skills.rest
RebelliousSmile
RebelliousSmileCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

behave

Manage behavioral test suites for Claude skills with dry-run judging.

1|Updated Mar 3, 2026
Search Tags:#quality assurance#Python#regression testing#Claude skill#behavioral testing
One-click install
npx skills add https://github.com/RebelliousSmile/my-claude-marketplace --skill behave-rebellioussmile
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: behave
Source: https://github.com/RebelliousSmile/my-claude-marketplace/tree/main/plugins/overcode/skills/behave
Command: npx skills add https://github.com/RebelliousSmile/my-claude-marketplace --skill behave-rebellioussmile

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python, behave, checklists, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill addresses the challenge of managing and auditing behavioral tests for Claude skills, ensuring reliable functionality and quality in prompts-driven workflows.

Core Features & Use Cases

  • Behavioral Test Management: Scaffold, execute, and review scenario suites for Claude skills.
  • Dry-Run Judge Harness: Scores each scenario against a populated fixture without affecting real data.
  • Regression Testing: Re-run suites post-change to detect any regressions in behavior.
  • Quality Review: Audit suite coverage and scenario quality using a 7-axis grid.
  • Use Case: When you have a Claude skill that handles user data, use this Skill to create and maintain behavioral tests that ensure the skill behaves as expected.

Quick Start

To scaffold a new behavioral test for a skill, run: /behave scaffold <path-to-skill-file>

Frequently Asked Questions about behave

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I manage behavioral tests for Claude skills to ensure prompt reliability?▼

Scaffold, execute, and review behavioral test scenario suites using a dry-run judge harness. This framework scores scenarios against populated fixtures to verify prompt-driven workflow functionality without affecting real data.

Can I run regression testing on Claude skills after making prompt changes?▼

Run regression testing by re-executing behavioral test suites post-change to detect any regressions in skill behavior. This validates that modifications do not break existing prompt-driven functionality.

Do I need Python to execute behavioral tests and check Claude skill data integrity?▼

Python is required to execute behavioral tests and perform data integrity checks. You must have the Python environment along with the specific behave library installed to run the evaluation framework.

What is the best way to audit behavioral test coverage and scenario quality?▼

Audit behavioral test coverage and scenario quality using a 7-axis grid review system. This quality review process evaluates the comprehensiveness and effectiveness of your scenario suites.

Does the dry-run judge harness affect real user data during behavioral testing?▼

The dry-run judge harness scores each scenario against a populated fixture without affecting real data. This allows safe behavioral testing and evaluation of Claude skills in an isolated environment.

Related Skills

Explore More Software Engineering Skills→
aviz85aviz85
45

aviz-skills-installer

Install and manage Claude Code skills from the AVIZ Skills Library.

Community
Intermediate
Sheldon-92Sheldon-92
3

Testing

Execute test suites and report failures with coverage metrics.

Community
Intermediate
peshaypeshay
1

bmad-tea

Provide guidelines for risk-based testing, fixture design, and CI/CD governance.

Community
Advanced
xlelibertyxleliberty

api-test-suite-builder

Scan API route definitions to generate test suites for Node.js and Python frameworks.

Community
Advanced