Agent skill

Clawteam Dev

by HKUDS in HKUDS/ClawTeam

A skill your agent uses when working inside the ClawTeam repository itself: local development, debugging, reviewing, testing, validating multi-agent flows, or checking whether a code change actually…

MITAuto-check passedTesting & QA

Install Clawteam Dev

skills CLI
$ npx skills add HKUDS/ClawTeam --skill clawteam-dev -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HKUDS/ClawTeam clawteam-dev --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HKUDS/ClawTeam.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/clawteam-dev .claude/skills/clawteam-dev && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
clawteam-dev
GitHub stars
5.5k
Used in
1 other repo
Token cost
~1.1k tokens
SKILL.md length
388 words
Files
3 (incl. scripts)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when working inside the ClawTeam repository itself: local development, debugging, reviewing, testing, validating multi-agent flows, or checking whether a code change actually…

  • Working inside the ClawTeam repository itself: local development
  • SKILL.md covers Development Bootstrap, Project Skill Wiring, Typical Uses and Fast Validation, plus 4 more sections
  • Runs Shell scripts from its folder; calls pytest, bash and ruff
  • Validating multi-agent flows

What it does

Clawteam Dev is an agent skill from HKUDS/ClawTeam. Use this skill when working inside the ClawTeam repository itself: local development, debugging, reviewing, testing, validating multi-agent flows, or checking whether a code change actually works end-to-end. Use the repository bootstrap scripts to standardize the local clawteam command and to wire project-local .agents and .claude skills back to this repository. This skill is repository-development oriented, not a general end-user usage guide.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `scripts/bootstrap_clawteam_dev.sh` and `scripts/link_local_clawteam_skills.sh`).

It sits in Testing & QA, covering Multi-agent orchestration. The repository describes itself as: "ClawTeam: Agent Swarm Intelligence" (One Command → Full Automation). The licence is MIT.

When your agent uses it

  • Working inside the ClawTeam repository itself: local development
  • Validating multi-agent flows
  • Checking whether a code change actually works end-to-end

Example prompts

  • “/clawteam-dev”

Requirements

  • Python 3
  • A Bash shell

What it can do on your machine

Read from SKILL.md and the folder at commit 0119833. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • pytest
    • bash
    • ruff

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Clawteam Dev loads about 1.1k tokens when it runs. Until then it costs about 117 tokens; SKILL.md has 388 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~117
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from HKUDS/ClawTeam at commit 0119833, republished under its MIT licence (© HKUDS). 388 words, ~1,094 tokens.

Download SKILL.mdSave it as .claude/skills/clawteam-dev/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
clawteam-dev
description
Use this skill when working inside the ClawTeam repository itself: local development, debugging, reviewing, testing, validating multi-agent flows, or checking whether a code change actually works end-to-end. Use the repository bootstrap scripts to standardize the local `clawteam` command and to wire project-local `.agents` and `.claude` skills back to this repository. This skill is repository-development oriented, not a general end-user usage guide.
version
0.2.0

ClawTeam Local Development

This skill is for developing and validating ClawTeam inside the ClawTeam repository. Use it when the task is about changing ClawTeam itself, testing local behavior, or verifying multi-agent workflows against the current checkout.

Development Bootstrap

Standardize the local development environment with the bootstrap script:

bash
bash scripts/bootstrap_clawteam_dev.sh

This script lives in scripts/bootstrap_clawteam_dev.sh inside this skill folder.

This script does all of the following:

  • Creates a fixed uv environment at ~/.clawteam-venv
  • Installs the current repository into that environment with dev dependencies
  • Writes ~/.local/bin/clawteam to point at the fixed environment
  • Adds a clawteam() shell function block to ~/.bashrc

After it finishes:

bash
source ~/.bashrc
clawteam --version

Use this bootstrap whenever you want the same clawteam command across different Python environments on the machine.

