Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
Install
npx skills add parcadei/Continuous-Claude-v3 --skill agentica-promptsnpx skills add parcadei/Continuous-Claude-v3 --skill agentica-prompts -a claude-code -gnpx skills add parcadei/Continuous-Claude-v3 --skill agentica-prompts -a codex -ggemini skills install https://github.com/parcadei/Continuous-Claude-v3.git --path .claude/skills/agentica-promptsgh skill install parcadei/Continuous-Claude-v3 agentica-promptsgit clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3 /tmp/parcadei__Continuous-Claude-v3
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/parcadei__Continuous-Claude-v3/.claude/skills/agentica-prompts ~/.claude/skills/agentica-prompts # Claude Code
cp -R /tmp/parcadei__Continuous-Claude-v3/.claude/skills/agentica-prompts ~/.agents/skills/agentica-prompts # Codex, Cursor, Gemini CLI, Copilot, OpenCode