Dev & Engineering multi-agent-orchestrationswarm-coordinationtmuxhermes-agentopenclawkanban-boardgit-worktreecli-automation

ClawTeam Multi-Agent Swarm Skill (Hermes Edition)

Spin up a team of 5–7 parallel specialist agents from Hermes in one command, with kanban boards and inboxes handling coordination instead of single sub-agent delegation.

FollowSkills review · FSRS-2.0
Use with care
48/ 100 5-point scale 2.4 / 5
1 2 3 4 5 6
1Trust11 / 25 · 2.2/5

The skill transparently documents how the spawn adapter builds commands, MCP inheritance, known upstream defects and fixes; data flow (~/.clawteam state, tmux, git worktrees) is clear, with MIT license and upstream attribution to HKUDS/ClawTeam. Deducted because: workers run with --yolo/skip_permissions by default, bypassing interactive permission confirmation; cleanup uses --force and template launch requires --force to suppress warnings; the README install flow also switches OpenClaw exec approvals to allowlist. Parallel multi-agent execution amplifies external side effects with no rollback/recovery mechanism described. This sits at the 'main risks visible but confirmation/isolation incomplete' anchor.

2Reliability10 / 20 · 2.5/5

High self-consistency: flag distinctions (--team-name vs --team, positional hermes), timing expectations (sleep 60, polling), diagnostic commands (tmux capture, team status) are all given, and three known failure modes (risk-manager crash, empty inbox, non-persistent output) are honestly documented. Deducted because the core read path (inbox peek) itself 'often returns EMPTY' and actual output survives only in tmux scrollback lost on cleanup — a real reliability defect, not merely a documentation issue; static review cannot verify key-path reproduction, so the score is capped at 10.

3Adaptability8 / 15 · 2.7/5

Trigger conditions are precise (explicit trigger words, when NOT to use delegate_task, four template scenarios), environment dependencies (Python 3.10+, tmux, Hermes ≤0.8.0 --source limitation) are disclosed, and Chinese users are served (Chinese README exists, though SKILL.md is English-only). Deducted because: the skill targets Hermes users yet sits in an OpenClaw-focused fork, an awkward fit; multi-agent launches are costly (7 analysts, 2-5 minutes, heavy token use) with no cost boundary stated; evidence of fit beyond stock/research/review scenarios is limited.

4Convention9 / 15 · 3.0/5

Good layered information architecture: triggers → critical flags → recommended path → manual path → command reference → known failure modes → anti-patterns, with progressive disclosure; has version (0.3.0), MIT license, upstream attribution, known-limitation disclosure and an upstream patch guide. Deducted: no CHANGELOG or maintenance-ownership statement (fork update path depends on upstream sync without commitment); pyproject version 0.3.0+openclaw2 mildly inconsistent with the skill file version; publisher identity is unverified in the registry.

5Effectiveness6 / 15 · 2.0/5

The core task (template-based multi-agent team launch producing a synthesized report) is fully described, with concrete use cases in the README. Deducted: Hermes workers often skip the inbox-send, output lives in tmux scrollback and is lost on cleanup, and risk-manager is prone to crashing leaving synthesis incomplete — the user must do substantial manual capture and assembly to obtain usable results; output correctness has no executed evidence; comparative benefit over a single agent is only asserted ('dramatically better'), not verified. Static cap limits the score below 7.

6Verifiability4 / 10 · 2.0/5

A real CI workflow (multi-OS/Python pytest matrix) and a committed test suite exist, and tests/test_adapters.py thoroughly covers the Hermes adapter behavior claimed in SKILL.md (chat insertion, --source tool, --yolo, -q prompt), mutually corroborating the documentation. Deducted: tests cover the CLI adapter layer, not the end-to-end multi-agent orchestration the skill promises; CI results are not visible as third-party execution evidence in static review; key value claims (7 analysts producing better results) are unverifiable. Static cap limits the score below 5.

