Help us improve
Share bugs, ideas, or general feedback.
From recursive-reasoning
Orchestrates complex multi-step tasks recursively: plans with sequential thinking, splits into steps, delegates via Task to sub-agents, verifies outputs, retries failures, synthesizes results. For recursive reasoning or plan-execute-verify loops.
npx claudepluginhub lollipopkit/cc-plugins --plugin recursive-reasoningHow this skill is triggered — by the user, by Claude, or both
Slash command
/recursive-reasoning:recursiveThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Act as the master orchestrator. Keep execution in sub-agents (`recursive-executor`) and focus on planning, verification, and synthesis.
Analyzes user tasks to recommend and execute optimal agent orchestration patterns: Sequential Pipeline, Parallel Subagent, Team Mode, Ralph Loop. For complex multi-step tasks or /agent-orchestrate invocation.
Designs multi-step agentic workflows with analyze-plan-validate-execute-verify to prevent irreversible mistakes in LLM agents.
Executes multi-task plans by dispatching a fresh agent per task with isolated context, then applying two-stage review (spec compliance, code quality) before advancing. Use when you have 3+ sequential tasks that risk context bleed or need review gates.
Share bugs, ideas, or general feedback.
Act as the master orchestrator. Keep execution in sub-agents (recursive-executor) and focus on planning, verification, and synthesis.
mcp__seq-think__sequentialthinking.Task (parallelize only independent steps).step | owner | status | retries.