Adk Agent Builder
google/adk-python
Builds ADK (Agent Development Kit) Python agents: LLM agents with tools, graph workflows of function and agent nodes, conditional routing, fan-out and join, schema-validated delegation between…
Swarm intelligence team skill — ACO-driven multi-agent exploration with hybrid LLM coordinator + Python optimization controller.
Install Team Swarm
$ npx skills add catlog22/maestro-flow --skill team-swarm -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install catlog22/maestro-flow team-swarm --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/catlog22/maestro-flow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/team-swarm .claude/skills/team-swarm && rm -rf skills-srcUse ~/.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/
Install the "team-swarm" agent skill from https://github.com/catlog22/maestro-flow/tree/master/.codex/skills/team-swarm into .claude/skills/team-swarm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "team-swarm", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/catlog22/maestro-flow/tree/master/.codex/skills/team-swarmType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add catlog22/maestro-flow --skill team-swarm -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install catlog22/maestro-flow team-swarm --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/catlog22/maestro-flow.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.codex/skills/team-swarm .agents/skills/team-swarm && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "team-swarm" agent skill from https://github.com/catlog22/maestro-flow/tree/master/.codex/skills/team-swarm into .agents/skills/team-swarm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "team-swarm", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add catlog22/maestro-flow --skill team-swarm -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install catlog22/maestro-flow team-swarm --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/catlog22/maestro-flow.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.codex/skills/team-swarm .cursor/skills/team-swarm && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "team-swarm" agent skill from https://github.com/catlog22/maestro-flow/tree/master/.codex/skills/team-swarm into .cursor/skills/team-swarm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "team-swarm", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/catlog22/maestro-flow.git --path .codex/skills/team-swarm--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add catlog22/maestro-flow --skill team-swarm -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install catlog22/maestro-flow team-swarm --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/catlog22/maestro-flow.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.codex/skills/team-swarm .gemini/skills/team-swarm && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "team-swarm" agent skill from https://github.com/catlog22/maestro-flow/tree/master/.codex/skills/team-swarm into .gemini/skills/team-swarm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "team-swarm", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install catlog22/maestro-flow team-swarmInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add catlog22/maestro-flow --skill team-swarm -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/catlog22/maestro-flow.git skills-src && mkdir -p .github/skills && cp -r skills-src/.codex/skills/team-swarm .github/skills/team-swarm && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "team-swarm" agent skill from https://github.com/catlog22/maestro-flow/tree/master/.codex/skills/team-swarm into .github/skills/team-swarm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "team-swarm", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add catlog22/maestro-flow --skill team-swarm -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install catlog22/maestro-flow team-swarm --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/catlog22/maestro-flow.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.codex/skills/team-swarm .opencode/skills/team-swarm && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "team-swarm" agent skill from https://github.com/catlog22/maestro-flow/tree/master/.codex/skills/team-swarm into .opencode/skills/team-swarm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "team-swarm", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
team-swarm- GitHub stars
- 564
- Token cost
- ~2k tokens
- SKILL.md length
- 306 words
- Files
- 17 (incl. scripts)
- Skills in repo
- 30
- Repo updated
- First seen
- Licence
- None found
At a glance
Swarm intelligence team skill — ACO-driven multi-agent exploration with hybrid LLM coordinator + Python optimization controller.
- Swarm intelligence
- SKILL.md covers Architecture, Role Registry, Role Router and Shared Constants, plus 7 more sections
- Runs Python scripts from its folder; calls python
- Tasks that involve Multi-agent orchestration
What it does
Team Swarm is an agent skill from catlog22/maestro-flow. Swarm intelligence team skill — ACO-driven multi-agent exploration with hybrid LLM coordinator + Python optimization controller. Coordinator generates swarm-config from user task, then runs K iterations of N parallel ants guided by pheromone state. Universal task space via config (nodes + scoring rule). Triggers on "team swarm", "swarm intelligence", "蚁群".
