Category
Best AI and LLM engineering skills, page 103
AI & LLM Engineering skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 4897 | A skill your agent uses when packaging the artifacts of an EMNLP paper — datasets, annotation guidelines, prompts, evaluation code, and model outputs — as anonymous review-time evidence or public… | brycewang-stanford/ | 1.2k | — | ~1.7k | Automated safety check: Pass | MIT | 11 days ago |
| 4898 | 4898.Emnlp Submission A skill your agent uses when auditing an EMNLP submission before the ACL Rolling Review deadline, covering ACL-template compliance, the 8-page long / 4-page short caps, the mandatory Limitations… | brycewang-stanford/ | 1.2k | — | ~1.8k | Automated safety check: Pass | MIT | 11 days ago |
| 4899 | A skill your agent uses when deciding whether a project belongs at EMNLP, weighing its empirical-NLP identity against ACL, NAACL, EACL, AACL, CoNLL, LREC-COLING, TACL, and ML venues, matching the… | brycewang-stanford/ | 1.2k | — | ~1.8k | Automated safety check: Pass | MIT | 11 days ago |
| 4900 | A skill your agent uses when preparing the accountability artifacts that accompany an ACM FAccT paper — datasheets for datasets, model cards, data statements, audit and impact-assessment… | brycewang-stanford/ | 1.2k | — | ~1.5k | Automated safety check: Pass | MIT | 11 days ago |
| 4901 | 4901.Facct Camera Ready A skill your agent uses when preparing an accepted ACM FAccT paper for camera-ready — de-anonymizing and adding the withheld Positionality/Acknowledgements statements, switching to the acmart… | brycewang-stanford/ | 1.2k | — | ~1.3k | Automated safety check: Pass | MIT | 11 days ago |
| 4902 | A skill your agent uses when deciding whether a responsible-AI project belongs at ACM FAccT or should route to a pure-ML venue (NeurIPS/ICML/ICLR), an HCI venue (CHI/CSCW), a law/policy venue, or an… | brycewang-stanford/ | 1.2k | — | ~1.7k | Automated safety check: Pass | MIT | 11 days ago |
| 4903 | 4903.Facct Workflow A skill your agent uses when planning an ACM FAccT project timeline from venue fit through abstract registration, OpenReview submission, the rebuttal window, the new Accept/Revise/Reject… | brycewang-stanford/ | 1.2k | — | ~1.5k | Automated safety check: Pass | MIT | 11 days ago |
| 4904 | 4904.Iccv Topic Selection A skill your agent uses when deciding whether a computer-vision project should target ICCV, weighing the biennial odd-year cadence and its two-year option cost, what the Marr Prize lineage says… | brycewang-stanford/ | 1.2k | — | ~1.7k | Automated safety check: Pass | MIT | 11 days ago |
| 4905 | 4905.Iclr Topic Selection A skill your agent uses when deciding whether a project is a strong ICLR submission, should be reframed for ICLR, or should be routed to NeurIPS, ICML, AAAI, AISTATS, ACL, CVPR, KDD, or another venue. | brycewang-stanford/ | 1.2k | — | ~990 | Automated safety check: Pass | MIT | 11 days ago |
| 4906 | A skill your agent uses when packaging datasets, models, prompts, or annotation materials for a NAACL-bound submission — building the artifact around the Responsible NLP checklist's artifact… | brycewang-stanford/ | 1.2k | — | ~1.5k | Automated safety check: Pass | MIT | 11 days ago |
| 4907 | A skill your agent uses when hardening the reproducibility story of a NAACL submission — treating the Responsible NLP checklist as a binding contract, pinning model versions and API access dates… | brycewang-stanford/ | 1.2k | — | ~1.4k | Automated safety check: Pass | MIT | 11 days ago |
| 4908 | A skill your agent uses when deciding what NeurIPS material belongs in the main PDF body, the references, text appendices, the mandatory Paper Checklist, the separate code/data ZIP, or an external… | brycewang-stanford/ | 1.2k | — | ~963 | Automated safety check: Pass | MIT | 11 days ago |
| 4909 | A skill your agent uses when deciding whether a project belongs at SIGIR and in which of its tracks — testing whether retrieval is the contribution or the plumbing, forking across… | brycewang-stanford/ | 1.2k | — | ~1.8k | Automated safety check: Pass | MIT | 11 days ago |
| 4910 | 4910.Smr Rebuttal A skill your agent uses when responding to a Sociological Methods & Research (SMR) decision letter — drafting the point-by-point response and revision plan for properties, simulations, the empirical… | brycewang-stanford/ | 1.2k | — | ~1.2k | Automated safety check: Pass | MIT | 11 days ago |
