Make an AI agent or automation reliable enough to trust — the tests, checks, and guardrails that catch its failures before they reach anything real. Use when asked how do I test my AI agent, make my automation reliable, my agent works sometimes, or how do I trust an AI workflow in production.
Install
npx skills add mohitagw15856/pm-claude-skills --skill ai-agent-reliabilitynpx skills add mohitagw15856/pm-claude-skills --skill ai-agent-reliability -a claude-code -gnpx skills add mohitagw15856/pm-claude-skills --skill ai-agent-reliability -a codex -ggemini skills install https://github.com/mohitagw15856/pm-claude-skills.git --path skills/ai-agent-reliabilitygh skill install mohitagw15856/pm-claude-skills ai-agent-reliabilitygit clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills /tmp/mohitagw15856__pm-claude-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/mohitagw15856__pm-claude-skills/skills/ai-agent-reliability ~/.claude/skills/ai-agent-reliability # Claude Code
cp -R /tmp/mohitagw15856__pm-claude-skills/skills/ai-agent-reliability ~/.agents/skills/ai-agent-reliability # Codex, Cursor, Gemini CLI, Copilot, OpenCode