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 24 other files, including scripts (for example `roles/analyst/role.md`, `roles/ant/role.md` and `roles/coordinator/commands/converge.md`).
It sits in Agent Workflows, covering Multi-agent orchestration. It works with Python. The repository describes itself as: Intent-driven workflow orchestration for multi-agent AI development — adaptive lifecycle engine, self-reinforcing knowledge graph, and visual dashboard for Claude Code, Gemini….
When your agent uses it
- Swarm intelligence
- Tasks that involve Multi-agent orchestration
Example prompts
- “team swarm”
- “swarm intelligence”
- “/team-swarm”
Requirements
- Python 3
- Pre-approved tools (allowed-tools): Bash, Edit, Glob, Grep, Read, Write, followup_task, interrupt_agent, list_agents, mcp__maestro__team_msg, request_user_input, send_message, spawn_agent, spawn_agents_on_csv, update_plan, wait_agent
What it can do on your machine
Read from SKILL.md and the folder at commit f888cec. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
BashEditGlobGrepReadWritefollowup_taskinterrupt_agentlist_agentsmcp__maestro__team_msg
…and 6 more on the same allowed-tools line.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 4 files in scripts/ (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
python
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
Team Swarm loads about 2k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 306 words of instructions outside code blocks.
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: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Bash, Edit, Glob, Grep, Read, Write, followup_task, interrupt_agent, list_agents, mcp__maestro__team
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
Without a licence we can't republish the file, so here is its outline and opening line. It has 306 words (~1,973 tokens).
- name
- team-swarm
- allowed-tools
- Bash, Edit, Glob, Grep, Read, Write, followup_task, interrupt_agent, list_agents, mcp__maestro__team_msg, request_user_input, send_message, spawn_agent, spawn_agents_on_csv, update_plan, wait_agent
- disable-model-invocation
- true
- session-mode
- run
- version
- 0.5.91
- contract.discovery
- self-described
Files
SKILL.md and 16 other files (scripts) in .codex/skills/team-swarm of catlog22/maestro-flow.
- SKILL.md
- roles/analyst/role.md
- roles/ant/role.md
- roles/coordinator/commands/converge.md
- roles/coordinator/commands/init-swarm.md
- roles/coordinator/commands/iterate.md
- roles/coordinator/role.md
- roles/scorer/role.md
- scripts/aco.py
- scripts/pheromone.py
- scripts/scoring.py
- scripts/test_aco.py
- specs/ant-output-schema.md
- … and 4 more
Open the folder on GitHubat commit f888cec
Compare with similar skills
Team Swarm 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Team Swarm this skillcatlog22/maestro-flow | 564 | — | ~2k | Automated safety check: Notes | None | |
| Adk Agent Buildergoogle/adk-python | 22k | — | ~879 | Automated safety check: Pass | Apache-2.0 | |
| Analyze Codebasedivar-ir/ai-doc-gen | 767 | — | ~899 | Automated safety check: Pass | MIT | |
| Cao Pluginawslabs/cli-agent-orchestrator | 1.4k | — | ~3.1k | Automated safety check: Notes | Apache-2.0 | |
| agystack Runtime Setupjtaroreh/agystack | 109 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Subagent-Driven DevelopmentHoangNguyen0403/agent-skills-standard | 571 | — | ~1.3k | Automated safety check: Pass | MIT |
Similar skills
- Official
Analyze Codebase
divar-ir/ai-doc-gen
Run a multi-agent deep analysis of a codebase, producing AI-readable analysis documents in .ai/docs/ covering structure, dependencies, data flow, request flow, and APIs.
- Official
Cao Plugin
awslabs/cli-agent-orchestrator
Create a new CAO (CLI Agent Orchestrator) plugin. An agent skill from awslabs/cli-agent-orchestrator.
agystack Runtime Setup
jtaroreh/agystack
Configures agystack's model tiers per role and its execution runtime, choosing between local subagents and Cloud Run jobs for large parallel swarms.
