MCP App StoreMCP App Store
from agent-skills-hub46
A structured workflow for improving agent performance via metrics, prompt engineering, testing (A/B), and safe staged rollouts.
This skill provides a full, data-driven workflow to analyze, optimize, and safely deploy improvements to existing AI agents. It covers baseline metric collection, failure-mode analysis, prompt engineering techniques (chain-of-thought, few-shot examples), test-suite and A/B testing design, evaluation metrics, and staged rollout/rollback procedures.
Use when improving an existing agent's accuracy, reliability, or efficiency — especially when you have metrics and test cases available. Also useful for teams running regression tests, human evaluation, and controlled deployments. Not intended for building brand-new agents from scratch.
context-manager and parallel-test-runner in instructions.Designed for orchestration and evaluation agents (agent runners, prompt-engineer assistants, testing harnesses, and CI-integrated agents like Claude Code or Copilot-style tooling).
This skill has not been reviewed by our automated audit pipeline yet.
FastAPI Project Templates
Creates production-ready FastAPI project scaffolds with async patterns, DI, middleware, and testing best practices for high-performance APIs.
Postmortem Writing
Guided, blameless postmortem authoring: timelines, root-cause analysis, and actionable follow-ups to turn incidents into organizational learning.
Backtesting Frameworks
Patterns and practical steps to build reliable, bias-aware backtesting systems for evaluating trading strategies and validating research hypotheses.
Referral & Affiliate Program
Design, launch, and optimize referral or affiliate programs — incentives, mechanics, measurement, and launch checklists for growth teams.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
Claw Bench
Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.
Replit — Advanced Troubleshooting
Step-by-step diagnostics and debugging techniques for deep Replit issues: Nix build failures, container crash loops, memory leaks, and platform vs app isolation
Klaviyo Observability
Add Prometheus metrics, OpenTelemetry tracing, structured logging, and alerting for Klaviyo API integrations to monitor performance and failures.
Juicebox Performance Tuning
Guidance and code patterns to reduce Juicebox AI analysis latency: caching, batching, upload chunking, and pagination to improve throughput and responsiveness.
Vercel Common Errors
Diagnose and fix common Vercel build, serverless runtime, and edge/routing errors with step-by-step checks and fixes.
Cortex - ML Pipeline Builder
Guided ML pipeline builder that walks an agent through data validation, feature engineering, training, evaluation, and serving endpoints for classification or r