| 4911 | 4911.Vldb Camera Ready A skill your agent uses when producing the final PVLDB version of an accepted VLDB paper, covering the volume-specific template, PDF/A compliance and font embedding, figure legibility floors, the… | brycewang-stanford/ | 1.2k | — | ~982 | Automated safety check: Pass | MIT | 11 days ago |
| 4912 | 4912.Openrouter Usage Track OpenRouter API spending — credit balance, per-model cost breakdown, and spending projections from OpenClaw session logs. | aAAaqwq/ | 105 | 1 repo | ~443 | Automated safety check: Pass | MIT | 11 days ago |
| 4913 | 4913.Langgraph A skill your agent uses when building or debugging LangGraph workflows — designing state graphs, adding conditional routing, wiring checkpointers, streaming tokens, implementing human-in-the-loop… | kid-sid/ | 189 | — | ~3.4k | Automated safety check: Pass | MIT | 2 mo ago |
| 4914 | 4914.Openai Agents A skill your agent uses when building or debugging OpenAI Agents SDK workflows — defining agents with tools and handoffs, wiring typed context, streaming responses, adding guardrails, or integrating… | kid-sid/ | 189 | — | ~3.4k | Automated safety check: Pass | MIT | 2 mo ago |
| 4915 | Stand up a PUBLIC, shareable inference endpoint for an HF/gs model on an Iris TPU so people on the internet can vibe-test it in a browser or via an OpenAI-compatible API. | open-thoughts/ | 301 | — | ~1.8k | Automated safety check: Warn | Apache-2.0 | 10 days ago |
| 4916 | Battle-tested prompt patterns for production AI agents. An agent skill from LeoYeAI/openclaw-master-skills. | LeoYeAI/ | 2.2k | — | ~6.8k | Automated safety check: Pass | MIT | 2 mo ago |
| 4917 | 4917.Glance Create, update, and manage Glance dashboard widgets. An agent skill from LeoYeAI/openclaw-master-skills. | LeoYeAI/ | 2.2k | — | ~7.3k | Automated safety check: Notes | MIT | 2 mo ago |
| 4918 | 4918.Prompt Optimizer When user asks to improve prompt, optimize prompt, better prompt, fix prompt, rewrite prompt, prompt engineering, make prompt better, enhance prompt, prompt template, system prompt, mega prompt… | LeoYeAI/ | 2.2k | — | ~6.2k | Automated safety check: Pass | MIT | 2 mo ago |
| 4919 | 4919.Trae Orchestrator Orchestrates TRAE IDE for automated software development with multi-agent collaboration. | LeoYeAI/ | 2.2k | — | ~6.3k | Automated safety check: Pass | MIT | 2 mo ago |
| 4920 | 4920.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/ | 167 | — | ~4.3k | Automated safety check: Pass | MIT | today |
| 4921 | 4921.Context Budget 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/ | 167 | — | ~2.4k | Automated safety check: Pass | MIT | today |
| 4922 | 4922.Deep Learning 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/ | 167 | — | ~3.4k | Automated safety check: Pass | MIT | today |
| 4923 | 4923.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/ | 167 | — | ~3.8k | Automated safety check: Pass | MIT | today |
| 4924 | 4924.Kpi Framework 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/ | 167 | — | ~2.9k | Automated safety check: Pass | MIT | today |
| 4925 | 4925.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/ | 167 | — | ~3.5k | Automated safety check: Pass | MIT | today |
| 4926 | 4926.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/ | 167 | — | ~4.1k | Automated safety check: Pass | MIT | today |
| 4927 | 4927.Training Data 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/ | 167 | — | ~3.7k | Automated safety check: Pass | MIT | today |
| 4928 | 4928.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/ | 167 | — | ~3.6k | Automated safety check: Pass | MIT | today |
| 4929 | 4929.Data Workshop Data Workshop internals — Dataset and Cell, derived versions and the use gate, Parquet identity, the sandboxed runner, agent engines and tools, reviewed preparation, synthetic examples, shared… | overmind-core/ | 597 | — | ~7.1k | Automated safety check: Warn | AGPL-3.0 | today |
| 4930 | 4930.Glimmer Delegation Delegates tasks to a locally served Muse Glimmer via ollama. | athola/ | 342 | — | ~988 | Automated safety check: Notes | MIT | 2 days ago |
| 4931 | 4931.Modular Skills Build composable skill modules with hub-and-spoke loading. An agent skill from athola/claude-night-market. | athola/ | 342 | — | ~1.6k | Automated safety check: Pass | MIT | 2 days ago |
