Agent skill

Agent Team And Skill Builder

by xvirobotics in xvirobotics/metabot

Decides whether a request wants a full agent team, one agent, or one skill, then follows the matching flow file to generate it.

MITAuto-check: notesAgent Workflows

Install Agent Team And Skill Builder

skills CLI
$ npx skills add xvirobotics/metabot --skill metaskill -a claude-code

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

GitHub CLI
$ gh skill install xvirobotics/metabot metaskill --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/xvirobotics/metabot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/skills/metaskill .claude/skills/metaskill && 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
metaskill
GitHub stars
994
Token cost
~628 tokens
SKILL.md length
258 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Decides whether a request wants a full agent team, one agent, or one skill, then follows the matching flow file to generate it.

  • Works in 2 steps: Detect Intent → Load and Execute Flow
  • Setting up a complete set of agents for a new project type
  • SKILL.md covers Auto-Detected Context, Step 1: Detect Intent and Step 2: Load and Execute Flow
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Given a free-text request, this skill first works out which of three modes applies: a complete team of agents suited to a project type, one individual agent such as a reviewer or deployment handler, or a single slash-command skill. Wording in the request points to the mode, and it asks the user to pick when that wording is ambiguous.

Once a mode is settled, it reads the matching flow file from the detected skill base directory and follows those instructions exactly, treating the original request as context for whatever gets generated for Claude Code, Kimi, or Codex.

When your agent uses it

  • Setting up a complete set of agents for a new project type
  • Creating one individual agent, such as a security reviewer or deployment agent
  • Creating a single custom skill or slash command for a project

Example prompts

  • “Build a full agent team for a fullstack web app.”
  • “Create a code reviewer agent for our Go services.”
  • “Make a skill that runs our test suite on request.”

Requirements

  • Read, Write, Edit, Bash, Glob, Grep, WebSearch, WebFetch, and AskUserQuestion tool access
  • Pre-approved tools (allowed-tools): Read, Write, Edit, Bash, Glob, Grep, WebSearch, WebFetch, AskUserQuestion

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. Detect Intent
  2. Load and Execute Flow

What it can do on your machine

Read from SKILL.md and the folder at commit 916637e. 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:

    • Read
    • Write
    • Edit
    • Bash
    • Glob
    • Grep
    • WebSearch
    • WebFetch
    • AskUserQuestion

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    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

Agent Team And Skill Builder loads about 628 tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 258 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~628

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: Read, Write, Edit, Bash, Glob, Grep, WebSearch, WebFetch, AskUserQuestion

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from xvirobotics/metabot at commit 916637e, republished under its MIT licence (© xvirobotics). 258 words, ~628 tokens.

Download SKILL.mdSave it as .claude/skills/metaskill/SKILL.md (or your agent's skills folder).
name
metaskill
description
The meta-skill: create AI agent teams, individual agents, or custom skills for any project. Use when the user wants to generate a complete agent team, create a single agent, or create a single skill for Claude Code, Kimi, or Codex.
allowed-tools
Read, Write, Edit, Bash, Glob, Grep, WebSearch, WebFetch, AskUserQuestion
user-invocable
true
disable-model-invocation
false
context
fork
agent
general-purpose
argument-hint
[what to create] e.g. 'ios app', 'a security reviewer agent', 'a deploy skill'

You are an elite AI agent architect. You can create complete agent teams, individual agents, or custom skills — all through a single command.

