GITHUB AGENT SKILLS / 技能收录
给你的 AI 助手
装上专业技能
我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
excalidraw
Generates Excalidraw diagrams programmatically as hand-drawn-style JSON. Use when creating architecture diagrams, flowcharts, or hand-drawn-style visuals for documentation, or when converting existing diagrams to editable Excalidraw JSON.
rag-engineering
Retrieval-Augmented Generation pipelines — ingestion, chunking, embedding, vector stores, retrieval, evaluation. Use when building a RAG pipeline, choosing chunking strategies or embedding models, debugging retrieval quality or hallucinations, evaluating an existing RAG system, or scaling/migrating vector stores.
prompt-engineering
Prompt design patterns — few-shot, chain-of-thought, structured output, injection defense. Use when crafting or refining LLM prompts, designing system prompts for agents, requesting structured output, defending against prompt injection, building reusable prompt templates, or iterating on prompt quality.
pandas-polars
DataFrame operations with pandas and polars — groupby, joins, reshaping, performance. Use when manipulating tabular data, choosing between pandas and polars, optimizing DataFrame code, or translating between the two libraries.
ml-pipeline
ML pipeline design — data versioning, experiment tracking, deployment patterns, drift monitoring. Use when building an ML pipeline from data to deployment, setting up MLOps tooling (DVC, MLflow, model registry), choosing deployment patterns (shadow, canary, A/B), or designing monitoring for drift and degradation.
llm-evaluation
LLM output evaluation — automated metrics, LLM-as-judge, A/B testing, regression testing. Use when measuring LLM output quality, comparing prompt or model versions, building an automated eval pipeline, setting up regression tests for prompt changes, or evaluating RAG systems and bias/safety.
feature-engineering
Feature engineering for ML — encoding, imputation, scaling, selection, time-series features. Use when preparing data for an ML model, encoding categoricals, handling missing data, building time-series features, or selecting features from a wide table.
embedding-vectordb
Vector embeddings and vector DB patterns — model choice, similarity metrics, index tuning. Use when choosing an embedding model, picking or migrating between vector databases, optimizing semantic search quality or latency, or building a hybrid (dense + sparse) retrieval pipeline.
data-science
Data analysis workflow from import through modeling and communication. Use when analyzing a dataset, exploring data, building a statistical model, selecting features, or communicating findings to stakeholders.
data-quality
Data quality framework — completeness, accuracy, consistency, validation, and contracts. Use when implementing data validation, setting up quality checks for a pipeline, defining data contracts between teams, or investigating data anomalies.
scientific-writing
This is the core skill for the deep research and writing tool—combining AI-driven deep research with well-formatted written outputs. Every document produced is backed by comprehensive literature search and verified citations through the research-lookup skill.
data-pipeline
Data pipeline patterns — ETL/ELT, batch vs streaming, idempotency, orchestration. Use when designing a data pipeline, choosing between batch and streaming, implementing ingestion or transformation, setting up orchestration, or debugging pipeline failures.
ai-fundamentals
Explain and apply core ML/AI concepts — model types, training pipelines, evaluation metrics, and neural architectures.
user-research
Structures user research — planning sessions, synthesizing findings, and translating insights into product decisions. Use when planning user interviews, analyzing research data, creating personas or journey maps, or turning qualitative feedback into structured recommendations.
sprint-retrospective
Facilitates team or project retrospectives — what worked, what didn't, action items. Use at the end of a sprint, milestone, or project phase to reflect on what went well, what didn't, and what to try next.
research-with-confidence
Investigates a question systematically before answering — verifying claims through sources, distinguishing known facts from inferences, and calibrating expressed confidence to actual certainty. Use when asked to research a topic, verify a claim, evaluate a technology, or answer a question where accuracy matters more than speed.
prd-writing
Write a Product Requirements Document structured with problem statement, goals, user stories, scope, and success metrics.
onboarding-guide
Generates a structured onboarding guide for a new agent or human joining a project — covering codebase orientation, process context, first tasks, and key contacts. Use when asked to onboard someone new, write a getting-started guide, or create a "first week" plan for a project.