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: This skill is for environments without subagent support. If subagents are available, use superpowers:subagent-driven-development instead — it provides higher quality through fresh-context-per-task and two-stage review.
The Process
Step 1: Load and Review Plan
- Ensure an isolated workspace: use superpowers:using-git-worktrees to create one or verify the existing one
- Read plan file
- Review critically - identify any questions or concerns about the plan
- If concerns: Raise them with the user before starting
- If no concerns: Create task.md artifact (using
write_to_filewithIsArtifact: trueand the task type inArtifactMetadata) 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:
Generate walkthrough artifact: Create a
walkthrough.mdartifact (usingwrite_to_filewithIsArtifact: true, with the walkthrough type andRequestFeedback: trueinArtifactMetadata) summarizing:- What was implemented (list of changes per component)
- What was tested and results
- Embed any relevant screenshots or recordings
- Use file links to point to key changed files
Finish the branch:
- Announce: "I'm using the finishing-a-development-branch skill to complete this work."
- REQUIRED SUB-SKILL: Use superpowers:finishing-a-development-branch
- Follow that skill to verify tests, present options, execute choice
When to Stop and Ask for Help
STOP executing immediately when:
- Hit a blocker (missing dependency, test fails, instruction unclear)
- Plan has critical gaps preventing starting
- You don't understand an instruction
- Verification fails repeatedly
Ask for clarification rather than guessing.
When to Revisit Earlier Steps
Return to Review (Step 1) when:
- User updates the plan based on your feedback
- Fundamental approach needs rethinking
Don't force through blockers - stop and ask.
Remember
- Review plan critically first
- Follow plan steps exactly
- Don't skip verifications
- Reference skills when plan says to
- Stop when blocked, don't guess
- Never start implementation on main/master branch without explicit user consent