Download

Skill UI

Browse and discover 6252+ curated skills

All Development Artificial Intelligence Design & Creative Product & Business Data Science Marketing Soft Skills Productivity Engineering Languages

Search OST , found 81 results

Default Newest Most Downloaded

LLM Prompt Optimizer

optimizing-prompts

jeremylongshore/claude-code-plugins-plus-skills

Optimizes prompts for LLMs to cut token usage, lower costs, and boost response quality by analyzing, condensing, and rewriting instructions; useful when teams need faster, cheaper, clearer AI conversations.

Perplexity Cost Tuning

perplexity-cost-tuning

jeremylongshore/claude-code-plugins-plus-skills

Optimize Perplexity AI search billing by routing queries to the right model, caching responses, limiting token output, filtering domains, and monitoring usage so your API spend stays predictable.

Perplexity Pitfalls Guide

perplexity-known-pitfalls

jeremylongshore/claude-code-plugins-plus-skills

A concise reference for spotting and avoiding Perplexity Sonar anti-patterns during reviews, onboarding, or audits, covering citation parsing, model selection, recency handling, and context limits so integrations stay accurate and cost-effective.

Perplexity Performance Tuning

perplexity-performance-tuning

jeremylongshore/claude-code-plugins-plus-skills

Optimize Perplexity Sonar API calls by selecting appropriate models, caching query hashes, streaming long research, and batching deduplicated requests for faster, cost-effective research or fact-checking workflows.

Perplexity Policy Guardrails

perplexity-policy-guardrails

jeremylongshore/claude-code-plugins-plus-skills

Implements Perplexity Sonar guardrails covering query moderation, tiered model selection, citation scoring, and per-user quotas, so teams can plug policy checks into pre-commit hooks or CI to keep live searches safe and cost-effective.

LLM Prompt Caching

sickn33/antigravity-awesome-skills

Designs multi-tier prompt caching that cuts LLM costs by up to 90% through prefix, full-response, and semantic similarity caching, while emphasizing sensible invalidation to keep stored outputs accurate for production workloads.

LLM Prompt Engineering

prompt-engineer

Jeffallan/claude-skills

Designs, refines, and evaluates prompts for LLM workflows, covering zero/few-shot, chain-of-thought, system personas, structured outputs, and testable evaluation suites to boost accuracy and efficiency.

Ray Train Distributed Orchestration

Orchestra-Research/AI-Research-SKILLs

Ray Train orchestrates distributed PyTorch/TensorFlow/HuggingFace training from laptops to thousands of nodes, adding elastic scaling, hyperparameter search, and fault tolerance while keeping most code unchanged.

Retell AI Cost Tuning

retellai-cost-tuning

jeremylongshore/claude-code-plugins-plus-skills

Guides teams through analyzing Retell AI billing, tuning call durations, choosing cheaper voice models, and monitoring usage so they can reduce minute-based voice-agent costs and set budget alerts.

Retell AI Policy Guardrails

retellai-policy-guardrails

jeremylongshore/claude-code-plugins-plus-skills

Implements lint rules, policy enforcement, and guardrails for Retell AI voice agents, covering content filtering, consent flows, cost caps, and escalation checks for CI or pre-commit setups.

Production ML Engineering Guide

senior-ml-engineer

alirezarezvani/claude-skills

Guides ML engineers through deploying models, building MLOps pipelines, integrating LLMs, implementing RAG systems, and monitoring drift while emphasizing production readiness, cost control, and operational reliability.

SkyPilot Cloud Orchestration

skypilot-multi-cloud-orchestration

Orchestra-Research/AI-Research-SKILLs

SkyPilot Multi-Cloud Orchestration codifies ML workload management by spinning up clusters across AWS/GCP/Azure, auto-optimizing costs, recovering spot instances, and unifying distributed GPU training and serving workflows.

Prev 1 2 3 456 7 Next

Language