User request: $ARGUMENTS

Auto-Detected Context

Working directory: !pwd Existing subdirectories: !ls -d */ 2>/dev/null | head -20 || echo "empty directory" Skill base: !for d in ".codex/skills/metaskill" ".claude/skills/metaskill" "$HOME/.codex/skills/metaskill" "$HOME/.claude/skills/metaskill"; do [ -d "$d/flows" ] && echo "$d" && break; done 2>/dev/null || echo "$HOME/.codex/skills/metaskill"

Step 1: Detect Intent

Analyze $ARGUMENTS to determine the mode:

  • Team mode (default): The user wants a complete agent team for a project type. Trigger words: "app", "project", "team", "fullstack", "pipeline", "game dev", or any domain/technology without explicit "agent" or "skill" keywords. Examples: "ios app", "fullstack web", "data science pipeline", "game dev with Unity"

  • Agent mode: The user wants to create a single agent. Trigger words: "agent", "reviewer", "engineer" (as a role), or phrases like "create an agent that..." Examples: "a security reviewer agent", "code reviewer for Go", "create an agent that handles deployments"

  • Skill mode: The user wants to create a single skill (slash command). Trigger words: "skill", "command", "slash command", or phrases like "create a skill that..." Examples: "a deploy skill", "slash command to run tests", "create a skill for linting"

If the intent is ambiguous, use AskUserQuestion to ask the user which mode they want.

Step 2: Load and Execute Flow

Based on the detected mode, read the corresponding flow file from the Skill base path detected above:

  • Team mode → Read <skill-base>/flows/team.md
  • Agent mode → Read <skill-base>/flows/agent.md
  • Skill mode → Read <skill-base>/flows/skill.md

Then follow the instructions in that flow file exactly, using the user's request as context.

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

Files

Just SKILL.md in src/skills/metaskill of xvirobotics/metabot.

Open the folder on GitHubat commit 916637e

Compare with similar skills

Agent Team And Skill Builder 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.

Agent Team And Skill Builder compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Team And Skill Builder this skillxvirobotics/metabot994—~628Automated safety check: NotesMIT
Harness Agent Team Designerrevfactory/harness9.1k—~4.5kAutomated safety check: PassApache-2.0
Harness Evolution Feedback Looprevfactory/harness9.1k—~855Automated safety check: PassApache-2.0
Kimi Code DelegationCherryHQ/cherry-studio52k—~504Automated safety check: PassAGPL-3.0
Skillbuddy Skill Creatorkonnga/skill-buddy117—~517Automated safety check: PassMIT
Open Dynamic Workflowsxz1220/open-dynamic-workflows105—~2kAutomated safety check: PassMIT

Similar skills

  • Harness Agent Team Designer

    revfactory/harness

    Designs a project-specific agent harness: defines specialist agents, writes the skills they follow, picks an execution mode and model for each, and keeps the setup maintained.

    9.1k GitHub stars~4.5k tokensUpdated 11 days ago
    Agent WorkflowsAuto-check passed
  • Collects feedback on how an agent harness performed, generalizes it, and updates the harness agents, skills and orchestrator along with a change-history table.

    9.1k GitHub stars~855 tokensUpdated 11 days ago
    Agent WorkflowsAuto-check passed
  • Kimi Code Delegation

    CherryHQ/cherry-studio

    Delegates one bounded repository task to Kimi Code in non-interactive prompt mode and reads back the final result from its JSON event stream.

    52k GitHub stars~504 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Skillbuddy Skill Creator

    konnga/skill-buddy

    通过自然语言对话创建或更新可由多个本机 AI agent 使用的 Skill,并检查重复、触发条件、资源依赖与跨平台兼容性。用户在 SkillBuddy 中要求新建、完善、迁移或适配 Skill 时使用。

    117 GitHub stars~517 tokensUpdated 27 days ago
    Agent WorkflowsAuto-check passed
  • Open Dynamic Workflows

    xz1220/open-dynamic-workflows

    Write and run dynamic workflows: short JavaScript scripts in Claude Code's workflow dialect, run with the odw CLI outside the host agent's context, fanning subtasks out to coding-agent CLIs (Codex…

    105 GitHub stars~2k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Agent Orchestrator

    NeverSight/learn-skills.dev

    Meta-agent skill for orchestrating complex tasks through autonomous sub-agents.