Subagent-Driven Development
HoangNguyen0403/agent-skills-standard
Runs a multi-task implementation plan by sending each task to a fresh implementer subagent, reviewing it independently, then reviewing the whole branch.
Agentscope Skill
agentscope-ai/skills
Build and debug Python applications using AgentScope 2.x. An agent skill from agentscope-ai/skills.
More from catlog22/maestro-flow
All 30 skills in this repoThesis DOCX
catlog22/maestro-flow
Create, revise, and format thesis or dissertation Word documents with strict academic formatting control.
Scholar Anti AI Writing
catlog22/maestro-flow
Remove AI writing patterns from academic prose. An agent skill from catlog22/maestro-flow.
Scholar Citation Verify
catlog22/maestro-flow
Four-layer citation verification for academic papers. An agent skill from catlog22/maestro-flow.
Maestro Help
catlog22/maestro-flow
Maestro Flow 命令帮助系统。搜索命令、浏览技能、工作流推荐、新手引导。Triggers on "maestro-help", "帮助", "命令", "怎么用", "skill", "workflow", "maestro 怎么用".
Maestro Impeccable
catlog22/maestro-flow
A skill your agent uses when designing, reviewing, refining, fixing, or codifying frontend UI with Maestro's self-contained Impeccable core
Scholar Experiment
catlog22/maestro-flow
Systematic experimental results analysis workflow for ML/AI research papers.
Related
Works with
Categories
Questions about Team Swarm
What does Team Swarm do?
Swarm intelligence team skill — ACO-driven multi-agent exploration with hybrid LLM coordinator + Python optimization controller. Team Swarm is an agent skill from catlog22/maestro-flow. Swarm intelligence team skill — ACO-driven multi-agent exploration with hybrid LLM coordinator + Python optimization controller.
When should I use Team Swarm?
Team Swarm fits situations like: swarm intelligence; tasks that involve Multi-agent orchestration.
How do I install Team Swarm in Claude Code?
Run `npx skills add catlog22/maestro-flow --skill team-swarm -a claude-code`. Or copy the skill folder (.codex/skills/team-swarm in catlog22/maestro-flow) into .claude/skills/team-swarm in your project. Claude Code loads it when a task matches its description.
How do I install Team Swarm in Codex?
Run `npx skills add catlog22/maestro-flow --skill team-swarm -a codex`. Or copy the skill folder (.codex/skills/team-swarm in catlog22/maestro-flow) into .agents/skills/team-swarm in your project. Codex loads it when a task matches its description.
Can I use Team Swarm 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 catlog22/maestro-flow --skill team-swarm -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/team-swarm, .gemini/skills/team-swarm, .github/skills/team-swarm and .opencode/skills/team-swarm in your project.
What does Team Swarm need to run?
Going by SKILL.md and its folder, Team Swarm needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Bash, Edit, Glob, Grep, Read, Write, followup_task, interrupt_agent, list_agents, mcp__maestro__team_msg, request_user_input, send_message, spawn_agent, spawn_agents_on_csv, update_plan, wait_agent.
Does Team Swarm 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 Team Swarm safe to install?
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. 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 Team Swarm use?
No licence was found for Team Swarm or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Team Swarm use?
About 2k tokens (SKILL.md is roughly 7.9k 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 Team Swarm?
Skills that share tags, products or a category with Team Swarm: Adk Agent Builder (google/adk-python, 22k stars), Analyze Codebase (divar-ir/ai-doc-gen, 767 stars), Cao Plugin (awslabs/cli-agent-orchestrator, 1.4k stars) and agystack Runtime Setup (jtaroreh/agystack, 109 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Team Swarm?
catlog22 (a GitHub user) maintains it in catlog22/maestro-flow, which has 564 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on October 8, 2026.
Source: catlog22/maestro-flow on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.