Skip to content

Agent skills

Agent skills are folders of instructions and scripts that teach Claude Code, Codex, Cursor and other agents a task. Each one lists what it can run and how to install it.

Showing 2,491–2,520 of 3,419

  1. Diagnoses Qdrant production issues using metrics and observability tools

    • Open source
    • 269 GitHub stars
    • Knowledge and memory
  2. Guides Qdrant monitoring setup including Prometheus scraping, Datadog integration, health probes, Hybrid Cloud metrics, alerting, and log ce

    • Open source
    • 269 GitHub stars
    • Knowledge and memory
  3. Guides tenant isolation architecture in Qdrant for multi-tenant or multi-user applications

    • Open source
    • 269 GitHub stars
    • Knowledge and memory
  4. Navigation hub linking sub-skills for proactive Qdrant tuning: search speed, indexing performance, and memory usage optimization

    • Open source
    • 269 GitHub stars
    • Knowledge and memory
  5. Guides Qdrant scaling decisions

    • Open source
    • 269 GitHub stars
    • Knowledge and memory
  6. Diagnoses and guides Qdrant horizontal scaling decisions

    • Open source
    • 269 GitHub stars
    • Knowledge and memory
  7. Guides Qdrant query throughput (QPS) scaling

    • Open source
    • 269 GitHub stars
    • Knowledge and memory
  8. Diagnoses and improves Qdrant search relevance

    • Open source
    • 269 GitHub stars
    • Knowledge and memory
  9. Fusing scores from multiple searches into a single ranked result (RRF, DBSF, custom fusion)

    • Open source
    • 269 GitHub stars
    • Knowledge and memory
  10. Constructing prefetch queries for hybrid retrieval, including BM25/dense and multi-field setups, and choosing a lexical retrieval method

    • Open source
    • 269 GitHub stars
    • Knowledge and memory
  11. Expanding the candidate pool via relevance feedback, as an alternative to reranking when a dense retriever is too weak

    • Open source
    • 269 GitHub stars
    • Knowledge and memory
  12. Probe thinking through iterative rounds of useful questions that expose assumptions and blind spots.

    • Open source
    • 120 GitHub stars
  13. Make an abstract idea concrete through mechanisms, examples, or situations.

    • Open source
    • 120 GitHub stars
  14. Identify candidate next steps for continuing the current thinking.

    • Open source
    • 120 GitHub stars
  15. Identify the important unresolved parts of our thinking.

    • Open source
    • 120 GitHub stars
  16. Derive observable predictions from the current understanding.

    • Open source
    • 120 GitHub stars
  17. Prioritize the current questions or branches by expected value for the goal.

    • Open source
    • 120 GitHub stars
  18. Learn a concept by reconstructing why it had to be invented.

    • Open source
    • 120 GitHub stars
  19. Explore a different representation or perspective on the current problem.

    • Open source
    • 120 GitHub stars
  20. Recover the current state of our thinking.

    • Open source
    • 120 GitHub stars