Enrich ACM test failure data with AI analysis and git history.
npx skills add https://github.com/stolostron/acm-ai-qe --skill acm-data-enricher
Please help me install this Agent Skill. Skill: acm-data-enricher Source: https://github.com/stolostron/acm-ai-qe/tree/main/.claude/skills/acm-data-enricher Command: npx skills add https://github.com/stolostron/acm-ai-qe --skill acm-data-enricher
This Skill enriches test failure data with AI-analyzed context, improving the accuracy of bug classification and feature knowledge.
Run the 'acm-data-enricher' skill with the path to your run directory containing 'core-data.json'.
High-intent search queries and answers about installing and using this skill.
To enrich test failure data with AI analysis, run the skill with your run directory containing 'core-data.json'. It performs page object resolution, selector verification, and git history analysis to improve bug classification accuracy.
Selector verification checks selector existence within product source code using the acm-source MCP. This validates that UI selectors extracted from test files actually exist in the codebase, improving failure context accuracy.
Yes, you need the gh CLI installed to analyze git history for selector timeline changes. The skill depends on the gh CLI to retrieve commit history and track how selectors have changed over time.
Yes, you can fill feature knowledge gaps for implementation bugs. The skill processes test failure data to add missing feature context, which helps in understanding and classifying feature-related test failures.
The best way to resolve page objects from test files is to use this skill on your run directory. It identifies page objects within the test files and resolves them to provide better context for the test failure data.
No, the acm-data-enricher requires the acm-source MCP to perform selector verification. Without this dependency, the skill cannot verify selector existence in the product source code.
stolostronAnalyze GitHub PR diffs for ACM repositories to identify code changes and testing scenarios.
OpenLAIRTrain large language models with Megatron-Core parallelism on multi-node GPU clusters.
sobhanashineExecute code health checks and calculate a weighted score from linters, type checkers, and test runners.
HomericIntelligenceParse test execution logs to identify and categorize failures by type.