| 4932 | 4932.Structured Output Formats review deliverables with consistent structure for comparable findings. | athola/ | 342 | — | ~1.2k | Automated safety check: Pass | MIT | 2 days ago |
| 4933 | 4933.Usage Logging Implements structured usage logging and audit trails for cost and session tracking. | athola/ | 342 | — | ~896 | Automated safety check: Pass | MIT | 2 days ago |
| 4934 | 4934.Writing Rules Creates behavioral rules in markdown to block dangerous commands or restrict AI behavior. | athola/ | 342 | — | ~1.4k | Automated safety check: Notes | MIT | 2 days ago |
| 4935 | ADK 框架适配层。为 LangChain / EINO / AutoGen / AgentScope / CrewAI 提供框架特定的 代码模板、惯用模式、API 映射和项目结构，供 agent-dev-workshop Phase 5 代码生成使用。 | hashgraph-online/ | 1.2k | — | ~528 | Automated safety check: Pass | Apache-2.0 | today |
| 4936 | 4936.Agent Dev Workshop 交互式 AI Agent 开发工作坊：通过 6 阶段深度协作对话，引导用户完成 Agent 需求分析、架构设计、 工具定义、Prompt 与编排设计、代码生成、验证迭代，产出可直接运行的 Agent 项目。 | hashgraph-online/ | 1.2k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | today |
| 4937 | AI Agent 架构模式目录。提供 ReAct、Multi-Agent Conversation、Multi-Agent Workflow、 RAG Agent、Tool-Use Agent、Autonomous Agent 六种核心模式的参考架构、组件拓扑、 数据流、设计决策和框架无关的最佳实践。供 agent-dev-workshop Phase 2 调用。 | hashgraph-online/ | 1.2k | — | ~445 | Automated safety check: Pass | Apache-2.0 | today |
| 4938 | Design and review predictable Go command-line interfaces with canonical names and flags; explicit inputs and precedence; human, plain, and structured output; safe prompting; stdout and stderr… | hashgraph-online/ | 1.2k | — | ~864 | Automated safety check: Pass | MIT | today |
| 4939 | Design and review stable, idiomatic Go package APIs covering naming, exported declarations, embedding, receivers, typed-nil interfaces, generics, functional options, method sets, errors, wire… | hashgraph-online/ | 1.2k | — | ~789 | Automated safety check: Pass | MIT | today |
| 4940 | 4940.Review PR Review a GitHub pull request with the RAG + code-graph pipeline (reviewer MCP server). | hashgraph-online/ | 1.2k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | today |
| 4941 | 4941.Solve Task Gather disciplined context for solving a task, then hand off to development. | hashgraph-online/ | 1.2k | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | today |
| 4942 | Plan an ad-intensive but policy-compliant Amazon launch that expands indexed and converting keyword coverage while preserving profitability and inventory guardrails. | xjli360/ | 240 | — | ~531 | Automated safety check: Pass | MIT | 10 days ago |
| 4943 | Sequence pre-event readiness (listing assets, review count, inbound inventory) against a promotion timeline, then lay out automatic, manual, product-targeting, brand, and display ad structures… | xjli360/ | 240 | — | ~773 | Automated safety check: Pass | MIT | 10 days ago |
| 4944 | Set up a beginner Sponsored Products structure on the US marketplace in five gated steps—auto campaigns bid by targeting group, search-phrase research, manual keyword campaigns, product (ASIN)… | xjli360/ | 240 | — | ~757 | Automated safety check: Pass | MIT | 10 days ago |
Explore related skills
Topics in AI & LLM Engineering
- Building AI agents563
- Deep learning415
- Embeddings386
- LLM inference and serving372
- Prompt engineering360
- Retrieval-augmented generation358
- Fine-tuning309
- LLM evaluation308
- Speech recognition and synthesis308
- Structured output and tool calling276
- LLM cost and token optimization259
- LLM API integration255
- Model routing and gateways255
- LLM observability240
- LLM guardrails221
- Computer vision203
- Model hubs and datasets180
- GPU and accelerator computing176
- Diffusion and image models166
- Natural language processing131
- Reinforcement learning66
- AI interpretability23
Products these skills work with
Roles that use these skills
Other categories
- Development15,229
- Frontend & Design5,834
- Backend & APIs7,161
- Testing & QA5,085
- DevOps & Cloud5,962
- Databases2,339
- Data & Analytics3,647
- Agent Workflows8,311
- Documents & Office4,273
- Writing & Content3,731
- Marketing & SEO3,910
- Sales & Support1,815
- Research & Science6,075
- Security3,084
- Productivity & Automation4,016
- Business, Finance & HR3,836
- Legal & Compliance1,617
- Education1,065
- Media & Creative4,286
- Mobile2,765
- Product & Project Management2,360
- Knowledge Management1,433
- Game Development1,673