4-stage evaluation framework for testing Claude Code plugin component triggering. Validates skills, agents, and commands activate correctly via programmatic detection and LLM judgment.

1 stars 0 forks 1 watchers TypeScript MIT License
ai-testing anthropic claude claude-agent-sdk claude-code cli developer-tools evaluation-framework llm plugin-testing test-automation testing-framework typescript
1 Open Issue Need Help Last updated: Jan 2, 2026

Open Issues Need Help

View All on GitHub

AI Summary: This issue aims to improve the unit test coverage for two critical utility modules, `src/utils/file-io.ts` and `src/utils/logging.ts`, which currently have significantly lower coverage (47% and 55%) compared to the overall codebase. The goal is to raise their coverage to 78% by adding specific tests for directory operations, error handling in file I/O, and various log level methods and formatting edge cases.

Complexity: 2/5
enhancement good first issue component:utils priority:medium effort:medium

4-stage evaluation framework for testing Claude Code plugin component triggering. Validates skills, agents, and commands activate correctly via programmatic detection and LLM judgment.

TypeScript
#ai-testing#anthropic#claude#claude-agent-sdk#claude-code#cli#developer-tools#evaluation-framework#llm#plugin-testing#test-automation#testing-framework#typescript