team

N coordinated agents on shared task list using Claude Code implicit agent teams

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Critical

Do not install without reviewing

Quality

Content

77%

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

The content is highly actionable and workflow-clear with concrete executable snippets and a well-sequenced staged pipeline, but it is verbose/repetitive and monolithic rather than progressively split across reference files. De-duplicating the TeamDelete notes and moving large optional sections into referenced files would improve both conciseness and progressive disclosure.

Suggestions

Consolidate the repeated 'no TeamCreate/TeamDelete in Claude Code 2.1.178+' notes into one stated-once section to remove duplication and tighten conciseness.

Split large optional sections (Per-Role Provider & Model Routing, Git Worktree Integration, CLI Workers, Runtime V2) into referenced files under references/ with one-level-deep links, and create the referenced docs/REFERENCE.md and scripts/cleanup-orphans.mjs so progressive disclosure references resolve.

Add a concise quick-start section near the top so the core spawn/monitor/shutdown flow is discoverable before the detailed pipeline and routing tables.

Dimension	Reasoning	Score
Conciseness	The body is densely actionable but noticeably repetitive — the 'no TeamCreate/TeamDelete, Claude Code 2.1.178+' note recurs across many sections and large inline tables/comparison blocks could be trimmed, fitting the 'mostly efficient but could be tightened' level 2 anchor rather than the lean level 3.	2 / 3
Actionability	It provides fully executable JSON snippets (state_write, task-list entries, Agent/Task spawns, shutdown messages), concrete file paths, runnable commands, and a complete worker preamble — copy-paste ready guidance matching the level 3 anchor.	3 / 3
Workflow Clarity	The staged pipeline (plan->prd->exec->verify->fix) has explicit entry/exit criteria, a bounded verify/fix loop with stop conditions, a blocking shutdown protocol with ordered steps, and watchdog/error-recovery policies, matching the level 3 'clear sequence with explicit validation and feedback loops' anchor.	3 / 3
Progressive Disclosure	It is a monolithic ~1045-line SKILL.md with no actual bundle directories on disk, while body references to docs/REFERENCE.md, scripts/cleanup-orphans.mjs, and source .ts files are external/non-local; substantial sections (CLI workers, role routing, worktree integration) that should be split out are inline, fitting the level 2 'content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

35%

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 conveys the skill's purpose and a distinct niche but relies on internal jargon and omits any explicit 'Use when' trigger guidance, limiting trigger quality and completeness. Adding natural-language triggers and a use-when clause would raise it materially.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases users would actually say (e.g., 'Use when you want to parallelize a task across multiple agents, split work among teammates, or run a staged plan/verify/fix pipeline').

Replace jargon ('implicit agent teams') with natural terms ('parallel agents', 'multi-agent teamwork', 'split a task across agents').

List concrete actions (decompose a task, spawn coordinated agents, run a verify/fix loop) to lift specificity from level 2 to 3.

Dimension	Reasoning	Score
Specificity	Names the domain and some concrete mechanics ('N coordinated agents', 'shared task list', 'implicit agent teams') but does not list multiple specific actions, matching the 'names domain and some actions' anchor rather than the comprehensive level 3.	2 / 3
Completeness	It states what the skill does but provides no 'Use when...' trigger clause, so per the rubric a missing explicit trigger caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	The phrasing leans on internal jargon ('implicit agent teams', 'shared task list') rather than natural user utterances; missing common variations a user would actually say, fitting the 'technical jargon' level 1 anchor.	1 / 3
Distinctiveness Conflict Risk	'Claude Code implicit agent teams' carves a recognizable niche, but the jargon-heavy phrasing leaves some overlap with generic multi-agent skills, matching the 'somewhat specific but could overlap' level 2 anchor.	2 / 3
	Total	7 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1045 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Yeachan-Heo/oh-my-claudecode
Commit: 6c59219

Reviewed: about 4 hours 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.