Project Skill Wiring

To wire another local project so its ./.agents and ./.claude directories use this repository's local ClawTeam skills directly:

bash
bash scripts/link_local_clawteam_skills.sh /path/to/project

This script lives in scripts/link_local_clawteam_skills.sh inside this skill folder.

This creates these symlinks inside the target project:

  • ./.agents/skills/clawteam
  • ./.claude/skills/clawteam

Run the same script again any time you want to refresh or recreate those links.

Typical Uses

  • Run targeted local validation after code changes
  • Reproduce a spawn / board / task / inbox / harness bug
  • Smoke-test the real CLI in tmux or subprocess mode
  • Review ClawTeam workflows end-to-end from the current repository checkout

Fast Validation

Prefer the smallest validation that proves the change.

bash
ruff check clawteam/ tests/
pytest tests/<target_file>.py -q

Use broader runs only when the change crosses modules:

bash
pytest tests/test_cli_commands.py -q
pytest tests/test_spawn_backends.py -q
pytest tests/test_harness.py tests/test_event_bus.py -q
Show full SKILL.md (163 more words)Show less

Prerequisites

  • clawteam command available
  • tmux available
  • A supported CLI agent such as claude or codex if you are spawning real workers
  • Current directory is the ClawTeam git repo when testing worktree isolation or local source changes

Local Smoke Test

Use this when you need a real multi-agent workflow check instead of unit tests.

bash
clawteam team spawn-team dev-smoke -d "Local ClawTeam smoke test" -n leader
clawteam task create dev-smoke "Smoke test worker" -o worker1 -p high
clawteam spawn --team dev-smoke --agent-name worker1 --task "Report your status to leader and mark the task completed when done."
clawteam board show dev-smoke
clawteam task wait dev-smoke --timeout 300 --poll-interval 5

If you are validating harness behavior specifically:

bash
clawteam harness conduct dev-harness \
  --goal "Create a small implementation plan and execute it with one worker" \
  --cli codex \
  --agents 1

Cleanup

Use the real ClawTeam commands instead of ad-hoc directory assumptions whenever possible:

bash
clawteam team cleanup dev-smoke
clawteam team cleanup dev-harness

If a crashed tmux session or worktree is left behind, clean it up explicitly after inspecting it.

Development Rules

  • Prefer clawteam commands over editing state files directly.
  • Prefer targeted tests over broad end-to-end runs unless the change crosses spawn/runtime/workflow boundaries.
  • Use board, task wait, and team status to observe behavior before assuming a bug is in the spawn layer.
  • When testing agent coordination, keep the team small first: one leader and one or two workers.
  • Only escalate to harness or full swarm tests when the lower-level task/spawn/inbox path already works.

© HKUDS, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts) in .agents/skills/clawteam-dev of HKUDS/ClawTeam.

  • SKILL.md
  • scripts/bootstrap_clawteam_dev.sh
  • scripts/link_local_clawteam_skills.sh

Open the folder on GitHubat commit 0119833

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in HKUDS/ClawTeam, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Clawteam Dev next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Clawteam Dev compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Clawteam Dev this skillHKUDS/ClawTeam5.5k1 repos~1.1kAutomated safety check: PassMIT
Reviewatelier-fashion/adlc-toolkit171—~1.9kAutomated safety check: PassMIT
Prompt Generatorcatlog22/Claude-Code-Workflow2.1k1 repos~4.7kAutomated safety check: NotesMIT
Workflow Reviewnabeelhyatt/coworkpowers114—~1.3kAutomated safety check: PassMIT
Multi Agent Task Orchestratorsickn33/agentic-awesome-skills47k2 repos~1.5kAutomated safety check: PassMIT
Agent Team OrchestrationaAAaqwq/AGI-Super-Team1053 repos~1.4kAutomated safety check: PassMIT

Similar skills

  • Review

    atelier-fashion/adlc-toolkit

    Multi-agent code review covering correctness, quality, architecture, test coverage, and security

    171 GitHub stars~1.9k tokensUpdated 8 days ago
    Testing & QAAuto-check passed
  • Prompt Generator

    catlog22/Claude-Code-Workflow

    Generate or convert Claude Code prompt files — command orchestrators, skill files, agent role definitions, or style conversion of existing files.

