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

92%

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%

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 well-structured, actionable orchestration guide with clear two-track workflows, validation checkpoints, and clean progressive disclosure into verified reference files. Its only weakness is moderate token redundancy from repeatedly enumerating the same agent list.

Suggestions

Define the supported agent list once (e.g., in a short variable-like preamble or table) and refer to 'the supported terminal agents' in subsequent rules instead of repeating the full 'Codex, Claude Code, Cursor CLI, ...' enumeration multiple times.

Tighten the longest Rules bullets by splitting the condition from the action so each rule reads as a single imperative, reducing per-line token cost.

Consider moving the verbatim multi-line host-install chat block into the relevant reference or a small snippet file so the main body stays leaner.

Dimension	Reasoning	Score
Conciseness	The body is mostly dense and assumes Claude's competence, but the full agent enumeration ('Codex, Claude Code, Cursor CLI, Gemini CLI, Grok Build, Hermes Agent, and OpenCode') is repeated across several rules and some bullets could be tightened, matching 'mostly efficient but could be tightened'.	2 / 3
Actionability	It provides copy-paste install commands (curl install.sh, irm install.ps1, a0), literal UI steps (F4/F3), a verbatim chat message template, and explicit verification guidance, all directly executable.	3 / 3
Workflow Clarity	Numbered flows for both host and container paths include explicit checkpoints (install/probe/smoke, then 'rerun the smoke prompt. Only then run the real task') and a verify-before-reporting feedback loop.	3 / 3
Progressive Disclosure	Generic rules stay in SKILL.md while agent-specific commands live in clearly signaled one-level-deep reference files (a0.md, codex.md, claude.md, etc., all verified present), with a clean reference index.	3 / 3
	Total	11 / 12 Passed

Description

100%

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

A concise, well-targeted description that explicitly states both what the skill does and when to use it, with concrete agent names serving as natural triggers. It is distinguishable and free of fluff.

Dimension	Reasoning	Score
Specificity	It names a concrete action ("delegating coding or repository work") and enumerates multiple specific targets (Claude Code/Codex/Cursor/Gemini CLI, container-installed pal agents), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	The 'Use when...' clause gives an explicit trigger and the body states what it does (delegating coding/repo work to external terminal agents), answering both what and when.	3 / 3
Trigger Term Quality	Natural user-facing terms like 'delegating coding or repository work', 'Claude Code', 'Codex', 'Cursor', and 'Gemini CLI' give good coverage of phrasings a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The niche (delegating to external terminal coding CLIs) is distinct and its triggers (specific CLI names) are unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: 391fab9

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.