Search
AI & LLM Engineering · OpenAI · By jeremylongshore
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Monitor and optimize LLM costs using Langfuse analytics and dashboards. | jeremylongshore/ | 2.8k | — | ~2.4k | Automated safety check: Pass | MIT | yesterday |
| 2 | Migrate from OpenAI/GPT to Anthropic/Claude — API differences, Use when working with migration-deep-dive patterns. | jeremylongshore/ | 2.8k | — | ~1.1k | Automated safety check: Pass | MIT | yesterday |
| 3 | Migrate an application to or from Cohere with a provider adapter, parallel embedding index, quality evaluation, canary traffic, and rollback. | jeremylongshore/ | 2.8k | — | ~1.1k | Automated safety check: Pass | MIT | yesterday |
| 4 | Works correctly with LangChain 1.0's typed content blocks on AIMessage.content — text, tooluse, image, thinking, document — across Claude, GPT-4o, and Gemini, including multi-modal composition and… | jeremylongshore/ | 2.8k | — | ~3.6k | Automated safety check: Pass | MIT | yesterday |
| 5 | Build and query vector stores with LangChain 1.0 without getting burned by flipped score semantics, embedding-dim mismatches, reranker quirks, and chunk-splitter bugs. | jeremylongshore/ | 2.8k | — | ~2.6k | Automated safety check: Pass | MIT | yesterday |
| 6 | Invoke Claude, GPT-4o, and Gemini through LangChain 1.0 without tripping on the content-block, token-accounting, and structured-output quirks that silently break production code. | jeremylongshore/ | 2.8k | — | ~2.7k | Automated safety check: Pass | MIT | yesterday |
| 7 | Manage LangChain 1.0 prompts like code — LangSmith prompt hub versioning, XML-tag conventions for Claude, few-shot example selection, discriminated-union extraction schemas, and A/B test wiring. | jeremylongshore/ | 2.8k | — | ~4.4k | Automated safety check: Pass | MIT | yesterday |
| 8 | Rate-limit LangChain 1.0 calls correctly across multi-worker deployments — Redis-backed limiters, asyncio.Semaphore, narrow exception whitelists, and provider-specific throttle handling. | jeremylongshore/ | 2.8k | — | ~4.4k | Automated safety check: Pass | MIT | yesterday |
| 9 | Compose LangChain 1.0 Python runnables with the production defaults the docs do not warn about: parallel batching, narrow fallbacks, and brace-safe prompts. | jeremylongshore/ | 2.8k | — | ~3.4k | Automated safety check: Pass | MIT | yesterday |
| 10 | Upgrade Langfuse SDK versions and migrate between API changes. | jeremylongshore/ | 2.8k | — | ~2.1k | Automated safety check: Pass | MIT | yesterday |
| 11 | 11.Ollama Setup Configure auto-configure Ollama when user needs local LLM deployment, free AI alternatives, or wants to eliminate hosted API costs. | jeremylongshore/ | 2.8k | — | ~1.4k | Automated safety check: Notes | MIT | yesterday |
| 12 | Configure automatic model fallbacks for high availability on OpenRouter. | jeremylongshore/ | 2.8k | — | ~2.4k | Automated safety check: Pass | MIT | yesterday |
| 13 | Implement function/tool calling with OpenRouter models. An agent skill from jeremylongshore/tons-of-skills-marketplace. | jeremylongshore/ | 2.8k | — | ~2.6k | Automated safety check: Pass | MIT | yesterday |
| 14 | Send your first OpenRouter API request and understand the response. | jeremylongshore/ | 2.8k | — | ~1.8k | Automated safety check: Pass | MIT | yesterday |
| 15 | Set up OpenRouter API authentication and configure API keys. | jeremylongshore/ | 2.8k | — | ~1.6k | Automated safety check: Notes | MIT | yesterday |
| 16 | Implement intelligent model routing to optimize cost, quality, and latency on OpenRouter. | jeremylongshore/ | 2.8k | — | ~2.4k | Automated safety check: Pass | MIT | yesterday |
| 17 | Use multiple AI providers (OpenAI, Anthropic, Google, Meta) through OpenRouter's unified API. | jeremylongshore/ | 2.8k | — | ~2.5k | Automated safety check: Pass | MIT | yesterday |
| 18 | Migrate from OpenAI to OpenRouter with minimal code changes. | jeremylongshore/ | 2.8k | — | ~2.4k | Automated safety check: Pass | MIT | yesterday |
| 19 | Optimize OpenRouter request latency and throughput. An agent skill from jeremylongshore/tons-of-skills-marketplace. | jeremylongshore/ | 2.8k | — | ~2.4k | Automated safety check: Pass | MIT | yesterday |
| 20 | Understand and handle OpenRouter rate limits. An agent skill from jeremylongshore/tons-of-skills-marketplace. | jeremylongshore/ | 2.8k | — | ~2.4k | Automated safety check: Pass | MIT | yesterday |
| 21 | Build reusable OpenRouter client wrappers with retries, typing, and middleware. | jeremylongshore/ | 2.8k | — | ~2.9k | Automated safety check: Pass | MIT | yesterday |
| 22 | Migrate to OpenRouter from direct provider APIs or upgrade between SDK/model versions. | jeremylongshore/ | 2.8k | — | ~2.6k | Automated safety check: Pass | MIT | yesterday |
| 23 | Encapsulate Together AI SDK v2 behind a typed adapter with catalog-resolved models, bounded retries, streaming normalization, usage capture, and OpenAI-compatible migration seams. | jeremylongshore/ | 2.8k | — | ~1k | Automated safety check: Pass | MIT | yesterday |
| 24 | Create a minimal working Langfuse trace example. An agent skill from jeremylongshore/tons-of-skills-marketplace. | jeremylongshore/ | 2.8k | — | ~1.9k | Automated safety check: Pass | MIT | yesterday |
| 25 | Migrate to Claude API from OpenAI, Gemini, or other LLM providers. | jeremylongshore/ | 2.8k | — | ~2k | Automated safety check: Pass | MIT | yesterday |
| 26 | A skill your agent uses whenever the user wants to find, shortlist, vet, or enrich US AI/ML/data consulting firms (consultancies) — AI/ML development, MLOps, generative AI / LLM apps (RAG, chatbots… | jeremylongshore/ | 2.8k | — | ~4k | Automated safety check: Notes | MIT | yesterday |
| 27 | Execute Langfuse primary workflow: Tracing LLM calls and spans. | jeremylongshore/ | 2.8k | — | ~2.3k | Automated safety check: Pass | MIT | yesterday |
