Best AI and LLM engineering skills, page 104

Retrieve relevant information from a knowledge base using semantic, keyword, or hybrid search to ground a query.

seb1n/awesome-ai-agent-skills

Train machine learning models end-to-end, covering data loading, preprocessing, architecture selection, training loops, validation, and checkpointing.

seb1n/awesome-ai-agent-skills

Compress selected context to a target token budget while preserving decisions, evidence, constraints, and unresolved questions.

seb1n/awesome-ai-agent-skills

Define deterministic guardrails for agent tool calls — protected paths, test-file locks during bug fixes, post-edit formatters, production approval gates, secret deny rules.

HoangNguyen0403/agent-skills-standard

After any AI-generated explanation, require the learner to identify one place it could be wrong, one thing to check, and one source to consult.

GarethManning/education-agent-skills

Design structured perspective-taking activities with anti-projection guardrails.

GarethManning/education-agent-skills

Provide graduated assistance from abstract conceptual nudge to concrete procedural step, with reflection required before each escalation.

GarethManning/education-agent-skills

Transcribe audio via OpenAI Whisper, Atlas Cloud, or MuAPI speech-to-text APIs.

CoWork-OS/CoWork-OS

Require the learner to explain a concept in their own words before the AI evaluates or extends it.

GarethManning/education-agent-skills

Wrap a learning session in a plan → monitor → reflect cycle.

GarethManning/education-agent-skills

When a learner gets something wrong or feels stuck, require them to diagnose the problem before receiving help.

GarethManning/education-agent-skills

Review the week using accumulated session evidence — retrieval rates, hint depths, calibration accuracy, transfer and unassisted results.

GarethManning/education-agent-skills

A skill your agent uses when creating, reviewing, or editing Agent Skills-format skills, or when implementing skill discovery and loading in an agent client.

magnus919/agent-skills

Build LLM applications with LangChain. An agent skill from magnus919/agent-skills.

magnus919/agent-skills

Operate, configure, benchmark, and troubleshoot llama.cpp across CPU, Metal, CUDA, HIP/ROCm, Vulkan, SYCL, and hybrid or multi-GPU systems.

magnus919/agent-skills

Build LLM applications with the LlamaIndex framework. An agent skill from magnus919/agent-skills.

magnus919/agent-skills

Plan and execute production ML engineering work — model training and fine-tuning (LoRA/QLoRA), evaluation and eval-set design, quantization decisions, inference deployment, lineage, feature parity…

magnus919/agent-skills

Run end-to-end product experiments from assumption to decision: translate assumptions into testable hypotheses and experiment briefs, select the right method among qualitative interviews…

magnus919/agent-skills

Build type-safe AI agents and graph-based workflows with PydanticAI and PydanticGraph.

magnus919/agent-skills

This skill should be used when the user asks about "gross to net", "GtN erosion", "net price assumption", "rebate pressure", "list vs net", "IRA maximum fair price impact", or wants to build or…

hh-health-AI/healthcare-equity

This skill should be used when the user asks about "Japan pricing", "NHI price", "Chuikyo", "MHLW", "PMDA", "Japanese reimbursement", "price revision", "foreign average price", or is modelling…

hh-health-AI/healthcare-equity

Prompt format rules for generative video and music models. An agent skill from sammcj/agentic-coding.

sammcj/agentic-coding

Offline experimental post-call feedback scorer using supplied ratings and text heuristics.

CALLE-AI/awesome-phone-call-agents

Offline experimental CALL-E transcript auditor that grades a returned transcript RELIABLE, SUSPECT, or UNUSABLE from text-visible ASR-hallucination symptoms before anything acts on it, and crafts…

CALLE-AI/awesome-phone-call-agents

Monitor business phone lines and deployed voice agents with LineCanary — scheduled CALL-E test calls that walk the caller journey, assert structured results, diff against baselines and alert on…

CALLE-AI/awesome-phone-call-agents

OI-3 spike harness — heavy consumer, ADVERSARIAL arm. An agent skill from testdouble/han.

testdouble/han

Guidance for Microsoft Defender for Endpoint (MDE) — enterprise endpoint security with next-gen AV, EDR, attack surface reduction (ASR), Defender Vulnerability Management, automated investigation…

vinayaklatthe/microsoft-security-skills

Build machine vision inspection systems with MATLAB Visual Inspection Toolbox.

matlab/matlab-agentic-toolkit

Reviews Claude Code agent definition files for tool-access security, triggering quality, and system prompt clarity.

bitwarden/ai-plugins

Use as the entry point for any American Sociological Review (ASR) manuscript.

franklee16/academic-research-skills

Implement AI chatbot analytics and conversation monitoring. An agent skill from curiositech/some_claude_skills.

curiositech/some_claude_skills

Selects the optimal LLM model and provider for each task based on complexity, cost budget, and capability requirements.

curiositech/some_claude_skills

Tracks cumulative LLM costs across DAG execution and makes real-time decisions to stay within budget.

curiositech/some_claude_skills

This package enables the interpretation and analysis of results from a gene set enrichment analysis using network-based and text-mining approaches.

bioMate-AI/biomate-bioconductor-kb

UMAP dimensionality reduction for visualization, clustering prep, and feature engineering.

jaechang-hits/SciAgent-Skills

Create AI agents and workflows using Microsoft Agent Framework SDK.

aiskillstore/marketplace

Master protocol for deconstructing agent frameworks to inform derivative system architecture.

aiskillstore/marketplace

Comprehensive framework for analyzing, creating, and refining prompts for AI systems.

aiskillstore/marketplace

Master Cohere v2 Chat API with Python, specializing in entity extraction using JSON Schema mode for structured outputs.

aiskillstore/marketplace

Operate a Famulor workspace through its hosted MCP server, including assistants, conversation history, campaigns, messaging, telephony, knowledge, dashboards, automations, billing, settings…

aiskillstore/marketplace

Creates custom output styles for Claude Code that modify system prompts and behavior.

aiskillstore/marketplace

使用本地 BiRefNet GGUF 模型完成图片或视频抠图、人物抠图、主体分割和背景移除，并输出透明 PNG、MOV 或 WebM。适用于用户提到图片抠图、照片去背景、人像透明图、视频抠图、透明视频、BiRefNet、JPG/PNG/BMP/WebP 图片，或 MP4/MOV/WebM 视频的场景；无需 Python、PyTorch 或 CUDA。

aiskillstore/marketplace

Integrate applications with RouterBase, the OpenAI-compatible model gateway at https://routerbase.com/v1.

aiskillstore/marketplace

Choose RouterBase model IDs and routing strategies for chat, image, video, audio, and embeddings workloads.

aiskillstore/marketplace

A skill your agent uses when routing Claude Code through a local LiteLLM proxy to GitHub Copilot, reducing direct Anthropic spend, configuring ANTHROPICBASEURL or ANTHROPICMODEL overrides, or…

aiskillstore/marketplace

A skill your agent uses when calling the Scanlume OCR API for screenshots, JPG, PNG, or image-based tables, especially when a task needs base64 data URLs, mode selection between simple and formatted…

aiskillstore/marketplace

Create specialized Claude Code agents on-the-fly. An agent skill from aiskillstore/marketplace.

aiskillstore/marketplace

Master SurrealDB 2.3.x with Python for multi-model database operations including CRUD, graph relationships, vector search, and real-time queries.

aiskillstore/marketplace