Evidence confidence:Low Reviewed Sep 09, 2026 Reviewed revision 8dac3fc9774d
Before you use it
  • The skill launches Hermes workers with --yolo/skip_permissions by default, bypassing permission prompts, and template launch requires --force to suppress warnings. Parallel multi-agent execution amplifies side effects; use only in acceptable code/environment sandboxes.
  • Known serious reliability defects: inbox peek often returns empty, actual output exists only in tmux scrollback and is permanently lost after team cleanup --force; the risk-manager agent is prone to crashing, leaving synthesis incomplete. Always capture all tmux panes before cleanup.
  • Hermes ≤0.8.0 does not propagate --source tool; a one-line upstream patch is required for session isolation, otherwise spawned sessions mix with interactive sessions.
  • The skill targets Hermes users while the repository promotes OpenClaw; templates default to openclaw, and omitting --command hermes fails outright. SKILL.md is English-only; Chinese users must rely on the README translations.
  • Seven-agent parallel launches incur high token/time cost (~2-5 minutes per team); publisher identity is unverified by FollowSkills; this is a static review with no execution performed.
Review evidence [1][2][3][4][5][6][7][8]
See the full review method →

What does this skill do, and when should you use it?

This is the Hermes-facing skill file (skills/hermes/SKILL.md) from the win4r/ClawTeam-OpenClaw repository. It teaches Hermes when to route team/swarm/multi-agent requests to the clawteam CLI rather than a single delegate_task call. It ships four built-in templates — hedge-fund (7 analyst roles), research-paper, code-review, and strategy-room — all running in isolated tmux windows with git worktrees. It prescribes exact launch flags (--team-name, --command hermes), a mandatory ~60-second boot wait with 30-second board polling, and documents known pitfalls: Hermes ≤ 0.8.0 ignoring --source tool, and unreliable inbox peek requiring tmux capture instead. It suits users already running Hermes who want multi-perspective parallel analysis.

The skill is an instruction file that, once installed, drives Hermes to: call clawteam launch to instantiate template-based teams (e.g., hedge-fund spawns portfolio-manager, buffett, growth, technical, fundamentals, sentiment, and risk-manager agents); use clawteam spawn for custom teams, where each worker runs hermes chat --yolo --source tool -q "<task>" in its own tmux window and git worktree; track tasks from pending to COMPLETED via the kanban board (board show/live); read agent output via clawteam inbox peek or tmux capture-pane; and tear down with team cleanup. Workers automatically inherit MCP servers configured in ~/.hermes/config.yaml.

  1. A developer who uses Hermes Agent daily and wants stock, research, or review questions answered by 5–7 parallel specialist agents instead of one response
  2. An individual investor wanting multi-perspective analysis of a stock (e.g., TSLA) across value, growth, technical, fundamentals, sentiment, and risk lenses
  3. A researcher surveying arXiv papers or multiple sources in parallel and synthesizing a report
  4. A developer reviewing a pull request from multiple angles (architecture, security, testing)
  5. Anyone needing an ad-hoc custom team (e.g., a researcher plus a writer) for a multi-step task

What are this skill's strengths and limitations?

Pros
  • Four ready-made templates; one command spins up a 7-role hedge-fund-style analysis team
  • The skill file exhaustively documents flag pitfalls, polling cadence, and failure modes, reducing trial and error
  • Each worker gets an isolated git worktree and dedicated tmux window, making output traceable
  • Workers automatically inherit Hermes-configured MCP servers, so knowledge bases and memory stores work out of the box
  • Clearly delineates when to use clawteam versus delegate_task
Limitations
  • Upstream Hermes ≤ 0.8.0 bug: --source tool is accepted but not propagated, so spawned sessions interleave with personal sessions until a one-line patch is applied
  • inbox peek often returns empty — Hermes workers write to tmux scrollback, not the inbox system; reading results requires tmux capture
  • Worker output is not persistent: findings are lost on cleanup unless captured or written to an MCP-backed store
  • The risk-manager agent is known to crash mid-run, potentially leaving the final synthesis incomplete
  • Each run takes 2–5+ minutes, and no token/cost estimates are documented
  • Templates were designed around OpenClaw's inbox-send coordination pattern; Hermes workers sometimes finish without sending inbox messages

How do you install this skill?

