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 Superpowers works much better with access to subagents (Claude Code, Codex CLI, Codex App, Copilot CLI, and Gemini CLI all qualify; see the per-platform tool refs in ../using-superpowers/references/). If subagents are available, use superpowers:subagent-driven-development instead of this skill.

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 your human partner before starting
If no concerns: Create todos for the plan items 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:

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:

Partner 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

Files1

1 files · 1.0 KB

Select a file to preview

Overall Score

72/100

Grade

B

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

82

Quality

68

Clarity

78

Completeness

60

Summary

This skill guides an AI agent to execute a pre-written implementation plan across a development session with built-in review checkpoints and safeguards. It emphasizes critical plan review before execution, task-by-task progress tracking, and delegation to sub-skills for specialized phases (git worktrees, branch completion). The skill explicitly forbids execution on main/master branches without user consent and includes clear stop conditions for blockers.

Detected Capabilities

plan file readingtask progress tracking (todo management)critical review before executiondelegation to sub-skillsworkspace verificationgit worktree management

Trigger Keywords

Phrases that agents use to match this skill to user intent.

execute implementation planapply prepared planmulti-step developmentplan with checkpointsexecute plan tasks

Use Cases

Execute a detailed multi-step development plan with checkpoints
Apply a code plan prepared in a separate session or by another agent
Safely implement complex features with verification between tasks
Coordinate execution of plans that reference other sub-skills
Implement plans while maintaining safety guardrails and avoiding direct main branch changes

Quality Notes

Skill correctly delegates dangerous operations (git worktree setup, branch completion) to specialized sub-skills rather than handling them inline
Clear stop conditions and blocker-handling guidance prevent forced execution through errors
Explicitly forbids main/master branch execution without user consent, a strong safety guardrail
Calls out that subagents are preferred, guiding users toward better options when available
Instructions are concise and follow a logical three-step process with clear decision points
Announcement requirement ('I'm using the executing-plans skill') aids transparency and auditability
Skill assumes plan file format and structure without documenting expected plan schema or fields
No guidance on plan validation or syntax checking — relies entirely on human-written plan quality
Missing documentation on how to handle partial failures or resume interrupted execution
Task state management (todos) is mentioned but not fully specified — unclear if agent should create files, use tool calls, or follow implied format

Model: claude-haiku-4-5-20251001Analyzed: Sep 9, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

v1.2
Content updated
✦ AIAdds isolated workspace setup via git-worktrees in Step 1, removes Integration section, condenses subagent recommendation.
2026-09-09
LATEST
v1.1
Content updated
✦ AIClarifies platform support for subagents (adds CLI variants), changes step 4 instruction from TodoWrite to generic todos, and softens git-worktrees requirement language.
2026-06-28
View This Version
v1.0
2026-05-02
View This VersionInitial version

executing-plans