    216 GitHub starsUsed in 1 repo~1.4k tokens
    Agent WorkflowsAuto-check passed

More from xvirobotics/metabot

  • Generates Chinese speech audio from text using Volcengine's Doubao TTS API, for narration, voiceovers or multi-voice podcasts.

    994 GitHub stars~1.1k tokensUpdated 24 days ago
    Auto-check: notes
  • MetaBot Agent Teams CLI

    xvirobotics/metabot

    Documents the metabot teams command surface for creating durable teams, spawning teammates, dispatching tasks and inspecting their runs across engine sessions.

    994 GitHub stars~693 tokensUpdated 24 days ago
    Auto-check passed
  • MetaBot Scheduler

    xvirobotics/metabot

    Schedules persistent cron and one-shot tasks on the MetaBot server that survive Claude session restarts and can be managed by other bots.

    994 GitHub stars~1k tokensUpdated 24 days ago
    Auto-check passed
  • MetaBot CLI

    xvirobotics/metabot

    Documents the unified `metabot` CLI for personal memory, the skill hub, durable agent messaging, the agent registry, T5T status and scheduling.

    994 GitHub stars~573 tokensUpdated 24 days ago
    Auto-check passed

Works with

Categories

Questions about Agent Team And Skill Builder

What does Agent Team And Skill Builder do?

Decides whether a request wants a full agent team, one agent, or one skill, then follows the matching flow file to generate it. Given a free-text request, this skill first works out which of three modes applies: a complete team of agents suited to a project type, one individual agent such as a reviewer or deployment handler, or a single slash-command skill. Wording in the request points to the mode, and it asks the user to pick when that wording is ambiguous.

When should I use Agent Team And Skill Builder?

Agent Team And Skill Builder fits situations like: setting up a complete set of agents for a new project type; creating one individual agent, such as a security reviewer or deployment agent; creating a single custom skill or slash command for a project.

How do I install Agent Team And Skill Builder in Claude Code?

Run `npx skills add xvirobotics/metabot --skill metaskill -a claude-code`. Or copy the skill folder (src/skills/metaskill in xvirobotics/metabot) into .claude/skills/metaskill in your project. Claude Code loads it when a task matches its description.

How do I install Agent Team And Skill Builder in Codex?

Run `npx skills add xvirobotics/metabot --skill metaskill -a codex`. Or copy the skill folder (src/skills/metaskill in xvirobotics/metabot) into .agents/skills/metaskill in your project. Codex loads it when a task matches its description.

Can I use Agent Team And Skill Builder 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 xvirobotics/metabot --skill metaskill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/metaskill, .gemini/skills/metaskill, .github/skills/metaskill and .opencode/skills/metaskill in your project.

What does Agent Team And Skill Builder need to run?

SKILL.md names no scripts, command-line tools or credentials: Agent Team And Skill Builder is instructions for the agent only. Our summary lists: Read, Write, Edit, Bash, Glob, Grep, WebSearch, WebFetch, and AskUserQuestion tool access. Its frontmatter pre-approves these tools: Read, Write, Edit, Bash, Glob, Grep, WebSearch, WebFetch, AskUserQuestion.

Does Agent Team And Skill Builder 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 Agent Team And Skill Builder 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. Review the folder before installing.

What licence does Agent Team And Skill Builder use?

Agent Team And Skill Builder 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 Agent Team And Skill Builder use?

About 628 tokens (SKILL.md is roughly 2.5k 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 Agent Team And Skill Builder?

Skills that share tags, products or a category with Agent Team And Skill Builder: Harness Agent Team Designer (revfactory/harness, 9.1k stars), Harness Evolution Feedback Loop (revfactory/harness, 9.1k stars), Kimi Code Delegation (CherryHQ/cherry-studio, 52k stars) and Skillbuddy Skill Creator (konnga/skill-buddy, 117 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Team And Skill Builder?

xvirobotics (a GitHub organization) maintains it in xvirobotics/metabot, which has 994 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 15, 2026.

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