Best AI and LLM engineering skills, page 90

Operate NEAR JSON-RPC reads through UXC with a public provider default, provider-override guidance, and read-only guardrails.

holon-run/uxc

Operate Sui public JSON-RPC through UXC with OpenRPC-driven discovery, mainnet fullnode defaults, and read-only query plus pubsub subscription guardrails.

holon-run/uxc

Before any explanation or answer, require the learner to produce a free-recall attempt and confidence rating.

GarethManning/education-agent-skills

After the learner demonstrates understanding of a concept, present near-transfer and far-transfer challenges.

GarethManning/education-agent-skills

After scaffolded practice, run an unassisted check with no AI help.

GarethManning/education-agent-skills

Build a library of metacognitive prompts targeting planning, monitoring, or evaluation for a specific task.

GarethManning/education-agent-skills

Stage exploration before instruction on complex problems. An agent skill from GarethManning/education-agent-skills.

GarethManning/education-agent-skills

The learner teaches the concept to the AI, which plays a curious novice peer and identifies gaps through authentic questions.

GarethManning/education-agent-skills

Build conversational multi-agent systems with Microsoft AutoGen.

magnus919/agent-skills

Build role-based multi-agent systems with CrewAI. An agent skill from magnus919/agent-skills.

magnus919/agent-skills

Optimize and build programmatic prompt systems with Stanford DSPy.

magnus919/agent-skills

Build production search and NLP pipelines with Haystack. An agent skill from magnus919/agent-skills.

magnus919/agent-skills

Operate, configure, secure, and troubleshoot the LiteLLM AI gateway (proxy) and Python SDK: run the proxy (litellm --config), route to 100+ providers through one OpenAI-compatible API, configure…

magnus919/agent-skills

Design, integrate, evaluate, self-host, and troubleshoot typed System One decision models including TypeSafe Jev, Convai Innovations Laya, CLM, and experimental Strands Decider.

magnus919/agent-skills

Operate, configure, benchmark, and troubleshoot vLLM inference servers: Docker and Kubernetes deployment, quantization-aware model configuration (tensor parallelism, KV cache), OpenAI-compatible API…

magnus919/agent-skills

Compare Triton, TLX, and inductor kernel numerics across A/B compiler builds with per-config isolation tests and grouped impact reporting.

facebookexperimental/triton

Loads when the agent calls delegate({...}) for a non-trivial sub-task.

friday-platform/friday-studio

How to read and write Friday memory stores correctly: store selection, terse entry format, large-content artifact pattern, and what's auto-injected into the system prompt.

friday-platform/friday-studio

Compact one or more Spec-Driven Development artifacts in place to reduce token cost on subsequent /speckit.

haru/redmine_ai_helper

Build a focused reading manifest for the next workflow step.

haru/redmine_ai_helper

Show token usage for every SDD artifact in the active feature, the projected context window for each upcoming phase, and the savings already realized by token-budget (full backups vs current files).

haru/redmine_ai_helper

Summarizes arbitrarily long text (1k-1M words) using recursive map-reduce with any LLM backend.

swyxio/skills

Transcribes audio and video files to text using pluggable ASR backends.

swyxio/skills

A skill your agent uses when image reading, screenshot analysis, visual diff, design mockup analysis, pasted image handling, or Z.AI Vision MCP fails, times out, returns 429/Too Many Requests, or…

skuramatata/my-pi-agent

Analyze SharePoint project content and project lists to produce a concise project health assessment covering schedule, risks, actions, decisions, and documentation.

pnp/sharepoint-skills

AI 评测工程专家 Owner — 当任务涉及模型/Prompt 评测、模型选择、黄金集、评分量表、LLM-as-judge、Judge 校准、重复采样、方差、质量-成本-延迟权衡、提示词回归或模型升级回归时使用；要求把概率性结果转化为可复现、可比较且防污染的评测证据。

devcodex-labs/devcodex

Tmux skill for running background tasks. An agent skill from archibate/dotfiles-opencode.

archibate/dotfiles-opencode

优化实际模型推理链路，将正确性对齐、分段 profiling、显存与数据搬运、TensorRT/ONNX/PyTorch 后端、attention/kernel、FP8/compile、缓存与少步采样、质量回归、GPU 成本和服务验收串成同一实验闭环。当用户要求推理提速、降低显存或 GPU 成本、复现模型效果、定位 GPU 利用率低、优化图像/视频/扩散模型或自托管 LLM 时使用，提供…

majiayu000/spellbook

Download Douyin (TikTok) videos from share links. An agent skill from OpenMinis/MinisSkills.

OpenMinis/MinisSkills

Reference skill for the OpenHands Software Agent SDK - the Python framework for building AI agents that write software.

OpenHands/extensions

LLM API 使用成本优化模式——基于任务复杂度的模型路由、预算跟踪、重试逻辑和提示词缓存. An agent skill from xu-xiang/everything-claude-code-zh.

xu-xiang/everything-claude-code-zh

适用于 Claude Code 会话的正规评测框架（Evaluation Framework），实现了评测驱动开发（Eval-Driven Development, EDD）原则

xu-xiang/everything-claude-code-zh

为 Claude Code 会话提供的正式评测框架，实现了评测驱动开发（EDD）原则. An agent skill from xu-xiang/everything-claude-code-zh.

xu-xiang/everything-claude-code-zh

Create Agent Bricks: Knowledge Assistants (KA) for document Q&A and Supervisor Agents for multi-agent orchestration (MAS).

databricks/databricks-agent-skills

Use Databricks built-in AI Functions (aiclassify, aiextract, aisummarize, aimask, aitranslate, aifixgrammar, aigen, aianalyzesentiment, aisimilarity, aiparsedocument, aiprepsearch, aiquery…

databricks/databricks-agent-skills

Databricks Vector Search endpoints and indexes for RAG and semantic search; covers index types, search modes, end-to-end RAG patterns

databricks/databricks-agent-skills

Author and validate hermetic single-tool Vally evals under evals/tools.

Azure/azure-sdk-tools

Author and validate multi-tool, multi-turn, mock, and live Vally scenarios under evals/workflows.

Azure/azure-sdk-tools

Run isolated eval and grading calls using CC 2.1.81 --bare mode.

yonatangross/orchestkit

Evals-first error analysis for LLM apps: clusters real Langfuse or JSONL traces into a human-confirmed failure taxonomy with counts, then recommends binary pass/fail evals for recurring named modes.

yonatangross/orchestkit

LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner).

yonatangross/orchestkit

Clay workflows — reduce a workflow's credit and LLM cost via the CLI (clay workflows commands).

clay-run/agent-plugins

A skill your agent uses when targeting ACM Conference on Fairness, Accountability, and Transparency (FAccT) or deciding whether a computer-science manuscript fits this venue.

franklee16/academic-research-skills

A skill your agent uses when targeting Annual Meeting of the Association for Computational Linguistics (ACL) or deciding whether a computer-science manuscript fits this venue.

franklee16/academic-research-skills

A skill your agent uses when targeting Asian Conference on Computer Vision (ACCV) or deciding whether a computer-science manuscript fits this venue.

franklee16/academic-research-skills

A skill your agent uses when executing and reporting the analysis for an American Sociological Review (ASR) manuscript so it survives expert masked review — honest uncertainty, robustness, and…

franklee16/academic-research-skills

A skill your agent uses when handling data documentation, sharing, and confidentiality for an American Sociological Review (ASR) manuscript.

franklee16/academic-research-skills

A skill your agent uses when positioning an American Sociological Review (ASR) manuscript against the literature so it reads as a broad sociological contribution rather than a subfield note.

franklee16/academic-research-skills