Open Issues Need Help
View All on GitHub feat: improve HTML report accessibility about 9 hours ago
enhancement good first issue
Prove whether AGENTS.md, CLAUDE.md, and SKILL.md context helps or hurts with isolated A/B trials.
Python
#agents-md#ai-agents#coding-agents#context-engineering#developer-tools#llm-evaluation#python
docs: add a Claude Code runner example about 9 hours ago
documentation good first issue
Prove whether AGENTS.md, CLAUDE.md, and SKILL.md context helps or hurts with isolated A/B trials.
Python
#agents-md#ai-agents#coding-agents#context-engineering#developer-tools#llm-evaluation#python
feat: compare individual context sections with ablation about 9 hours ago
enhancement good first issue
Prove whether AGENTS.md, CLAUDE.md, and SKILL.md context helps or hurts with isolated A/B trials.
Python
#agents-md#ai-agents#coding-agents#context-engineering#developer-tools#llm-evaluation#python
feat: add JSON value assertion check about 9 hours ago
enhancement good first issue
Prove whether AGENTS.md, CLAUDE.md, and SKILL.md context helps or hurts with isolated A/B trials.
Python
#agents-md#ai-agents#coding-agents#context-engineering#developer-tools#llm-evaluation#python
feat: add bootstrap confidence intervals for pass-rate lift about 9 hours ago
enhancement good first issue
Prove whether AGENTS.md, CLAUDE.md, and SKILL.md context helps or hurts with isolated A/B trials.
Python
#agents-md#ai-agents#coding-agents#context-engineering#developer-tools#llm-evaluation#python