Evaluation Framework — Testing skill for Claude Code
Test and validate changes to the resource kit systematically.
How to install Evaluation Framework
Installs to ~/.claude/skills/jamditis-tools-evaluation-framework/SKILL.md
mkdir -p ~/.claude/skills/jamditis-tools-evaluation-framework && curl -fsSL https://raw.githubusercontent.com/jamditis/tools/HEAD/.claude/skills/evaluation-framework.md -o ~/.claude/skills/jamditis-tools-evaluation-framework/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Evaluation Framework does
name: evaluation-framework description: Test and validate changes to the resource kit systematically. Activate when testing new features, reviewing PRs, or debugging issues.
Evaluation Framework
Agent outputs are non-deterministic—traditional unit tests don't fully apply. This skill provides evaluation approaches for the Amditis Resource Kit.
When to activate
- Testing changes before pushing
- Reviewing pull requests
- Debugging reported issues
- Validating data integrity
- Asse
Alternatives in Testing
- Webapp Testing — Test local web applications using Playwright for UI verification and debugging 94.1k ★
- Fix Issue — by metabase - Addresses GitHub issues by taking issue number as parameter, analyzing context, implementing sol 46.5k ★
- Testing Strategy — This project is small, runs in a terminal, and is mostly deterministic 10.9k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Local Binary Swap
Publish and swap local netclaw/netclawd binaries for live integration testing. Activate when user says "swap b
Validate Hypothesis
Business hypothesis validation skill. Validates ideas through 6 phases (origin check, market confirmation, int
Reduce Golang Detections Skill
Claude Code skill for systematically reducing VirusTotal/EDR detection rates on compiled Go binaries via PE st
Validate Module
Run complete two-agent validation on module+tests (contract extraction + test validation). Binary pass/fail wi
QA Validate Features
Validate QA FlowKit Gherkin feature files / Validar archivos Gherkin de QA FlowKit
QA Validate Karate Features
Validate executable Karate feature files / Validar features ejecutables de Karate
Related Agents
Symphony Reviewer
Use for reviewing code changes, PRs, and implementations for architecture compliance, security issues, and qua
Educator
The Coach. Generates walkthroughs, quizzes, and mastery assessments. Builds understanding through teaching, no
QA Test Engineer
Use this agent when you need to verify that features work correctly, ensure product quality, validate performa