Claude Skills by vibhasdutta

Domain-agnostic autonomous loop for any goal — coding, research, content, data, automation, or any objective. Asks 3 questions, then orchestrates a self-assembling agent team (resource-scout, researcher, planner, agent-factory, executor, verifier, auditor, memory-keeper) that researches, discovers resources, builds specialized agents for the goal, executes, and iterates until done. Modes: build (from scratch), research (investigate only), patch (fix/extend existing code), audit (review only, ...

Loop engineering wizard for Antigravity. Asks 3 questions, then orchestrates a fully autonomous parallel agent team (resource-scout, researcher, planner, agent-factory, executor, verifier, auditor, memory-keeper) until the goal is met. Uses invoke_subagent for true parallel dispatch. Researcher agents use the built-in research TypeName. Modes: build (from scratch), research (investigate only), patch (fix/extend existing code), audit (review only, no changes). Persistent memory, git integration.

Domain-agnostic autonomous loop for any goal — coding, research, content, data, automation, or any objective. Asks 3 questions, then orchestrates a self-assembling agent team (resource-scout, researcher, planner, agent-factory, executor, verifier, auditor, memory-keeper) that researches, discovers resources, builds specialized agents for the goal, executes, and iterates until done. Modes: build (from scratch), research (investigate only), patch (fix/extend existing code), audit (review only, ...

Domain-agnostic autonomous loop for OpenAI Codex CLI. Asks 3 questions, scaffolds a parallel agent team as TOML files (resource-scout, researcher, planner, agent-factory, executor, verifier, auditor, memory-keeper), generates loop-stack/<LOOP_ID>/ state files, and outputs the exact `codex /goal` command for the fully autonomous loop. Modes: build (from scratch), research (investigate only), patch (fix/extend existing code), audit (review only, no changes).

Domain-agnostic autonomous loop wizard for VS Code GitHub Copilot. Asks 3 questions, then orchestrates a fully autonomous agent team via true parallel subagent dispatch. Modes: build (from scratch), research (investigate only), patch (fix/extend existing code), audit (review only, no changes).

Loop engineering wizard for Cursor. Asks 3 questions, then orchestrates a fully autonomous parallel agent team (resource-scout, researcher, planner, agent-factory, executor, verifier, auditor, memory-keeper) for any goal. Multiple agents run in parallel — dynamic researcher count, multiple executors on independent parts simultaneously. Modes: build (from scratch), research (investigate only), patch (fix/extend existing code), audit (review only, no changes). Persistent memory, git integration.

Loop engineering wizard for Gemini CLI. Asks 3 questions, then orchestrates a fully autonomous agent team (resource-scout, researcher, planner, agent-factory, executor, verifier, auditor, memory-keeper) until the goal is met. Each agent is a named tool. On Gemini CLI v0.36+, subagents run in true parallel (spawn multiple in one turn); on older versions, invoke one at a time. Dynamic researcher count. Modes: build (from scratch), research (investigate only), patch (fix/extend existing code), a...

Loop engineering wizard for Hermes Agent. Asks 3 questions, then orchestrates a fully autonomous parallel agent team (resource-scout, researcher, planner, agent-factory, executor, verifier, auditor, memory-keeper) for any goal. Uses delegate_task for true parallel subagent dispatch. Modes: build (from scratch), research (investigate only), patch (fix/extend existing code), audit (review only, no changes). Persistent memory, git integration. Activate with /loop-engineer.

Loop engineering wizard for OpenCode. Asks 3 questions, then orchestrates a fully autonomous agent team (resource-scout, researcher, planner, agent-factory, executor, verifier, auditor, memory-keeper) until the goal is met. Agents run sequentially via the task tool. Dynamic researcher count. Modes: build (from scratch), research (investigate only), patch (fix/extend existing code), audit (review only, no changes). Persistent memory, git integration.