Execute Plan

Overview

This skill executes a research plan phase by phase. It starts by invoking academic-baseline as the standing policy layer, dispatches subagents for independent tasks, invokes replication-driven-research as a guardrail, and runs two-stage review at phase boundaries: correctness first, reproducibility second. It must honor each task's declared Skills involved field during execution rather than improvising generic behavior. Stops and asks the user at any scaffolding or destructive action. The skill never proceeds past a phase until both reviews pass.

When to Use

• A plan exists in docs/superpapers/plans/
• User says "execute the plan", "run the plan", or "let's start implementing"
• Transitioning from write-plan to implementation
• Resuming execution of a partially-completed plan

Prerequisites

• An approved plan in docs/superpapers/plans/YYYY-MM-DD-<topic>-plan.md
• User has explicitly confirmed they want to proceed to execution
• replication-driven-research has been invoked at least once in this project (to scaffold directories) or will be invoked as the first step

Mandatory Steps

1. Invoke academic-baseline first. This resolves CLAUDE.superpapers.md via the walk-up Read (current working directory, then parent directories) and carries its settings into the session. Keep academic-baseline active through every phase.

2. Load and parse the plan. Read the plan file in full. Extract tasks, phases, dependencies, verification criteria, and Skills involved.

3. Invoke replication-driven-research to ensure project structure. If directories are missing, propose scaffolding. Wait for user confirmation before creating directories or files at the project root.