Marketplace

29 skills

Each listing spells out exactly what's inside — the steps, the ready-to-run code, and which AI tools it works with — so you know what you're getting before you buy.

Clear filters

Design seamless handoff protocols between specialized agents: context transfer, state serialization, and recovery on failure.

  • 9-step procedure
  • 6 pitfalls to avoid
  • Installs into 6 tools
agent-infrastructureBest with a strong model (Claude Sonnet 4)·5 min read·Updated 1 month ago

Design self-improving agent systems: outcome tracking, reward signal extraction, prompt refinement cycles, and human preference collection.

  • 9-step procedure
  • 6 pitfalls to avoid
  • Installs into 6 tools
agent-infrastructureBest with a strong model (Claude Sonnet 4)·6 min read·Updated 1 month ago

Use when an agent workflow needs measurable quality: build task-based evals with graders, baselines, and A/B comparisons before shipping changes.

  • 9-step procedure
  • 1 ready-to-run code block
  • 8-point quality checklist
agent-infrastructureBest with a strong model (Claude Sonnet 4)·6 min read·Updated 1 month ago

Design and run comprehensive eval suites for AI agents: task completion rates, tool call accuracy, cost tracking, and regression testing.

  • 9-step procedure
  • 6 pitfalls to avoid
  • Installs into 6 tools
agent-infrastructureBest with a strong model (Claude Sonnet 4)·5 min read·Updated 1 month ago

Analyze and reduce AI agent operating costs: model routing, prompt caching, context window management, and batch processing strategies.

  • 10-step procedure
  • 6 pitfalls to avoid
  • Installs into 6 tools
agent-infrastructureBest with a strong model (Claude Sonnet 4)·5 min read·Updated 1 month ago
← PrevPage 2 of 2