Add a new team to the agent swarm with leader + specialists, YAML config, and prompt files
How this skill is triggered — by the user, by Claude, or both
Slash command
/superpowers-extended-cc:add-team [team-name] [description][team-name] [description]The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Before starting, create a task list using TodoWrite with the major steps below. Mark each completed as you finish it.
Before starting, create a task list using TodoWrite with the major steps below. Mark each completed as you finish it.
Add a new team called "$0" to the agent swarm.
Create YAML config at config/teams/$0.yaml
Create prompt files in src/prompts/library/
.md file for the team leader: tl_$0.md.md file per specialist: specialist_<name>.mdVerify the team loads correctly:
source .venv/bin/activate
python3 -c "
import sys, os; sys.path.insert(0, '.')
os.environ['ANTHROPIC_API_KEY'] = 'test-key'
from src.llm.client import AnthropicClient
from src.prompts.loader import PromptLoader
from src.teams.registry import TeamRegistry
client = AnthropicClient()
loader = PromptLoader()
registry = TeamRegistry(client, loader)
teams = registry.load_all()
for t in teams.values():
print(t)
"
Wire into hierarchy if it belongs to a new department:
main.py:build_swarm()Update CLAUDE.md with the new team's purpose and any conventions.
competitive_intel)prompt_file field in the YAML exactly (without .md)After completion, run /swarm-status to verify the new team loads correctly. Update CLAUDE.md with the new team.
npx claudepluginhub drcharleskamen-png/superpowers --plugin superpowers-extended-ccCreates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.