claude-code-team

Name: claude-code-team
Author: tomevault-io

AI Community

Repo stars 0
Author updated Live
Author repo skills-registry

Fluxly profile Facts only: domain, agents, trust score, runtime, permissions and network

Domain: AI
Compatible agents: Claude Code
Cursor
Cline
Codex
Windsurf
Gemini CLI

+20
Trust score: 88 / 100 · community maintained
Author / version / license: @tomevault-io · no license declared
Token usage: Lean
Setup complexity: Guided setup
External API key: Required · Anthropic
Operating systems: macOS · Linux
Runtime requirements: No special requirements
Permissions: Read-only
Write / modify
Shell exec
Env read
Network behavior: External requests
Install commands: 26 variants

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview claude-code-team.preview

---
name: claude-code-team
description: Asynchronous Claude Code Agent Teams with session management and multi-channel notifications (Fe…
category: ai
runtime: no special runtime
---

# claude-code-team output preview

## PART A: Task fit
- Use case: Asynchronous Claude Code Agent Teams with session management and multi-channel notifications (Feishu, Discord, Telegram). Use when this capability is needed. Execute coding tasks asynchronously with automatic notifications on completion. requires Anthropic API key. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Tools / Quick Start / Setup” and do not present inference as author intent.

## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Asynchronous Claude Code Agent Teams with session management and multi-channel notifications (Feishu, Discord, Telegram). Use when this capability is needed. Execute coding tasks asynchronously with automatic notifications on completion. requires Anthropic API key. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Tools / Quick Start / Setup” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, run shell commands, read environment variables; may access external network resources; requires Anthropic API keys.

## Running Rules
- read files, write/modify files, run shell commands, read environment variables; may access external network resources; requires Anthropic API keys.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.

SKILL.md SKILL.md

---
name: claude-code-team
description: Asynchronous Claude Code Agent Teams with session management and multi-channel notifications (Fe…
category: ai
source: tomevault-io/skills-registry
---

# claude-code-team

## When to use
- Asynchronous Claude Code Agent Teams with session management and multi-channel notifications (Feishu, Discord, Telegra…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.

## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.

## Execution rules
- Organize steps around “Tools / Quick Start / Setup” and keep inference separate from source facts.
- read files, write/modify files, run shell commands, read environment variables; may access external network resources; requires Anthropic API keys.
- Validate with a small sample before expanding the task.

## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.

Evidence boundary and execution chain

The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.

skill "claude-code-team" {
  input      -> user goal + target files + boundaries + acceptance criteria
  context    -> Tools / Quick Start / Setup
  rules      -> SKILL.md triggers / order / output contract
  runtime    -> no special runtime | read files, write/modify files, run shell commands, read environment variables | may access external network resources
  guardrails -> requires Anthropic API keys + small-sample validation + diff/log review
  output     -> copyable result + checklist + next iteration
}

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: Asynchronous Claude Code Agent Teams with session management and multi-channel notifications (Feishu, Discord, Telegram). Use wh…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “Tools”, “Quick Start”, “Setup”, “Prerequisites”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name claude-code-team directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “Tools / Quick Start / Setup” before expanding.

Boundaries And Review

Dependencies: Prepare Anthropic API keys before running a full task.
Permissions: Declared permissions include read / write / shell-exec / env-read; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

Claude Code Agent Teams

Execute coding tasks asynchronously with automatic notifications on completion.

Tools

Tool	Description
`invoke_task`	Execute a coding task asynchronously
`list_sessions`	List all active sessions
`get_session`	Get session ID for a project directory
`remove_session`	Remove a session mapping
`check_env`	Validate environment configuration
`test_notification`	Send test notification

Quick Start

# 1. Set API key
export ANTHROPIC_API_KEY="sk-xxx"

# 2. Install hooks (one-time setup)
./main.sh install-hooks

# 3. Run a task
./main.sh invoke "Create a snake game" /path/to/project

Setup

Prerequisites

# Install dependencies
sudo apt-get install jq curl      # Ubuntu/Debian
brew install jq curl              # macOS
npm install -g @anthropic-ai/claude-cli

Configuration

Configuration priority: Environment Variables > settings.json > Defaults

Priority	Source	Use Case
1 (Highest)	Environment variables	API keys, secrets, temporary overrides
2	`config/settings.json`	Team-shared configuration
3 (Lowest)	Built-in defaults	Default values if not configured

Environment variables (recommended for secrets):

export ANTHROPIC_API_KEY="sk-xxx"       # Required
export ANTHROPIC_BASE_URL="https://..." # Optional
export ANTHROPIC_MODEL="claude-sonnet-4-6" # Optional

Config file (config/settings.json):

{
  "api_base_url": "https://coding.dashscope.aliyuncs.com/apps/anthropic",
  "model": "claude-sonnet-4-6",
  "notify": {
    "channels": ["feishu"],
    "feishu": { "chat_id": "user:ou_xxx" }
  }
}

Tip: Use environment variables for sensitive data (API keys) and settings.json for shareable configuration (notification channels).

Usage

# Auto session (recommended)
./main.sh invoke "Fix login bug" /path/to/project

# Force new session
./main.sh invoke "Refactor module" /path/to/project new

# Custom session ID
./main.sh invoke "Hotfix" /path/to/project hotfix-001

# Manage sessions
./main.sh list-sessions
./main.sh get-session /path/to/project
./main.sh remove-session /path/to/project

# Check environment
./main.sh check-env

# Test notification
./main.sh test-notify

Notification Channels

Configure in config/settings.json:

Feishu:

{"notify": {"channels": ["feishu"], "feishu": {"chat_id": "user:ou_xxx"}}}

Discord:

{"notify": {"channels": ["discord"], "discord": {"webhook_url": "https://discord.com/api/webhooks/..."}}}

Telegram:

{"notify": {"channels": ["telegram"], "telegram": {"bot_token": "123456:ABC...", "chat_id": "@channel"}}}

Workflow

Invoke task → Validate env → Get/Create session → Start notification
    ↓
Run Claude Code in background → Task completes → Hook triggers
    ↓
Send completion notification → Write results

Output Files

Default: ~/.openclaw/data/claude-code-results/

File	Description
`task-output.txt`	Full Claude Code output
`task-meta.json`	Task metadata (status, exit code)

Troubleshooting

# Check environment
./main.sh check-env

# Test notification
./main.sh test-notify

# Reinstall hooks
./main.sh remove-hooks && ./main.sh install-hooks

Source: damiangao/agent-skills — distributed by TomeVault.

Install command

One-click installPick a runner, click Copy, paste into your terminal, press enter

npx skills add tomevault-io/skills-registry/damiangao--agent-skills--claude-code-team -y

Open general install guide

View skill source

Works with

Claude Code
Cursor
Cline
Codex
Windsurf
Gemini
OpenCode
Roo Code
AAide
+Augment
GitHub Copilot
OpenClaw
KKiro
Junie
WWarp
Goose
Trae
Kilo Code
OpenHands
Amp
Zencoder
CContinue
AIAider
CodeBuddy
CodeGeeX
Replit Agent

Security audit

88 / 100

Community

未声明 license/许可。
未声明 version。
未限定 allowed-tools，默认拥有全部工具权限。

Metadata

Source: github
tomevault-io/skills-registry
中文

More by @tomevault-io

Category & tags

Category AI