NeVibeCode · 9 items
Skills and MCP tagged “evals”
caveman-manage skill The skill reads an experiment's state and results in Caveman Cloud, weighs the evidence, then reports one recommendation or blocks the action.
Claude Code CX Codex Cursor +1
103,300installs
eval-harness skill A skill for eval-driven development: it sets pass/fail criteria before you write code and tracks agent reliability with pass@k and pass^k.
Claude Code CX Codex Cursor +1
4,700installs
agentic-engineering skill Establishes protocols for agent-led workflows: breaks work into 15-minute verifiable units, enforces eval-first testing, and routes tasks between Haiku, Sonnet, and Opus.
Claude Code CX Codex Cursor +1
4,700installs
continuous-agent-loop skill A skill that lays out a continuous agent loop: mode selection, quality gates, evals and recovery. Useful when an agent runs unattended.
Claude Code CX Codex Cursor +1
4,500installs
bmad-eval skill Runs automated benchmarks and evaluations for agent skills across four modes, checking trigger accuracy and grading quality in a clean workspace.
Claude Code CX Codex Cursor +1
4,500installs
deepeval skill DeepEval skill sets up evaluation loops for AI agents and RAG systems. It creates pytest suites, generates golden datasets, and catches regressions.
Claude Code CX Codex Cursor +1
2,800installs
checkpoint-promotion skill Gates a trained checkpoint before release by checking data quality, capability drift, forgetting, and paired results against the base model.
Claude Code CX Codex Cursor
2,600installs
senior-prompt-engineer skill Tests prompts against baselines, measures RAG retrieval metrics, and validates agent configs using three Python stdlib tools. Useful for disciplined prompt iteration without guess-driven edits.
Claude Code
970installs
agents-sdk
official skill Builds, runs, and tests OpenAI Agents SDK apps from Codex. Turns a prompt, repo, or session into a working agent with tools and eval tests.
CX Codex GP ChatGPT
22installs
