ruflo-ai-team
claudeTenant-isolated AI teams that plan work, coordinate tasks, recall approved context, and return evidence-backed results
6 skills · 6 commands · 4 agents · 1 MCP server
The product is a verified problem contract (problem + model-checkable done_when); direct execution by default, deterministic machinery forging when the contract earns it
Plugin team-forge from marketplace team-forge-dev in shirleyfuxw/team-forge. Commands read from the repo's manifest — 26 days ago.
team-forge:designUse ONLY when a contract (team-forge:goal) chose `route: machinery` — the machinery-design phase. Absorbs the machinery interrogation (archetype, roster, tracking, budget), then multiple forge-design-agents propose roster + skill discoveries + tracking spec in parallel; their reciprocal review catch
team-forge:evolveUse when a run has finished producing evidence and something should be learned from it — a forged run reaching Close, a recurring workflow closing a cycle, someone asking what a run taught us or for a retro / post-mortem / process-improvement write-up, and always just before team-forge:teardown arch
team-forge:goalUse at the START of any non-trivial piece of work whose real problem or finish line is not yet pinned down — "our flaky tests keep blocking releases", "clean up the duplicate helpers", "make onboarding not take a week" — and again whenever scope shifts mid-project. Interrogates the problem behind th
team-forge:runThe shared runtime for every forged team/workflow — load it whenever driving a forged team's work loop, whether a team's thin entry skill (/<team>-workflow or /<team>-team) sent you here or you are resuming one mid-flight. Adopt the lead role and drive the loop — sequential-gated, parallel-drain, or
team-forge:teardownUse when a forged team or workflow is DONE and you want to retire it cleanly. "Complete" is not "cleaned up": this archives the ledger, prunes worktrees, removes the launcher skill + its trigger, and classifies every forged file as durable (keep) or ephemeral (remove). Invoke after the final go/no-g
Tenant-isolated AI teams that plan work, coordinate tasks, recall approved context, and return evidence-backed results
6 skills · 6 commands · 4 agents · 1 MCP server
Write accurate Pydantic AI code from the start. Up-to-date patterns, decision trees, and common gotchas for agents, tools, structured output, streaming, and multi-agent apps.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
6 skills · 7 commands · 4 agents
Claude Code native multi-agent orchestration with intelligent model routing across agents and skills. Zero learning curve. Maximum power.
85 skills · 20 commands · 19 agents · 1 MCP server · hooks
Multi-agent collaboration — spawn N parallel subagents that compete on code optimization, content drafts, research approaches, or any task that benefits from diverse solutions. 7 slash commands (/hub-init, /agenthub:spawn, /hub-status, /agenthub:eval, /agenthub:merge, /agenthub:board, /hub-run), agent templates, DAG-based orchestration, LLM judge mode, message board coordination.
8 skills · 1 agent · hooks
Agent coordination and meta-programming - multi-agent orchestration, workflow automation, and safe refactor governance. Works best with other voltagent plugins installed.
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.