team

N coordinated agents on shared task list using tmux-based orchestration

Quality

46%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/oh-my-codex/skills/team/SKILL.md

Quality

Content

51%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 skill body is a thorough, executable operator manual with a clear lifecycle and validation gates, but it is a monolithic ~535-line wall of text with no progressive disclosure into reference files and significant verbosity explaining OMX internals. Strong on actionability and workflow, weak on conciseness and file structure.

Suggestions

Split the long reference material (Environment Knobs, Failure Modes and Diagnosis, Team + Worker Protocol Notes) into separate reference files (e.g. references/env-vars.md, references/failure-modes.md) and link them from SKILL.md to improve progressive disclosure.

Trim the ATEM / Big Five / Ultragoal / model-resolution sections down to the operator-actionable essentials and remove re-explanation of OMX internals Claude already knows.

Move the '## What This Skill Must Do' empty-heading section's content so the heading is not orphaned, and consolidate the duplicate launch/deprecation guidance currently spread across multiple sections.

Dimension	Reasoning	Score
Conciseness	The body is a ~535-line operator manual with large padded sections on ATEM coordination, Big Five teamwork, Ultragoal bridges, and model/thinking-resolution rules that re-explain OMX internals Claude largely already knows; noticeably verbose per the score-2 anchor.	2 / 5
Actionability	It provides concrete executable commands (omx team N:agent-type, omx team api ... --json, env-var selectors, status/resume/shutdown) and specific state paths, with only minor gaps around a few prose-only protocol sections.	4 / 5
Workflow Clarity	There is a clear Required Lifecycle with explicit completion gates (pending=0, in_progress=0, failed=0) before shutdown, plus monitoring loops and a feedback loop (status -> intervene -> re-check); minor gaps keep it just below the fully-checklisted score-5 anchor.	4 / 5
Progressive Disclosure	There are no reference files in references/scripts/assets and the entire manual is inlined into SKILL.md; content that clearly belongs in separate files (env knobs, failure-mode diagnosis, protocol notes) is all in one long document, matching the inlined-content anchor.	2 / 5
	Total	12 / 20 Passed

Description

42%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 third-person and names the domain and mechanism, but it is terse and lacks trigger phrases or a 'Use when' clause, so it does not tell a user when to reach for the skill. It is reasonable but below the strong examples.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases (e.g. parallel workers, durable tmux task coordination, shared task list, multi-worker execution).

List a few concrete actions (launch N workers, monitor via omx team status, coordinate via mailbox, graceful shutdown) to raise specificity.

Include natural synonyms and the CLI surface (e.g. '$team', 'omx team', tmux worker panes) so the description matches terms users actually say.

Dimension	Reasoning	Score
Specificity	Names the domain (coordinated agents, shared task list) and one concrete mechanism (tmux-based orchestration), but does not enumerate multiple concrete actions like launch/monitor/shutdown; fits the score-3 anchor of domain plus 1-2 concrete actions.	3 / 5
Completeness	There is a clear 'what' (N coordinated agents on a shared task list via tmux), but no 'Use when...' or equivalent explicit trigger guidance, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	The only natural user-facing term is 'agents'; 'coordinated agents', 'shared task list', and 'tmux-based orchestration' are operator jargon a user would rarely say when they need this skill, matching the one-or-two-generic-keywords anchor.	2 / 5
Distinctiveness Conflict Risk	'tmux-based orchestration' gives a recognizable niche, but 'N coordinated agents on shared task list' is fairly broad and could overlap with native subagent or ralph skills, fitting the somewhat-specific-but-could-overlap anchor.	3 / 5
	Total	11 / 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
skill_md_line_count	SKILL.md is long (541 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: Yeachan-Heo/oh-my-codex
Path: plugins/oh-my-codex/skills/team/SKILL.md
Commit: e94437f

Reviewed: 8 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.