Score
Specificity	Names concrete agents ("Claude Code/Codex/Cursor/Gemini CLI") and the concrete action ("delegating coding or repository work"), with only minor gaps in enumerating every supported agent.	4 / 5
Completeness	Explicitly answers both what (delegate coding/repo work to external terminal agents) and when ("Use when delegating...") with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Includes natural phrases users say ("delegating coding or repository work", agent names, "terminal coding agents"); a few common synonyms or product-name variants are missing.	4 / 5
Distinctiveness Conflict Risk	The external-terminal-agent delegation niche is distinct with specific agent triggers; minor overlap risk with general coding skills.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: agent0ai/agent-zero
Path: plugins/_orchestrator/skills/orchestrator/SKILL.md
Commit: b22a144

Reviewed: 4 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.