Executes complex development plans step-by-step with integrated verification and review stages.
Install
mkdir -p .claude/skills/executing-plans && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/581" && unzip -o skill.zip -d .claude/skills/executing-plans && rm skill.zipInstalls to .claude/skills/executing-plans
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use when you have a written implementation plan to execute in a separate session with review checkpointsKey capabilities
- →Load and review implementation plans
- →Execute tasks sequentially with verification
- →Pause for human review on blockers
- →Integrate with git worktrees
- →Complete development branches
How it works
The skill loads a plan, creates todos for each step, and enforces strict verification before marking tasks as complete. It requires human intervention if blockers arise or if the plan needs fundamental rethinking.
Inputs & outputs
When to use executing-plans
- →Execute a multi-stage refactoring plan
- →Implement a new feature from a detailed design
- →Perform a series of bug fixes sequentially
- →Manage complex codebase migrations
About this skill
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
When not to use it
- →When subagent-driven development is available
- →Starting implementation on main branch without consent
Prerequisites
Limitations
- →Requires human review for blockers
- →Cannot proceed if verification fails
How it compares
It enforces a structured, step-by-step execution with mandatory verification checkpoints rather than free-form coding.
Compared to similar skills
executing-plans side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| executing-plans (this skill) | 6 | 3mo | No flags | Intermediate |
| rein-go | 0 | 3mo | Review | Advanced |
| long-task-workflow | 0 | 26d | No flags | Advanced |
| trello | 41 | 2mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by obra
View all by obra →You might also like
rein-go
jstxn
Run one task through the full REIN flow from clarification through implementation, cleanup, review, and verification
long-task-workflow
Seven128
Prepare, execute, resume, verify, or close a Single-Goal Delivery Contract, logical Contract Bundle, or Delivery Set in the current platform-native Goal and workspace. Use only when explicitly invoked or an active ty-context long-task authority exists.
trello
openclaw
Manage Trello boards, lists, and cards via the Trello REST API.
spec-workflow
TencentCloudBase
Standard software engineering workflow for requirement analysis, technical design, and task planning. Use this skill when developing new features, complex architecture designs, multi-module integrations, or projects involving database/UI design.
feature-design-assistant
davila7
Turn ideas into fully formed designs and specs through natural collaborative dialogue. Use when planning new features, designing architecture, or making significant changes to the codebase.
github-project-management
ruvnet
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning