Search
AI & LLM Engineering · By ericrisco
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | A skill your agent uses when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual… | ericrisco/ | 190 | — | ~3.2k | Automated safety check: Pass | MIT | today |
| 2 | A skill your agent uses when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server —… | ericrisco/ | 180 | — | ~5k | Automated safety check: Pass | MIT | yesterday |
| 3 | 3.Elixir A skill your agent uses when writing or refactoring Elixir/OTP on the BEAM — GenServers, supervision trees and restart strategies, pattern matching, mix projects and releases — or when processes… | ericrisco/ | 180 | — | ~2.9k | Automated safety check: Pass | MIT | yesterday |
| 4 | A skill your agent uses when choosing an embedding model, chunk size, or query form, when semantic search returns irrelevant results, when adding hybrid BM25+vector or a reranker, or when a… | ericrisco/ | 180 | — | ~2.7k | Automated safety check: Pass | MIT | yesterday |
| 5 | A skill your agent uses when running open models or working on the Hugging Face platform — the Inference Providers router or InferenceClient, Hub repos via the hf CLI, a dedicated Inference Endpoint… | ericrisco/ | 180 | — | ~2.6k | Automated safety check: Pass | MIT | yesterday |
| 6 | A skill your agent uses when wiring several LLM calls into a production flow: typed contracts between steps, a router/gateway so 429s, timeouts and outages fail over instead of taking you down, and… | ericrisco/ | 180 | — | ~3k | Automated safety check: Pass | MIT | yesterday |
| 7 | 7.Ollama A skill your agent uses when running open-weight LLMs locally with Ollama — pulling and tagging models, calling the local API, picking a quantization or GGUF, writing Modelfiles, and sizing VRAM and… | ericrisco/ | 180 | — | ~2.8k | Automated safety check: Pass | MIT | yesterday |
| 8 | 8.Phoenix A skill your agent uses when building an Elixir web app with Phoenix — contexts, Ecto schemas, changesets and migrations, LiveView, channels and PubSub, the generators, and the boundary between… | ericrisco/ | 180 | — | ~2.9k | Automated safety check: Notes | MIT | yesterday |
| 9 | A skill your agent uses when an operator wants to run a small or mid-sized project from a flat file instead of standing up Jira or Asana — dated milestones each with one named owner and a binary… | ericrisco/ | 180 | — | ~2.4k | Automated safety check: Pass | MIT | yesterday |
| 10 | A skill your agent uses when one prompt must give the same right answer across reruns, models, and pasted-in hostile input: forcing a fixed schema, picking the few-shot set, ordering the prompt… | ericrisco/ | 180 | — | ~2.4k | Automated safety check: Pass | MIT | yesterday |
| 11 | 11.RAG A skill your agent uses when building grounded Q&A over your own corpus — chunk, retrieve hybrid, rerank, ground, cite chunk ids, refuse when the sources fall short — or when the right document is… | ericrisco/ | 180 | — | ~2.9k | Automated safety check: Pass | MIT | yesterday |
| 12 | 12.Runpod A skill your agent uses when running GPU compute on RunPod and deciding between Pods (hourly, always-on) and Serverless (per-second, autoscaling) for training, fine-tuning or inference — serverless… | ericrisco/ | 180 | — | ~2.8k | Automated safety check: Pass | MIT | yesterday |
| 13 | 13.Skill Scout A skill your agent uses when a specialized skill probably exists but is not loaded, when a task feels harder than it should because generic reasoning is doing a domain skill's job, when the work… | ericrisco/ | 180 | — | ~3.9k | Automated safety check: Pass | MIT | yesterday |
| 14 | A skill your agent uses when calling open-weight LLMs on Together AI or Fireworks AI's OpenAI-compatible endpoints — baseurl plus namespaced model id, the cheapest model that clears the bar… | ericrisco/ | 180 | — | ~3.3k | Automated safety check: Pass | MIT | yesterday |
| 15 | 15.Vector DB A skill your agent uses when operating a vector store as a data layer — choosing or migrating between Pinecone, Qdrant, Weaviate and pgvector; designing a collection or index (distance metric… | ericrisco/ | 180 | — | ~2.8k | Automated safety check: Pass | MIT | yesterday |
| 16 | 16.Chatbot A skill your agent uses when a support or sales bot on a live website must behave: persona/system prompt, grounding so it cannot invent prices or policy, jailbreak and injection defense, the human… | ericrisco/ | 180 | — | ~3.3k | Automated safety check: Pass | MIT | yesterday |
| 17 | 17.Author Skill A skill your agent uses when authoring a NEW rsc skill or editing an existing one — scoping it to one job, writing the description that decides whether it ever loads, splitting the body into… | ericrisco/ | 180 | — | ~4.3k | Automated safety check: Pass | MIT | yesterday |
| 18 | A skill your agent uses when a long-horizon task is filling the context window and you must decide what to keep, offload, drop, or hand off to a fresh window — when to compact, what the summary must… | ericrisco/ | 180 | — | ~2.4k | Automated safety check: Pass | MIT | yesterday |
| 19 | A skill your agent uses when training or debugging a neural net in PyTorch — the forward/loss/backward/step loop and its silent bugs, mixed precision (AMP), AdamW/LR schedules, DDP/FSDP/ZeRO… | ericrisco/ | 180 | — | ~3.4k | Automated safety check: Pass | MIT | yesterday |
| 20 | 20.Finetuning A skill your agent uses when adapting an open-weight model to a target form or behavior — tone, output format, reasoning pattern — via LoRA/QLoRA or full fine-tuning with TRL SFTTrainer, then… | ericrisco/ | 180 | — | ~3.8k | Automated safety check: Pass | MIT | yesterday |
| 21 | A skill your agent uses when a team must decide what to measure before building anything — picking one north-star metric, separating leading input drivers from lagging outputs, adding guardrails so… | ericrisco/ | 180 | — | ~2.9k | Automated safety check: Pass | MIT | yesterday |
| 22 | 22.NLP A skill your agent uses when choosing how to tokenize text or which transformer type fits an NLP task, when a tokenizer over-fragments non-English text or inflates token cost, when picking a… | ericrisco/ | 180 | — | ~3.5k | Automated safety check: Pass | MIT | yesterday |
| 23 | 23.Open Weights A skill your agent uses when choosing an open-weight LLM and clearing it for use — which family and size fit the task, the hardware and the budget, and above all whether the license permits shipping. | ericrisco/ | 180 | — | ~4.1k | Automated safety check: Pass | MIT | yesterday |
| 24 | A skill your agent uses when assembling or curating the corpus a fine-tune trains on — turning raw examples into the JSONL shape a trainer expects (instruction, conversational, preference-pair or… | ericrisco/ | 180 | — | ~3.7k | Automated safety check: Pass | MIT | yesterday |
| 25 | 25.Unsloth A skill your agent uses when fine-tuning an open-weight LLM fast on ONE GPU with low VRAM — Unsloth's fast model loaders with 4-bit QLoRA and the trl trainer, response-only loss masking so the… | ericrisco/ | 180 | — | ~3.6k | Automated safety check: Pass | MIT | yesterday |
| 26 | 26.Vllm A skill your agent uses when self-hosting an open-weight LLM for high-throughput concurrent serving with vLLM — running an OpenAI-compatible endpoint, splitting a model across GPUs with tensor or… | ericrisco/ | 180 | — | ~3.6k | Automated safety check: Pass | MIT | yesterday |
