| name | executing-plans |
| description | Use when you have a written implementation plan to execute in a separate session with review checkpoints |
Ported here, and some of what it names is not. This skill comes from upstream, where it
sits beside sibling skills this port does not vendor. Any superpowers:<name> or
elements-of-style:<name> reference below that does not match a skill you actually have is
not available here — do not try to invoke it. Where one is named as a required step, do
the work it describes directly instead, or use the closest skill that is installed. Run
ls ~/.claude/skills to see what you have.
Executing Plans
Overview
Load plan, review critically, execute all tasks, report when complete.
Announce at start: "I'm using the executing-plans skill to implement this plan."
Note: Tell your human partner that plan execution works much better with access to subagents. The quality of its work will be significantly higher if run on a platform with subagent support (such as Claude Code). If subagents are available, dispatch each task to a fresh subagent via the Agent tool instead of executing tasks inline in this session.
The Process
Step 1: Load and Review Plan
- Read plan file
- Review critically - identify any questions or concerns about the plan
- If concerns: Raise them with your human partner before starting
- If no concerns: Create TodoWrite and proceed
Step 2: Execute Tasks
For each task:
- Mark as in_progress
- Follow each step exactly (plan has bite-sized steps)
- Run verifications as specified
- Mark as completed
Step 3: Complete Development
After all tasks complete and verified:
- Verify the implementation: run typecheck, lint, and all tests
