omc-teams

CLI-team runtime for claude, codex, gemini, antigravity, grok, or cursor workers in tmux panes when you need process-based parallel execution

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%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 highly actionable with a clear, validated multi-phase workflow and concrete commands throughout. Its only weaknesses are repeated agent-list enumerations that add tokens and a long single-file layout where some reference material could be split out.

Suggestions

Replace the repeated inline enumeration of all six agent types (claude/codex/gemini/antigravity/grok/cursor) in Phase 1, Phase 2.5, Phase 3, and the tables with a single defined list referenced once, to cut redundant tokens (conciseness).

Move the detailed Error Reference table and the multi-repo Phase 2.5 workspace-root guidance into separate reference files (e.g. ERRORS.md, MULTI_REPO.md) linked from the body, so SKILL.md stays a lean overview (progressive_disclosure).

Dimension	Reasoning	Score
Conciseness	Mostly lean and command-focused with no over-explanation of concepts Claude already knows, but the full six-agent list is repeated ~8 times across sections and some Phase 2.5 guidance is wordy; anchor 5's "every token earns its place" is not quite reached.	4 / 5
Actionability	Fully executable with copy-paste-ready bash commands and real flags (--cwd, --json, --force), concrete launch/status/shutdown/api examples, a launch-verification step, and an error table with specific fixes covering common cases.	5 / 5
Workflow Clarity	Clear 6-phase sequence with explicit validation checkpoints (Phase 0 tmux presence check that stops on failure, Phase 3 launch verification via tmux capture-pane, stale-state shutdown recovery) and feedback loops for the batch N-worker operation.	5 / 5
Progressive Disclosure	No bundle files exist and all content is inline in a single well-organized SKILL.md with clear section headers and no nested references; the ~200-line length means some inline content (Error Reference table, detailed Phase 2.5) could be split out, keeping it below the well-signaled one-level-deep reference structure of anchor 5.	4 / 5
	Total	18 / 20 Passed

Description

75%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 specific, third-person, and explicitly answers both what the skill does and when to use it, with a clear distinct niche. It sits just below top marks because the trigger phrasing and the when-clause could enumerate a few more natural scenarios.

Dimension	Reasoning	Score
Specificity	Names the domain plus several concrete actions ("CLI-team runtime", "workers in tmux panes", "process-based parallel execution") and enumerates all six worker types; not quite the comprehensive multi-distinct-action list of anchor 5 but clearly above the 1-2 actions of anchor 3.	4 / 5
Completeness	Clearly answers "what" (CLI-team runtime spawning workers in tmux panes) and has an explicit "when" clause ("when you need process-based parallel execution"); the when could be more specific with concrete scenarios to reach anchor 5.	4 / 5
Trigger Term Quality	Includes natural target-audience terms ("parallel execution", "tmux panes", and the named CLIs claude/codex/gemini/antigravity/grok/cursor) but misses common natural synonyms a user might say like "run multiple agents" or "parallel agents".	4 / 5
Distinctiveness Conflict Risk	The tmux-pane + process-based-parallel-execution + named-CLI niche is clearly distinct with minimal conflict risk; only minor overlap with the closely related /team skill, which the body explicitly disambiguates.	4 / 5
	Total	16 / 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: Yeachan-Heo/oh-my-claudecode
Path: skills/omc-teams/SKILL.md
Commit: 5aa678c

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.