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.
-
coreindustries Skill ReviewMulti-perspective code review against project standards with P1/P2/P3 severity classification. Works in Claude Code (Agent + optional GitHub MCP) and Cursor (Task subagents + gh/git). Use when the user invokes /review, asks for a PR or diff review, or wants a standards-aligned review with severity tags.
-
coreindustries Skill HandoffWrite a structured handoff at session end. Preserves context so the next agent can resume without human briefing. Invoke before ending any feature session longer than 30 minutes.
-
claude-world-director-mode-lite Skill MCP CheckValidate MCP configuration and suggest improvements. Use when MCP servers fail to load, after editing .mcp.json, or when the user runs /mcp-check.
-
claude-world-director-mode-lite Skill Doc WriterDocumentation templates and standards: README structure, API reference format, changelog (Keep a Changelog), and comment guidelines. Use when creating or updating documentation. Loaded automatically by the doc-writer agent.
-
claude-world-director-mode-lite Skill Agent CheckValidate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when an agent fails to load.
-
claude-world-director-mode-lite Skill Code ReviewerCode review knowledge base: quality, security (OWASP Top 10), error-handling, performance, and test-coverage checklists with severity-ranked output format. Use when reviewing code changes, PRs, or before commits. Loaded automatically by the code-reviewer agent.
-
claude-world-director-mode-lite Skill Agent TemplateGenerate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.
-
u9401066-pubmed-search-mcp Skill Tool SyncAuto-sync MCP tool documentation when tools are added, removed, or renamed. Triggers: TS, tool-sync, 工具同步, 同步工具, sync tools, new tool, 新增工具, 工具變更, update tools.
-
u9401066-pubmed-search-mcp Skill LLM Wiki BuilderBuild or refresh Foam-compatible LLM wikis from Zotero, PubMed, documents, and local Markdown notes using a multi-tool workflow.
-
u9401066-pubmed-search-mcp Skill Pubmed Pico SearchAgent-guided PICO clinical question search using validate_pico_plan handoff and unified_search. Triggers: PICO, 臨床問題, A比B好嗎, treatment comparison, clinical question, 療效比較
-
u9401066-pubmed-search-mcp Skill PDF Asset ExtractorMCP tools for PDF ingestion → extract figures, tables, sections → build knowledge graph. Transforms PDF into queryable assets (images, tables, text) with cross-document RAG. Triggers: PDF, ingest, extract, 圖片, 表格, figure, table, manifest, knowledge graph, 知識圖譜, RAG, 文獻分析.
-
gapfdev Bundle Github FlowHow to detect GitHub CLI and set up a full GitHub-based development workflow
-
gapfdev Bundle Manager LogHow to maintain a lightweight work log for Manager Agents to track high-level decisions during project execution. Use when you need to document key choices, rationale, and project status manually throughout the workflow.
-
gapfdev Skill Tdd WorkflowHow to implement features using Test Driven Development (Red-Green-Refactor)
-
gapfdev Skill Agent HandoffHow to manage transitions between agent roles and generate handoff prompts for new threads
-
gapfdev Skill QA ValidationHow to validate features through functional testing and produce a validation report
-
gapfdev Bundle Security GateEnforce Security Gates A/B/C across architecture, PR review, and release sign-off using severity-based blocking rules.
-
gapfdev Bundle Tech AnalysisHow to map product features to technical solutions and define a tech strategy
-
gapfdev Skill Gh Pr CloseoutStandardize PR closure workflow for GitHub tickets with required linkage, test evidence, and issue close-out comments. Use when finishing implementation and preparing to close a ticket.
-
gapfdev Skill Visual SummaryHow to present deliverable information as visually appealing ASCII summaries
-
gapfdev Skill Manager HandoffStandardizes the creation of "Source of Truth" Markdown briefs in .agent/temp for assigning tasks to Developer Agents.
-
u9401066-pubmed-search-mcp Skill Zotero Keeper HarnessCline harness for Zotero Keeper and the bundled VS Code extension. Triggers: zotero keeper, zotero mcp, full check, release checklist, workflow, vsix, Cline.
-
u9401066-pubmed-search-mcp Skill Asset Aware MCP HarnessCline harness for this repo (rules + workflows + checks). Triggers: cline harness, full check, release checklist, workflow, 文檔工作流, DFM, citation-ready.
-
u9401066-pubmed-search-mcp Skill Pubmed MCP Tools ReferenceComplete reference for all 41 PubMed Search MCP tools. Triggers: 工具列表, all tools, 完整功能, tool reference, 有哪些工具
-
kenneth-liao Bundle ManageManage scheduled Claude Code tasks — add (recurring or one-off), list, pause, resume, remove, view results, and test execution of skills, prompts, and scripts with safety controls and notifications. Use when the user mentions scheduling, cron, automated tasks, recurring tasks, background tasks, running something on a schedule, periodic execution, or wants a skill/prompt/script to run automatically at a set time. Cross-platform (macOS, Linux, Windows).
-
gapfdev Skill QA Release GateEnforce QA final gate for milestone release with dependency verification, full matrix execution, and sign-off reporting. Use when QA must wait for implementation tickets to close before validating release readiness.
-
gapfdev Skill Gh Ticket RunnerExecute one GitHub ticket end-to-end with a consistent operational contract (STARTED, BLOCKED, DONE), evidence posting, and closure hygiene. Use when an agent picks up a specific issue for implementation.
-
gapfdev Bundle Github Board OpsOperate GitHub Projects boards with clear status flow, entry/exit policies, field hygiene, and automation rules. Use when configuring a board, running daily execution, or fixing status drift across tickets.
-
gapfdev Skill Project ScaffoldHow to initialize a project repository with proper structure and configuration
-
gapfdev Skill External TrackingHow to support non-GitHub tracking systems (Jira, Linear, Trello, Asana) via manual sync
-
gapfdev Skill Ralph Wiggum LoopHow to enforce local self-correction (linting, compiling, testing) before requesting peer review. Use when an agent finishes coding a feature and needs to validate it locally to ensure it is grammatically and syntactically flawless.
-
gapfdev Skill UI Design PreviewGenerate visual UI mockups from product vision for human review before development begins
-
gapfdev Skill Knowledge GardenerHow to automatically audit the docs/ directory and remove/archive outdated Markdown files to prevent agent context rot at the end of a sprint. Use during Step 7 (Release) or when finalizing a milestone.
-
gapfdev Skill Milestone WatchdogMonitor milestone execution health by detecting stale tickets, blocked queues, missing ownership signals, and timeline risk. Use during active delivery windows to keep work moving and escalate risks early.
-
gapfdev Bundle Agent CommunicationHow to coordinate between multiple AI agents working simultaneously on the same project through a shared message board. Use when agents need to post status updates, log decisions, ask questions, or report blockers.
-
gapfdev Skill Agents Md GeneratorHow to generate a lightweight AGENTS.md table of contents file to provide progressive disclosure of the repository to other agents. Use when scaffolding a new project or updating core architectural boundaries.
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 review, handoff, mcp-check. 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.