skills/tools/agent-teams/SKILL.md
Pre-composed agent team library. Use when the user asks which teams are available, what a team does, when to pick one team over another, or to browse multi-agent compositions. Catalogs ready-to-run teams (development team, review squad, war room) with their purpose, agent roster, workflow type, and when to use each. The actual dispatching is handled by the dispatching-agent-teams skill.
npx skillsauth add krzysztofsurdy/code-virtuoso agent-teamsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
A catalog of pre-composed agent teams. Each team bundles a roster of agents, a coordination workflow, and entry/exit criteria into a ready-to-use unit. Pick a team and dispatch it via the dispatching-agent-teams skill.
| Team | Workflow | Lead | Use when | |---|---|---|---| | development-team | hybrid | Product Manager | Delivering a full feature from requirements to merged PR | | review-squad | parallel | Reviewer | Multi-perspective code review before merging significant changes | | war-room | war-room | Architect | Structured technical debate that ends in a decision (architecture choice, tech selection, design trade-off) |
| Situation | Recommended Team |
|---|---|
| "I need to ship feature X end-to-end" | development-team |
| "Code review this PR thoroughly" | review-squad |
| "We need to decide between X and Y" | war-room |
| "Just review the diff" | Skip the team, delegate to reviewer agent directly |
| "Investigate this area" | Skip the team, delegate to investigator agent directly |
If no team fits the work, skip the team and chain individual agents (see the using-ecosystem skill's chaining patterns).
Every team file follows the team specification (spec/team-spec.md):
name, description, lead, agents, skills, workflowThe dispatcher reads these fields to resolve the team, verify entry criteria, and execute the workflow in the appropriate spawning mode.
User-authored teams live at the project root in teams/{name}.md. The dispatcher discovers project teams before falling back to the bundled library here, so project teams can override bundled ones by name.
See spec/team-spec.md for the full team format and template/team-template.md for a starter.
| Situation | Recommended Skill |
|---|---|
| Run a team you picked from this catalog | dispatching-agent-teams |
| Discover what agents and skills are available | using-ecosystem |
| Decide between teams and ad-hoc agent chaining | using-ecosystem |
| Author a new team definition | spec/team-spec.md and template/team-template.md |
development
Spawn and coordinate a pre-composed agent team from a team definition file. Reads team files from teams/, resolves agents and skills, picks the best spawning mode (peer or sequential), and runs the workflow. Use when the user asks to run a team, dispatch a development team, start a feature delivery, or coordinate multiple agents for a multi-phase task.
tools
Ecosystem discovery advisor. Use when the user asks 'what skill should I use', 'what agent should I delegate to', 'which team fits this task', or when onboarding to available skills, agents, and teams. Scans ALL installed skills at runtime -- not limited to any single plugin or vendor. Triggers: 'which skill', 'which agent', 'what do I use for', 'orient me', 'what tools do I have'.
tools
Interactive tool to scaffold a complete Claude Code plugin -- plugin.json manifest, skills, agents, hooks, MCP servers, LSP servers, and an optional marketplace.json catalog entry. Use when the user asks to create a plugin, build a Claude Code plugin, scaffold a plugin marketplace, convert an existing .claude/ configuration into a plugin, or package skills and agents for distribution. Runs a guided questionnaire, writes all required files to disk, and prints test instructions.
development
Interactive pre-implementation design exploration. Use when the user has a vague idea, feature request, or problem statement but no written spec. Asks focused questions one at a time to surface goals, non-goals, constraints, success criteria, and risks, then produces a written spec and hard-gates implementation until approved. Use before writing any code, before planning, and before answering 'how should I build X'. Triggers: 'I want to build', 'I'm thinking about', 'help me figure out', 'let's brainstorm', 'help me spec out'.