Orchestrates parallel implementation and review cycles using Agent Teams.

Install

mkdir -p .claude/skills/team-execute && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18214" && unzip -o skill.zip -d .claude/skills/team-execute && rm skill.zip

Installs to .claude/skills/team-execute

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.

Two-phase Agent Teams execution — replaces the old /team-implement and /team-review skills. Phase 1 IMPLEMENT (formerly /team-implement): parallel implementation with teammates per module/layer, file-ownership separation, and a shared task list with dependencies. Run after /feature plan approval. Phase 2 REVIEW (formerly /team-review): specialized reviewers (security, quality, test coverage) review the changes from different perspectives in parallel. Pass --review-only to skip Phase 1 and review existing changes (after manual or Codex implementation).
557 charsno explicit “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Advanced

Key capabilities

  • Execute a feature plan in two phases: implement and review
  • Spawn agent teams for parallel implementation based on modules or layers
  • Coordinate and monitor implementation progress
  • Conduct parallel reviews by specialized agents (security, quality, test coverage)
  • Synthesize review findings and report to the user

How it works

The skill orchestrates a two-phase process: first, it spawns agent teams for parallel implementation, and then it spawns specialized reviewers for parallel code review. It uses project context and design documents to guide the agents.

Inputs & outputs

You give it
Approved feature plan and architectural documentation
You get back
Implemented code and a review report

When to use team-execute

  • Execute approved feature plan
  • Run parallel code reviews
  • Implement complex multi-module features

About team-execute

Manages a two-phase execution flow: a parallel implementation phase for features, followed by a specialized parallel review phase covering security, quality, and tests. Ensures code matches architectural designs documented in project metadata.

|

When not to use it

  • When a feature plan has not been approved by the user
  • When implementation is not complete and all tests are not passing for Phase 2
  • When the user wants to implement manually without a review

Prerequisites

The /feature skill is complete and the plan has been approved by the userArchitecture is documented in .claude/docs/DESIGN.mdA task list has been createdImplementation is complete and all tests are passing for Phase 2

Limitations

  • Requires an approved plan from the /feature skill
  • Relies on architecture documented in .claude/docs/DESIGN.md
  • Requires implementation to be complete and tests passing for the review phase

How it compares

This skill automates and structures the implementation and review process into parallel agent teams, which differs from a single agent or manual workflow.

Compared to similar skills

team-execute side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
team-execute (this skill)017dReviewAdvanced
setup04moReviewBeginner
shellcheck-configuration92moNo flagsIntermediate
wolf-scripts-core58moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry