Executing Plans
Follow and execute pre-defined action steps with precision and professionalism.
SKILL.md Definition
Executing Plans
Overview
Load plan, review critically, execute tasks in batches, report for review between batches.
Core principle: Batch execution with checkpoints for architect review.
Announce at start: "I'm using the executing-plans skill to implement this plan."
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 Batch
Default: First 3 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: Report
When batch complete:
- Show what was implemented
- Show verification output
- Say: "Ready for feedback."
Step 4: Continue
Based on feedback:
- Apply changes if needed
- Execute next batch
- Repeat until complete
Step 5: 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 mid-batch (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
- Between batches: just report and wait
- Stop when blocked, don't guess
About Superpowers
Superpowers is a complete software development workflow for your coding agents, built on top of a set of composable "skills".
Philosophy
- Test-Driven Development - Write tests first, always
- Systematic over ad-hoc - Process over guessing
- Complexity reduction - Simplicity as primary goal
- Evidence over claims - Verify before declaring success
Installation
Note: Installation differs by platform. Claude Code has a built-in plugin system. Codex and OpenCode require manual setup.
Claude Code (via Plugin Marketplace)
In Claude Code, register the marketplace first:
/plugin marketplace add obra/superpowers-marketplace
Then install the plugin from this marketplace:
/plugin install superpowers@superpowers-marketplace
Verify Installation
Check that commands appear:
/help
# Should see:
# /superpowers:brainstorm - Interactive design refinement
# /superpowers:write-plan - Create implementation plan
# /superpowers:execute-plan - Execute plan in batches
Links & Support
- Repository: https://github.com/obra/superpowers
- Issues: https://github.com/obra/superpowers/issues
Featured Skills
"Find the perfect 'agent skills' for your project"
ZINC Database
Curated database of commercial compounds for virtual screening.
Zarr Python
Python implementation of chunked, compressed, N-dimensional arrays for scientific data.
USPTO Database
Access to the United States Patent and Trademark Office database.
UniProt Database
Comprehensive, high-quality, and free resource for protein sequences and functional information.
Powerful Agent Skills
Boost your AI performance with our professional skill collection.
Ready to Use
Copy and paste into any agent system supporting skills.
Modular Design
Mix and match 'code skills' to create complex agent behaviors.
Optimized
Each 'agent skill' is tuned for high performance and accuracy.
Open Source
All 'code skills' are open for contributions and customization.
Cross-Platform
Works with various LLMs and agent frameworks.
Safe & Secure
Vetted skills that follow best practices for AI safety.
How it Works
Get started with agent skills in three simple steps.
Pick a Skill
Find the skill you need from our collection.
Read Docs
Understand how the skill works and its constraints.
Copy & Use
Paste the definition into your agent's config.
Test
Verify the results and refine as needed.
Deploy
Launch your specialized AI agent.
What Developers Say
See why developers worldwide choose Agiskills.
Alex Smith
AI Engineer
"Agiskills has completely changed how I build AI agents."
Maria Garcia
Product Manager
"The PDF Specialist skill solved complex document parsing issues for us."
John Doe
Developer
"Professional and well-documented skills. Highly recommend!"
Sarah Lee
Artist
"The Algorithmic Art skill produces incredibly beautiful code."
Chen Wei
Frontend Specialist
"Themes generated by Theme Factory are pixel-perfect."
Robert T.
CTO
"We now use Agiskills as the standard for our AI team."
FAQ
Everything you need to know about Agiskills.
Yes, all public skills are free to copy and use.