clawteam

Multi-agent swarm orchestration. USE THIS (not delegate_task) when the user says team/swarm/multi-agent/clawteam/parallel-agents/agent-team, or asks for multi-perspective analysis (stocks, research, code review, strategy). Spawns N Hermes workers in tmux windows with git worktree isolation, file-based inboxes, and a kanban board. Four built-in templates: hedge-fund (7 analyst agents), research-paper, code-review, strategy-room.

Quality

88%

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

77%Weight 40%Scale 1-3

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

Highly actionable with a clearly sequenced, checkpointed workflow, but the body is verbose and monolithic — redundant inbox-peek warnings and an upstream patch inflate the token budget, and there is no progressive disclosure via separate reference files.

Suggestions

Consolidate the three separate inbox-peek-is-unreliable warnings (Known Failure Modes #2, the 'CRITICAL: Inbox Peek Is Unreliable' section, and the Anti-Patterns bullet) into one authoritative section to cut redundancy.

Move the 'Known upstream issues' Hermes source patch and the full command-reference tables into a reference file (e.g. references/commands.md) and link to it from the body, improving both conciseness and progressive disclosure.

Trim the per-flag explanatory notes in 'How The Hermes Adapter Builds Commands' to the essentials Claude needs to invoke the tool correctly.

Dimension	Reasoning	Score
Conciseness	Mostly actionable but padded: the inbox-peek-is-unreliable warning is repeated across three sections, and the 'Known upstream issues' section embeds a Hermes source-code patch that is beyond what Claude needs to use the skill.	2 / 3
Actionability	Provides copy-paste-ready bash blocks for launch, spawn, board polling, and tmux capture-pane, plus concrete command-reference tables — fully executable guidance.	3 / 3
Workflow Clarity	The polling pattern is clearly sequenced (sleep 60, tick loop, board check, inbox read, cleanup) with explicit checkpoints ('NEVER check inboxes within the first 60 seconds', 'Clean up ONLY after reading reports') and an error-recovery branch.	3 / 3
Progressive Disclosure	No bundle files exist, yet the body is a monolithic 200+ line file with the command reference tables and upstream-issues patch inline — content that would benefit from being split into referenced files.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 strong, concrete description with explicit trigger guidance, natural keyword coverage, and clear differentiation from delegate_task. It answers both what and when without vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Spawns N Hermes workers in tmux windows with git worktree isolation, file-based inboxes, and a kanban board' and enumerates four specific templates (hedge-fund, research-paper, code-review, strategy-room).	3 / 3
Completeness	Explicitly answers both what ('Multi-agent swarm orchestration...Spawns N Hermes workers...') and when ('USE THIS...when the user says...') with explicit trigger guidance.	3 / 3
Trigger Term Quality	Covers natural terms users would say — 'team/swarm/multi-agent/clawteam/parallel-agents/agent-team' plus 'multi-perspective analysis (stocks, research, code review, strategy)'.	3 / 3
Distinctiveness Conflict Risk	Explicitly distinguishes from delegate_task ('USE THIS (not delegate_task)') and names a clear multi-agent niche, making wrong-skill triggering unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: win4r/ClawTeam-OpenClaw
Path: skills/hermes/SKILL.md
Commit: 8dac3fc

Reviewed: 29 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.