agent-teams

Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/agent-teams/SKILL.md

Quality

Content

75%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.

A well-structured, actionable body that covers team sizing, task decomposition, locking, plan approval, and when-to-use guidance with concrete commands and examples, with only minor trimming and validation-detail gaps.

Suggestions

Add an explicit validation/feedback-loop step in the file-lock claiming and plan-approval workflows (e.g. how to verify a lock is released or re-validate after a redirected plan).

Tighten the Display Modes section by dropping generic tmux/iTerm2 instruction that Claude already knows, keeping only the Claude-specific shortcuts.

Show the actual command or API for claiming/releasing a file lock rather than describing the steps abstractly.

Dimension	Reasoning	Score
Conciseness	Mostly lean and well-organized with tables and code blocks earning their tokens; only minor over-explanation (e.g. generic tmux/iTerm2 split advice) that could be trimmed.	4 / 5
Actionability	Provides concrete, runnable commands (`export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`, `Shift+Tab`, `claude -w`, `/batch`) and concrete task-decomposition examples; the file-lock claiming steps stay somewhat abstract with no actual claim command.	4 / 5
Workflow Clarity	Clear sequenced processes for plan approval (receive → plan → review → approve/redirect → implement) and a full example session ending in integration tests; checkpoints are present though mid-task validation is only implicit.	4 / 5
Progressive Disclosure	Single cohesive SKILL.md with well-organized sections and a single external doc link, no nested references; at ~170 lines it stays appropriately in one file, with only minor organization gaps.	4 / 5
	Total	16 / 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.

A specific, well-scoped description with strong distinctiveness and concrete capability listing, but it lacks an explicit 'Use when ...' trigger clause so Claude knows precisely when to invoke it.

Suggestions

Add an explicit trigger clause, e.g. 'Use when coordinating multiple Claude Code sessions on the same repo in parallel, or when the user asks for agent teams / multi-session collaboration.'

Include a natural synonym a user might say (e.g. 'parallel sessions' or 'multiple Claude instances') to broaden trigger coverage.

Lead with the 'when' alongside the 'what' so the trigger condition is as prominent as the capability list.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'shared task lists, mailbox messaging, and file-lock claiming' plus 'team sizing, task decomposition' — giving comprehensive coverage of what the skill does rather than vague abstractions.	5 / 5
Completeness	The 'what' is clear ('Coordinate multiple Claude Code sessions as a team ...'), but there is no explicit 'Use when ...' trigger clause; the 'when to use teams vs sub-agents vs worktrees' phrase describes skill content rather than telling Claude when to invoke it, capping completeness at 3 per the missing-trigger-clause rule.	3 / 5
Trigger Term Quality	Good natural keyword coverage ('Claude Code sessions', 'team', 'lead + teammates', 'sub-agents', 'worktrees') that users would plausibly say, though a few synonyms (e.g. 'parallel sessions') are absent.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche — coordinating multiple full Claude Code sessions as a team — and explicitly contrasts itself against sub-agents and worktrees, minimizing the chance of triggering the wrong skill.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rohitg00/pro-workflow
Path: skills/agent-teams/SKILL.md
Commit: 7f7209d

Reviewed: 3 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.