Coordinate multiple AI agents for feature development or refactoring across several files. The skill guides team setup, task assignment, status checks, and recording successful approaches for use in later work.
Multi-agent swarm coordination for complex tasks. Use when: 3+ files need changes, new features, refactoring. Skip when: single file edits, simple fixes, documentation.
This skill coordinates multiple AI agents for development work that spans several files. It uses @claude-flow/cli to initialize a group of agents, route tasks to suitable agents, and check the group's current status. The initialization example specifies a hierarchical structure, with a chain of coordination and a maximum of eight agents.
Use it when a task requires changes to three or more files, when developing a new feature, or when refactoring the structure of existing code. It also describes a working process that starts by checking saved knowledge for existing patterns. After the work is complete, successful patterns and newly learned information are recorded for later use. This makes both coordination during the task and recording what worked part of the process.
The listed commands use npx @claude-flow/cli. Single-file edits, simple fixes, and documentation work are explicitly excluded from this skill's intended scope.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.
The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 21, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Multi-agent swarm coordination for complex tasks.
Start a new swarm with hierarchical topology
npx @claude-flow/cli swarm init --topology hierarchical --max-agents 8
Route a task to the appropriate agents
npx @claude-flow/cli hooks route --task "[task description]"
Check the current swarm status
npx @claude-flow/cli swarm status
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Compare models available through the HuggingFace router with chat-ui configuration, research missing models, and write short English descriptions of their architecture and capabilities. Add entries to both production and development configuration files and commit the changes.
Create an Architecture Decision Record, a document for recording important design choices, with the next sequential number. It generates a Markdown template, registers the record in AgentDB, and links related decisions found through search.
Build a searchable index and relationship graph from ADRs, records of architectural decisions. Import two supported document formats, refresh existing metadata without duplicate relationships, and review summaries of statuses, missing references, and inconsistencies.
Rebuild the index of ADRs, records of architectural decisions, after files or relationship lines are deleted. It clears stored records and relationships, indexes the files still present, and checks that the final record count matches.
Review code changes against accepted Architecture Decision Records, documents that capture agreed design choices. Report violations, outdated references, compliant changes, and areas without ADR coverage, then suggest code fixes or a new decision record where appropriate.
Check saved architecture decision records (ADRs) for broken references, circular replacement relationships, and inconsistent statuses. Use the results to verify imported records or stop a CI check when selected integrity rules fail.