Golden Prompt Tests
Golden file tests that capture the exact JSON payload we send to the LLM API
Explore
41,493 skills indexed with the new KISS metadata standard.
Golden file tests that capture the exact JSON payload we send to the LLM API
> **New to Claude?** Start with [INSTANT_START_WITH_CLAUDE.md](./INSTANT_START_WITH_CLAUDE.md) for a guided tutorial on using Claude for Geotab development. This page is a quick reference for specific prompts.
generic skill
LLM 애플리케이션을 위한 프롬프트를 저장, 관리하고 버전별로 추적하세요
The current CLI is a bit cumbersome to use with users having to type commands
Suggest relevant GitHub Copilot prompt files from the awesome-copilot repository based on current repository context and chat history, avoiding duplicates with existing prompts in this repository, and identifying outdated prompts that need updates.
bias checks)
practical starter prompt
mini variants) — usually lack depth/context/tool reliability
very large context windows
fast
excellent for self-hosting
import Tabs from "@theme/Tabs";
writing quality
real-time knowledge via X
function calling
always tailor to the process):
open behavior
20% time savings
recommend which AI engines are best suited and why.
dependencies
some inconsistency |
then issue your verdict with clear reasoning.
but context accuracy is critical. Recommend hybrid approach with AI drafts + human review.