All skills
caveman-discover
Finds and labels every LLM workflow in your repository so Caveman Cloud can group spend by workflow.
- Part of JuliusBrussee/caveman
- 131k installs
- AI Engineering · Evals and monitoring
More Evals and monitoring skills
See all- prompt-engineering-patterns24.8kDesigns, debugs and improves prompts using templates, chain-of-thought and few-shot patterns.
- llm-evaluation13.8kSets up automated metrics, human feedback and benchmarks to measure how well your LLM application performs.
- ai-prompt-engineering-safety-review10.5kReviews prompts for safety, bias, security and effectiveness, then suggests concrete improvements.
- agentic-eval10.3kSets up evaluation and self-critique loops to measure and improve AI agent output quality.
Also in this pack
- caveman641kMakes the agent answer in terse caveman speech, dropping fluff but keeping every technical fact.
- caveman-compress445kCompresses a memory file like CLAUDE.md into caveman format to save input tokens, keeping a readable backup.
- caveman-commit444kWrites a short Conventional Commits message that captures only the intent of your change.
- caveman-review440kReviews a diff or pull request in compressed form, one line per finding with location, problem and fix.