Coordinates agent teams across projects with CLI-based configuration, syncing, and history tracking.
Install
mkdir -p .claude/skills/team-epicsagas && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16398" && unzip -o skill.zip -d .claude/skills/team-epicsagas && rm skill.zipInstalls to .claude/skills/team-epicsagas
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Org-level agent team designer via `epic team` CLI (cross-project, append-merge). Subcommands: list, show, sync, link, unlink, history. Use when setting up agents, designing teams, or /spec yields 3+ requirements.Key capabilities
- →Design agent teams for organizational use
- →List available agent teams in an organization
- →Show configuration, agents, and mission of a team
- →Sync agent configurations across projects
- →Link or unlink existing agent teams
How it works
The skill wraps the `epic team` CLI, which interactively resolves organizational context, scans projects, recommends team compositions, and manages agent configurations.
Inputs & outputs
When to use team
- →Listing available agent teams
- →Syncing agent configs across projects
- →Linking or unlinking team members
- →Viewing agent team history
About this skill
/team — Agent Team Design
This skill is a thin wrapper around the epic team CLI.
Run in terminal:
epic team
epic team handles the full interactive flow:
- Resolves org (
HARNESS_ORGenv → prompt → default"epic") - Scans the project (tech stack, domain boundaries, key modules)
- Recommends team type and agent composition
- Shows diff if team already exists in
~/.harness/orgs/ - Applies merge strategy (no silent overwrites)
- Copies agents to
.claude/agents/{team}/with## Team Contextinjected
For the full spec see docs/research/team-spec.md.
Other subcommands
epic team list # list teams in current org
epic team show {team} # config + agents + mission
epic team show {team} --playbook # full accumulated playbook
epic team sync {team} # re-copy agents to .claude/agents/
epic team link {team} # attach existing team (skip design)
epic team unlink {team} # remove .claude/agents/{team}/
epic team history {team} {agent} # show .history/ entries
When not to use it
- →When not setting up agents or designing teams
- →When the task does not involve `epic team` CLI
- →When the task does not require cross-project agent management
Limitations
- →Requires the `epic team` CLI to be available.
- →Relies on `HARNESS_ORG` environment variable or user prompt for organization context.
- →Applies an append-merge strategy, not silent overwrites.
How it compares
This skill automates the design and management of agent teams across projects with a structured CLI, preventing silent overwrites and ensuring consistent configurations.
Compared to similar skills
team side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| team (this skill) | 0 | 1mo | No flags | Intermediate |
| planning-with-files | 233 | 6mo | Review | Intermediate |
| ralph-plan | 14 | 6mo | No flags | Beginner |
| agent-planner | 3 | 6mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by epicsagas
View all by epicsagas →You might also like
planning-with-files
davila7
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
ralph-plan
mastra-ai
Interactive planning assistant that helps create focused, well-structured ralph-loop commands through collaborative conversation
agent-planner
ruvnet
Agent skill for planner - invoke with $agent-planner
llm-council
am-will
Orchestrate a configurable, multi-member CLI planning council (Codex, Claude Code, Gemini, OpenCode, or custom) to produce independent implementation plans, anonymize and randomize them, then judge and merge into one final plan. Use when you need a robust, bias-resistant planning workflow, structured JSON outputs, retries, and failure handling across multiple CLI agents.
agent-queen-coordinator
ruvnet
Agent skill for queen-coordinator - invoke with $agent-queen-coordinator
swarm-planner
am-will
[EXPLICIT INVOCATION ONLY] Creates dependency-aware implementation plans optimized for parallel multi-agent execution.