Longwave

Verification before completion skill

Verification before completion is part of Superpowers, Jesse Vincent's development method. Its job is to run the checks and read their output before claiming anything is fixed or done. It loads on its own when a request matches its description, and you can also call it by name.

Add to Longwave

Source

When the agent reaches for it

The agent keeps every installed skill's description in view and loads the full instructions when a request matches. This is the description it reads:

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

What the instructions cover

The sections of its SKILL.md, in order.

Overview
The Iron Law
The Gate Function
Common Failures
Red Flags - STOP
Rationalization Prevention
Key Patterns
When To Apply

Install the verification before completion skill

In Claude Code, run this in a session. It comes from the publisher's own instructions.

Claude Code

/plugin install superpowers@claude-plugins-official

License: MIT.

In Longwave, add Superpowers from the marketplace. It installs all 14 of its skills, and your Claude Code, Codex and OpenCode threads can use them.

Questions people ask

How do I install the verification before completion skill?

In Claude Code, run /plugin install superpowers@claude-plugins-official. In Longwave, add Superpowers from the marketplace, and its skills reach your Claude Code, Codex and OpenCode threads.

When does the agent use the verification before completion skill?

When a request matches its description. The agent keeps only the name and description of each installed skill in view, and reads the full instructions when a task fits. You can also ask for it by name.

Use your skills in every harness.

Longwave installs a skill collection once, and your Claude Code, Codex and OpenCode threads can all use it.

Download Longwave