team

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

Quality

61%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/team/SKILL.md

Quality

Content

70%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 a thorough, well-sequenced operational spec with strong workflow clarity, but it is verbose in places and structurally monolithic: large configuration/API sections are inlined rather than split into reference files, and some cited scripts/docs are not present in the bundle.

Suggestions

Split the 'Per-Role Provider & Model Routing' section and the Git Worktree API table into separate reference files and link to them one level deep, leaving the overview in SKILL.md.

Dedupe the 'TeamCreate/TeamDelete removed / no TeamDelete' note to a single authoritative statement near the top.

Either add the referenced scripts (cleanup-orphans.mjs, docs/REFERENCE.md) to the bundle or remove the dangling references so navigation paths are real.

Dimension	Reasoning	Score
Conciseness	Mostly efficient reference material (tables, JSON payloads, routing rules), but the 'TeamCreate/TeamDelete removed in 2.1.178+' note is repeated roughly ten times and shutdown/state cleanup is restated across four-plus sections, adding avoidable padding.	3 / 5
Actionability	Provides concrete copy-paste payloads (state_write JSON, Agent spawn JSON, TodoWrite entries) covering common cases, but several referenced utilities (getTeamStatus, createWorkerWorktree, buildLaunchArgs, cleanup-orphans.mjs) have no source location and no bundle files exist to ground them.	4 / 5
Workflow Clarity	The staged pipeline (plan->prd->exec->verify->fix loop) has explicit entry/exit criteria, a bounded fix loop with max attempts and stop conditions, a handoff convention, and a blocking shutdown protocol with feedback recovery.	5 / 5
Progressive Disclosure	Headers and tables are well organized, but this is a monolithic 1045-line file that inlines content better split out (role-routing config, worktree API table) and references files that do not exist (docs/REFERENCE.md, scripts/cleanup-orphans.mjs).	3 / 5
	Total	15 / 20 Passed

Description

53%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 states the domain and core action concisely in third person, but lacks an explicit 'Use when...' trigger clause and relies on somewhat technical terminology, leaving the when-to-use guidance only implicit.

Suggestions

Append an explicit trigger clause, e.g. 'Use when parallelizing a task across N agents, or when the user asks for multi-agent/parallel execution on a shared task list.'

Add natural-language synonyms ('parallel agents', 'spawn multiple agents') alongside 'implicit agent teams' to improve trigger match.

List 1-2 more concrete capabilities (e.g., 'decomposes tasks, assigns workers, verifies results') to lift specificity above 3.

Dimension	Reasoning	Score
Specificity	Names the domain ('Claude Code implicit agent teams') and 1-2 concrete actions ('N coordinated agents', 'shared task list'), but the action set is minimal and not comprehensive.	3 / 5
Completeness	Gives a clear 'what' (coordinate N agents on a shared task list) but has no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3.	3 / 5
Trigger Term Quality	Has relevant terms ('agents', 'agent teams', 'task list', 'coordinated') but 'implicit agent teams' is technical jargon and common natural phrasings like 'parallel agents' or 'spawn multiple agents' are missing.	3 / 5
Distinctiveness Conflict Risk	Targets a clear niche (multi-agent team coordination on shared task lists) that is mostly distinct from sibling skills, with only minor overlap risk against ralph/swarm.	4 / 5
	Total	13 / 20 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
Path: skills/team/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.