    2.1k GitHub starsUsed in 1 repo~4.7k tokens
    Testing & QAAuto-check: notes
  • Workflow Review

    nabeelhyatt/coworkpowers

    Run parallel multi-agent review on completed knowledge work.

    114 GitHub stars~1.3k tokensUpdated 7 mo ago
    Testing & QAAuto-check passed
  • Multi Agent Task Orchestrator

    sickn33/agentic-awesome-skills

    Route tasks to specialized AI agents with anti-duplication, quality gates, and 30-minute heartbeat monitoring

    47k GitHub starsUsed in 2 repos~1.5k tokens
    Testing & QAAuto-check passed
  • Agent Team Orchestration

    aAAaqwq/AGI-Super-Team

    Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows.

    105 GitHub starsUsed in 3 repos~1.4k tokens
    Testing & QAAuto-check passed
  • Team Coordination

    bybren-llc/safe-agentic-workflow

    Agent Teams orchestration patterns for multi-agent SAFe workflows.

    421 GitHub stars~1.9k tokensUpdated 2 mo ago
    Testing & QAAuto-check: notes

Questions about Clawteam Dev

What does Clawteam Dev do?

A skill your agent uses when working inside the ClawTeam repository itself: local development, debugging, reviewing, testing, validating multi-agent flows, or checking whether a code change actually…. Clawteam Dev is an agent skill from HKUDS/ClawTeam. Use this skill when working inside the ClawTeam repository itself: local development, debugging, reviewing, testing, validating multi-agent flows, or checking whether a code change actually works end-to-end.

When should I use Clawteam Dev?

Clawteam Dev fits situations like: working inside the ClawTeam repository itself: local development; validating multi-agent flows; checking whether a code change actually works end-to-end.

How do I install Clawteam Dev in Claude Code?

Run `npx skills add HKUDS/ClawTeam --skill clawteam-dev -a claude-code`. Or copy the skill folder (.agents/skills/clawteam-dev in HKUDS/ClawTeam) into .claude/skills/clawteam-dev in your project. Claude Code loads it when a task matches its description.

How do I install Clawteam Dev in Codex?

Run `npx skills add HKUDS/ClawTeam --skill clawteam-dev -a codex`. Or copy the skill folder (.agents/skills/clawteam-dev in HKUDS/ClawTeam) into .agents/skills/clawteam-dev in your project. Codex loads it when a task matches its description.

Can I use Clawteam Dev in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HKUDS/ClawTeam --skill clawteam-dev -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/clawteam-dev, .gemini/skills/clawteam-dev, .github/skills/clawteam-dev and .opencode/skills/clawteam-dev in your project.

What does Clawteam Dev need to run?

Going by SKILL.md and its folder, Clawteam Dev needs a shell for the scripts in its folder and the command-line tools its instructions call (pytest, bash and ruff). Our summary lists: Python 3; A Bash shell.

Does Clawteam Dev access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Clawteam Dev safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Clawteam Dev use?

Clawteam Dev is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Clawteam Dev use?

About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Clawteam Dev?

Skills that share tags, products or a category with Clawteam Dev: Review (atelier-fashion/adlc-toolkit, 171 stars), Prompt Generator (catlog22/Claude-Code-Workflow, 2.1k stars), Workflow Review (nabeelhyatt/coworkpowers, 114 stars) and Multi Agent Task Orchestrator (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Clawteam Dev?

HKUDS (a GitHub organization) maintains it in HKUDS/ClawTeam, which has 5,535 GitHub stars. The repository was last updated on May 9, 2026.

Source: HKUDS/ClawTeam on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.