Prerequisites: Python 3.10+, tmux (Linux/macOS/WSL), and Hermes Agent. Install the host (do NOT pip install clawteam — the PyPI version defaults to claude and lacks this fork's adaptations): git clone https://github.com/win4r/ClawTeam-OpenClaw.git && cd ClawTeam-OpenClaw && pip install -e . Optionally ensure PATH in fresh shells: mkdir -p ~/bin && ln -sf "$(which clawteam)" ~/bin/clawteam. Install the skill (Hermes users): mkdir -p ~/.hermes/skills/openclaw-imports/clawteam && cp skills/hermes/SKILL.md ~/.hermes/skills/openclaw-imports/clawteam/SKILL.md, then verify with hermes skills list | grep clawteam. The source does not document any Hermes-specific differences under native Windows.

How do you use this skill?

Trigger it by phrasing requests with team/swarm/multi-agent keywords. One-command template launch: clawteam launch hedge-fund --team-name tesla --goal "Analyze TSLA" --command hermes --force (Hermes users MUST pass --command hermes; templates default to openclaw and will fail with gateway token errors otherwise). Manual mode: clawteam spawn -t my-team -n researcher --task "..." --no-workspace hermes (hermes is a trailing positional arg, not --command). After launching, sleep 60 for boot (each worker takes 20–40 s), then poll board show every 30 seconds; total runtime is typically 2–5 minutes. Read results via tmux capture-pane per window (inbox peek is unreliable), and only run clawteam team cleanup <name> --force after capturing reports.

How does this skill compare with similar options?

The upstream project is HKUDS/ClawTeam; this repo is a fork with deep OpenClaw integration (openclaw as default agent) that syncs all upstream fixes. The skill file itself contrasts clawteam against the single sub-agent delegate_task: the latter is one agent, while clawteam is 5–7 parallel specialists with a kanban board and shared inboxes. The README also contrasts ClawTeam with other multi-agent frameworks, which require humans to write orchestration code and depend on Redis/message queues, whereas ClawTeam needs only a filesystem plus tmux.

FAQ

Why are inboxes empty during the first 60 seconds after launch?
Each Hermes worker takes 20–40 seconds to boot (loading 62 tools, 113 skills, and MCP servers), and research/analysis takes 1–5 more minutes. The skill mandates sleep 60 followed by 30-second board polls; checking earlier leads to a false conclusion that the team failed.
Why does inbox peek return empty while tasks show COMPLETED?
This is a documented failure mode: Hermes workers write output to tmux scrollback, not the inbox system. Use tmux capture-pane per window, or instruct agents in the task prompt to persist findings to an MCP-backed store.
Why do spawned sessions mix into my personal Hermes session list?
An upstream Hermes ≤ 0.8.0 bug: the agent constructor reads platform='cli' before honoring the HERMES_SESSION_SOURCE env var set by --source tool. SKILL.md includes a one-line precedence swap (source=os.environ.get("HERMES_SESSION_SOURCE") or self.platform or "cli" in run_agent.py) to apply locally or wait for upstream.
What are the permission and dependency requirements?
Python 3.10+, tmux (Linux/macOS/WSL), and a working Hermes Agent install; clawteam must be installed locally from this repo via pip install -e . (the PyPI clawteam is the upstream version, and the npm package of the same name is an unrelated name-squat). MCP capability comes from ~/.hermes/config.yaml — no MCP required if none is configured. The source provides no cost estimates for template runs.

More skills from this repository

All from win4r/ClawTeam-OpenClaw

Related skills