SPF Exec Plan

Use when you have a written implementation plan to execute in a separate session with review checkpoints

This skill appears to be what it says (execute a written plan) but before installing, be aware: it will read and modify project files (task_plan.md, active_tdd_plan.md, findings.md, progress.md and .superpower-with-files/*), and it mandates appending timestamps and creating/updating handoff.md. It also requires or will attempt to spawn sub-agents for parallel tasks and will call other 'superpowers' (e.g., finishing-a-development-branch). Ask the maintainer to clarify the inconsistent guidance around git worktrees (it both 'requires' using worktrees and says 'No dedicated worktree required'), and confirm: where exactly will it write files, whether it will ever run actions without explicit approval (especially branch operations), and what happens if the platform doesn't support sub-agents. If you allow this skill, back up your repository, ensure you’re comfortable with automated edits to the listed files, and restrict it from running on main/master branches unless you explicitly authorize that behavior.

Type: OpenClaw Skill Name: spf-exec-plan Version: 1.0.0 The skill bundle defines a structured workflow for an AI agent to execute multi-step implementation plans in batches with checkpoints. It focuses on state management using local markdown files (e.g., `active_tdd_plan.md`, `progress.md`) and integrates with other workflow skills like git worktrees, without any evidence of data exfiltration, malicious execution, or unauthorized access.