数据处理
数据转换、清洗与 ETL
evaluating-code-models
davila7
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.
llamaindex
davila7
Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.
ray-data
davila7
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.
deepspeed
davila7
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
model-pruning
davila7
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
moe-training
davila7
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
evaluating-llms-harness
davila7
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
immune
Mathews-Tom
'Hybrid adaptive memory: Cheatsheet (positive patterns pre-generation) and Immune (negative patterns post-generation) with Hot/Cold tiered auto-learning. Triggers on: "scan for errors", "immune scan", "check output quality", "antibody scan". NOT for PR review (use pr-review) or repo audits (use repo-sentinel).'
prompt-lab
Mathews-Tom
'LLM prompt engineering: analyzes failure modes, generates variants (direct, few-shot, CoT), designs rubrics, produces test suites. Triggers on: "prompt engineering", "generate prompt variants", "A/B test prompts", "optimize prompt", "improve this prompt". NOT for SKILL.md files, use skill-evaluator.'
manuscript-provenance
Mathews-Tom
'Computational provenance audit verifying every number, table, and figure in a manuscript derives from code, not manual entry. Triggers on: "check provenance", "verify reproducibility", "audit my pipeline", "are my numbers from code", "provenance audit". Companion to manuscript-review (prose audit).'
mongodb-usage
fcakyon
This skill should be used when user asks to "query MongoDB", "show database collections", "get collection schema", "list MongoDB databases", "search records in MongoDB", or "check database indexes".
agent-browser
EveryInc
Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Alternative to Playwright MCP - uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click button", "take screenshot", "scrape page", "web automation".
dspy-ruby
EveryInc
Build type-safe LLM applications with DSPy.rb — Ruby's programmatic prompt framework with signatures, modules, agents, and optimization. Use when implementing predictable AI features, creating LLM signatures and modules, configuring language model providers, building agent systems with tools, optimizing prompts, or testing LLM-powered functionality in Ruby applications.
angular-component
zard-ui
Create modern Angular standalone components following v20+ best practices. Use for building UI components with signal-based inputs/outputs, OnPush change detection, host bindings, content projection, and lifecycle hooks. Triggers on component creation, refactoring class-based inputs to signals, adding host bindings, or implementing accessible interactive components.
configuring-dbt-mcp-server
dbt-labs
Use when setting up, configuring, or troubleshooting the dbt MCP server for AI tools like Claude Desktop, Claude Code, Cursor, or VS Code.
migrating-dbt-project-across-platforms
dbt-labs
Use when migrating a dbt project from one data platform or data warehouse to another (e.g., Snowflake to Databricks, Databricks to Snowflake) using dbt Fusion's real-time compilation to identify and fix SQL dialect differences.
skills
UiPath
This is a repository of skills for interfacing UiPath capabilities to external developers.
react-patterns
rohitg00
React 19 patterns including Server Components, Actions, Suspense, hooks, and component composition
data-engineering
rohitg00
Data engineering patterns for ETL pipelines, data warehousing, Apache Spark, and data quality validation
prompt-engineering
rohitg00
Prompt engineering patterns including structured prompts, chain-of-thought, few-shot learning, and system prompt design
excel-mcp
sbroenne
Automate Microsoft Excel on Windows via COM interop. Use when creating, reading, or modifying Excel workbooks. Supports Power Query (M code), Data Model (DAX measures), PivotTables, Tables, Ranges, Charts, Slicers, Formatting, VBA macros, connections, and calculation mode control. Triggers: Excel, spreadsheet, workbook, xlsx, Power Query, DAX, PivotTable, VBA.
sglang
davila7
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.
nemo-curator
davila7
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
ljg-present
lijigang
"高桥流（Takahashi Method）演示生成器。把一段文本的思想提炼成节拍，一页一个关键词，字撑满屏，浏览器全屏即开讲。使用时用户会说：'高桥流'、'讲这个'、'present'、'做成演讲'、'做个高桥流 PPT'、'把这个讲出来'、'呈现一下'、'铸成演示'、'做个 slides'、'把这段讲成高桥流'。输出单文件 HTML 到 ~/Downloads/。"