MCP servers and skills: search, filter by where they run, and compare.
StructAI offers a robust toolkit for LLM interaction—such as structured outputs, context management, and parallel execution.
SkillMIT★ 8No key
Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop
OfficialSkillMIT★ 40k in collectionNo key
Downloads, exports, and inspects existing Arize traces and spans to understand what an LLM app is doing or debug runtime issues. Covers exporting traces by ID, spans by ID, sessions by ID, and root-ca
OfficialSkillMIT★ 40k in collectionNo key
Agent skill for current LLM selection using Artificial Analysis and OpenRouter data: quality, price, speed, context, slugs, and free-tier options. Refreshed daily.
SkillMIT★ 3Few starsNo key
Claude/agent skill: build LLM training data from YouTube transcripts in bulk (Apify)
SkillLink onlyFew stars
Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container when no dedicated TAO model skill matches. Use when the user wants to fine-tune a HuggingFace model
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Turn on AI + ML features in Grafana Cloud — Grafana Assistant (NL → PromQL/LogQL/TraceQL, dashboard build, incident investigation, MCP integration), Dynamic Alerting (Prophet forecasting + DBSCAN outl
OfficialSkillApache-2.0★ 285 in collectionNo key
Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level captions, structured descriptions, and QA pairs (MCQ, binary, open-ended) with reasoning tr
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Claude Code and Codex skills for empirical applied-micro research: reproducibility auditing, LLM-pipeline methods, event studies, WRDS, Stata, publication-grade tables
SkillMIT★ 22No key
Audits Python + BigQuery pipelines for cost safety, idempotency, and production readiness. Returns a structured report with exact patch locations.
OfficialSkillMIT★ 40k in collectionNo key
Dingo: A Comprehensive AI Data, Model and Application Quality Evaluation Tool
SkillApache-2.0★ 758No key
Go-to-market strategy for AI products. Use when positioning AI products, handling "who is responsible when it breaks" objections, pricing variable-cost AI, choosing between copilot/agent/teammate fram
OfficialSkillMIT★ 40k in collectionNo key
Turn Claude into a disciplined research analyst — verify facts against primary sources, brief any topic, draft flagship reports. Standalone or chained; runs across LLM terminals. | 把 Claude 变成讲纪律的研究分析
SkillMIT★ 63No key
Daily digest of interesting arXiv papers — an unattended LLM pipeline for cron, plus a zero-dependency agent skill your AI agent runs itself
SkillMIT★ 22No key
Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when generating synthetic user scenarios, evaluating an agent or model, build
OfficialSkillApache-2.0★ 21k in collectionNo key
Use when running video data augmentation and auto-labeling workflows on OSMO: flow selection, preflight, submit-time interpolation, monitoring, and output retrieval. Trigger keywords: video data augme
OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key
Configure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load balancing, AI model governance, MCP rate limiting, jailb
OfficialSkillMIT★ 1.6k in collectionNo key
AI-powered personalized IELTS corpus distillation — install-only skill (zero-backend Agent loop) + runnable backend with QMD-RAG. 7-stage pipeline producing schema-validated corpus.json & static profi
SkillMIT★ 33No key
Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use when a user needs to get started with PAIDF Auto-Labeling, plan a scenario, run or debug a shipped cookbook, author prompts or cookbooks, migrate a pipeline, or configure a stage. Confirm critical
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Unofficial Python API and agentic skill for Google Gemini Notebook. Full programmatic access to Gemini Notebook's features—including capabilities the web UI doesn't expose—via Python, CLI, and AI agen
SkillMIT★ 20kNo key
Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline). Use when the user asks to "integrate a Hugging
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Answer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, AutoML, and platform manifests. Use when the user asks "what can TAO Skill Bank do", "li
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Expand workflow HDF5 demonstrations with action jitter, optionally scoped to node segments. Use for synthetic variants; do not use to collect data, alter state directly, or generate new images.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Who stands behind it
