AI & ML
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
-
tristan-hauber Bundle Quick Code Review 2Budget-aware code review for the current diff, a PR number, a branch, or a path. A lighter, cost-capped alternative to /code-review's multi-agent fan-out — use when you want a review but want to control token spend, or after /code-review has burned through budget without finishing.
-
prince-vince Skill QAInteractive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".
- prince-vince Skill Write A Skill
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
-
samraddhashrivastavatech Skill Comparison 2comparison
- samraddhashrivastavatech Skill Web Reader 2
web-reader
- samraddhashrivastavatech Skill Web Search 2
web-search
- samraddhashrivastavatech Skill Android Screen 2
android_screen
- samraddhashrivastavatech Skill Android Vision 2
android_vision
- samraddhashrivastavatech Skill Code Search 2
code-search
- samraddhashrivastavatech Skill Web Crawler 2
web-crawler
- samraddhashrivastavatech Skill Android Control 2
android_control
- samraddhashrivastavatech Skill Android Intents 2
android_intents
-
justin-mc-lai Bundle DistillDistill a trusted, durable source — a classic book, paper, codebase, docs set, transcript, or interview — into a reusable, invokable agent skill. Use when the user wants to turn a book/PDF/paper/repo/docs/transcript into a skill (book-to-skill, 书籍转 skill, 把资料变成 skill), wants to ground agent answers in a verified source instead of model priors, or wants the QBS method (Question to Book to Skill). Trigger on distill, source-to-skill, QBS, 蒸馏, 把书变成 skill, 资料转 skill, 经典来源, 用书解决问题. Does not download copyrighted material or automate z-library—acquisition stays user-side. Does not write the distilled method from the model's own memory; the method must come from the source.
-
haldata-net Bundle New Category Research新しく参入・仕入れを検討しているカテゴリの下調べを、Ahrefs（検索需要と難易度）→ Google Trends（季節性と伸び）→ Keepa（上位商品の価格帯・評価・順位）→ TrendViewer（レビューで不満が集中している観点）の順に集めて1枚の比較表と判断メモにする。ユーザーが「新規カテゴリの市場調査をしたい」「参入すべきカテゴリを比べたい」「この商品ジャンルは需要があるか」「競合の価格帯と不満点を知りたい」「仕入れ候補の下調べ」と言ったとき、また候補カテゴリ名を複数挙げて比較を頼まれたときは、MCP名が出ていなくてもこのスキルを使うこと。
- haldata-net Bundle Ad Copy From Review Stats
Google広告の検索キャンペーンで「どの訴求が刺さるか」を担当者の勘でなく実購入者レビューの統計で決める。Google Ads MCP で CTR・コンバージョンの低い広告グループ（検索語）を絞り、TrendViewer MCP でそのカテゴリのレビューから購買動機になっている観点を選び、その言葉を使った見出し案を各5本作る。ユーザーが「広告の訴求軸を決めたい」「広告文の見出し案が欲しい」「CTRの低い広告グループを直したい」「レビューをもとに広告コピーを作りたい」「レスポンシブ検索広告の見出しを増やしたい」と言ったとき、また Google Ads と TrendViewer が接続された状態で広告の改善を頼まれたときは、「レビュー」という語が無くてもこのスキルを使うこと。
- prince-vince Skill Firecrawl Agent
AI-powered autonomous data extraction that navigates complex sites and returns structured JSON. Use this skill when the user wants structured data from websites, needs to extract pricing tiers, product listings, directory entries, or any data as JSON with a schema. Triggers on "extract structured data", "get all the products", "pull pricing info", "extract as JSON", or when the user provides a JSON schema for website data. More powerful than simple scraping for multi-page structured extraction.
- prince-vince Skill Firecrawl Scrape
Extract clean markdown from any URL, including JavaScript-rendered SPAs. Use this skill whenever the user provides a URL and wants its content, says "scrape", "grab", "fetch", "pull", "get the page", "extract from this URL", or "read this webpage". Handles JS-rendered pages, multiple concurrent URLs, and returns LLM-optimized markdown. Use this instead of WebFetch for any webpage content extraction.
- prince-vince Skill Ubiquitous Language
Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".
- samraddhashrivastavatech Skill PDF Research 2
pdf-research
- samraddhashrivastavatech Skill Android Recovery 2
android_recovery
- samraddhashrivastavatech Skill Deep Research 2
deep-research
- samraddhashrivastavatech Skill Fact Checking 2
fact-checking
- samraddhashrivastavatech Skill News Research 2
news-research
- samraddhashrivastavatech Skill Query Builder 2
query-builder
- samraddhashrivastavatech Skill Android Discovery 2
android_discovery
- samraddhashrivastavatech Skill Android Messaging 2
android_messaging
- samraddhashrivastavatech Skill Github Research 2
github-research
- samraddhashrivastavatech Skill Knowledge Graph 2
knowledge-graph
- samraddhashrivastavatech Skill Query Expansion 2
query-expansion
- samraddhashrivastavatech Skill Source Analysis 2
source-analysis
-
orcaqubits Skill Ucp Ap2 Mandates 2Implement UCP AP2 Mandates extension — cryptographic payment mandates for fully autonomous agent commerce using SD-JWT credentials, merchant authorization signatures, and the Agent Payments Protocol. Use when building autonomous agent payment flows without human-in-the-loop.
- orcaqubits Skill Ucp Checkout A2a 2
Implement UCP Checkout over the A2A (Agent-to-Agent) binding — enable autonomous agent-to-agent commerce using Agent Cards and structured message parts. Use when building agent-to-agent commerce flows.
- orcaqubits Skill Nlweb Setup 2
Bootstrap a local NLWeb development environment from scratch — clone the repo, configure .env, install Python deps via `nlweb init-python`, run `nlweb init` for interactive LLM/retrieval selection, load sample Schema.org data, and verify with `nlweb check`. Use when starting a new NLWeb deployment from zero.
- samraddhashrivastavatech Skill Android Device Info 2
android_device_info
- samraddhashrivastavatech Skill Query Refinement 2
query-refinement
- samraddhashrivastavatech Skill Search Operators 2
search-operators
Frequently asked questions
What are AI & ML agent skills?
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
Which AI & ML skills are most installed?
Popular AI & ML skills on SkillMD right now include quick-code-review, qa, write-a-skill. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do AI & ML skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.