Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library
Install
npx skills add davila7/claude-code-templates --skill instructornpx skills add davila7/claude-code-templates --skill instructor -a claude-code -gnpx skills add davila7/claude-code-templates --skill instructor -a codex -ggemini skills install https://github.com/davila7/claude-code-templates.git --path cli-tool/components/skills/ai-research/prompt-engineering-instructorgh skill install davila7/claude-code-templates instructorgit clone --depth 1 https://github.com/davila7/claude-code-templates /tmp/davila7__claude-code-templates
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/prompt-engineering-instructor ~/.claude/skills/instructor # Claude Code
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/prompt-engineering-instructor ~/.agents/skills/instructor # Codex, Cursor, Gemini CLI, Copilot, OpenCode