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.
-
saddss Bundle LLM Serving Capacity PlannerParse SGLang/vLLM startup logs for GPU memory decomposition (weights, KV pool, CUDA graph, overhead) and max-concurrency estimates. Use for KV cache budget, mem-fraction-static tuning, OOM triage, or explaining why concurrency is capped.
- saddss Bundle Perf Nsight Compute Analysis
Analyze ncu (NVIDIA Nsight Compute) profiling output: SOL% bottleneck classification, roofline analysis, occupancy diagnosis, memory hierarchy analysis, warp stall analysis, metric interpretation, and programmatic .ncu-rep report analysis. Use when optimizing CUDA kernels in vLLM / SGLang / TRT-LLM / custom inference ops, or interpreting .ncu-rep for attention / GEMM / KV-cache kernels. NOT for kernel writing, nsys timeline work, or host-side profiling. Triggers also include "SOL 多少" / "ncu 分析".
- saddss Bundle Improve Codebase Architecture
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, make a codebase more testable and AI-navigable, or untangle inference engine / benchmark harness code.
-
xaiht Skill JiraRead and write Jira issues, comments, transitions via the Jira REST API v3.
- xaiht Skill Gmail
Read and send Gmail messages and threads via Gmail API.
- xaiht Skill Slack
Post messages, read channels, and manage threads via Slack Web API.
- xaiht Skill Github
Use the gh CLI for GitHub issues, PR status, CI/logs, comments, reviews, releases, and API queries.
- xaiht Skill Notion
Use the Notion API to create, read, update Notion pages, data sources (databases), and blocks.
- xaiht Skill Trello
Manage Trello boards, lists, and cards via the Trello REST API.
- xaiht Skill Todoist
Manage Todoist tasks and projects via the Todoist REST API v2.
- xaiht Skill Weather
Look up current weather and short forecast for a location via Open-Meteo (no API key required).
- xaiht Skill Summarize
Summarize a long text or file into a tight, faithful brief at a target word count.
- xaiht Skill Acp Router
Route plain-language requests for Claude Code, Cursor, Codex, Gemini, Qwen, Pi, Kiro, Kimi, iFlow, Factory Droid, Kilocode, OpenCode, Copilot into ACPX child sessions via acp_spawn. Pick the right agentId for the user's intent.
- xaiht Skill Code Review
Review a git diff (or working-tree changes) like a senior engineer — correctness, security, performance, readability — and return a verdict plus structured, line-anchored findings.
- xaiht Bundle Flow Making
Turn a natural-language objective into a downloadable .flw workflow by driving the FlowCreator engine (full 89-agent catalog), then emit a canvas-loadable .flw.
- xaiht Skill Hello World
Smoke-test skill that echoes its inputs and confirms the SkillHarness wiring is alive end-to-end.
- xaiht Skill Kali Pentest
Drive an authorized, scoped penetration-testing / recon / CTF workflow against a target through the Kalier agent and the MCP-Kali-Server — health-probe, port/service scan (nmap), service-specific enumeration (gobuster/dirb/nikto/sqlmap/wpscan/enum4linux), credential/hash attacks (hydra/john), optional Metasploit, then a written findings report. Authorized targets only.
- xaiht Skill Roblox Studio
Build and edit in Roblox Studio via the Roblox Studio MCP the RIGHT way - preflight the Studio connection, do the whole build in a few big execute_luau scripts (not dozens of tiny calls), make REALISTIC terrain with the Terrain VOXEL api driven by Perlin noise (NEVER stacked Parts or concentric layers - those give ugly blocky stepped pyramids), poll generative jobs, check the console, and fail honestly. Invoke for ANY "in Roblox / Roblox Studio" request - terrain, mountains, parts, scripts, models, materials, assets.
-
zcweah1981 Bundle Ppt Assistant单 Agent 帮用户把一个主题直接压成“可继续做成 PPT 的整套稿”。
- zcweah1981 Bundle Agile Web QA Agent
你是敏捷 Web 验收专家。你的任务是检查这套 Web 原型是否满足最小开工条件，并输出可执行的页面级验收清单、风险点和缺口。
- zcweah1981 Bundle Agile Web API Agent
你是敏捷 Web 接口设计专家。你的任务是把页面和数据需求压成字段字典、接口约定、请求返回结构和 mock 对接方案。
- zcweah1981 Bundle Agile Web Product Agent
你是敏捷 Web 产品拆解专家。你的任务是把一个 Web 工具需求压成页面清单、关键操作流、状态机、权限矩阵和可交接的产品包。
- zcweah1981 Bundle Agile Web Builder Agent
你是敏捷 Web 前端骨架专家。你的任务是把产品交接物压成目录骨架、页面文件建议、组件建议、状态流转和首批代码开工清单。
- zcweah1981 Bundle Action Plan Assistant
单 Agent 帮用户把一个目标、会议结论或讨论结果直接压成"可执行、可发送的行动计划表"。
- zcweah1981 Bundle Meeting Minutes Assistant
单 Agent 帮用户把一场会议直接压成“可发送、可执行的会议纪要”。
- zcweah1981 Bundle Xiaohongshu Content Assistant
单 Agent 帮用户把一个主题直接压成“可发布小红书内容包”。
- zcweah1981 Bundle Material Summary Assistant
单 Agent 帮用户把一批资料直接压成“可发送、可判断、可继续补的结构化总结”。
- zcweah1981 Bundle Daily Report Assistant
单 Agent 帮用户把一天进展直接压成“可发送、可跟进的项目日报”。
- zcweah1981 Bundle Wechat Mini Program QA Agent
负责根据前面产物生成测试检查单和验收判断。
- zcweah1981 Bundle Message Summary Assistant
单 Agent 帮用户把一封长邮件或一堆飞书/企微/钉钉群消息直接压成"能转发、能同步、不用再解释"的结构化摘要。
- zcweah1981 Bundle Agile Web Development Solo Assistant
单 Agent 帮用户把 Web 工具需求直接压成“可开工页面结构 + 接口草案 + 代码骨架”。
- zcweah1981 Bundle Wechat Official Account Writer
单 Agent 帮用户把一个主题直接压成“可继续润色的公众号文章草稿”。
- zcweah1981 Bundle Wechat Mini Program Solo Assistant
单 Agent 帮用户把微信小程序需求直接压成“可开工代码骨架 + 实施包”。
- zcweah1981 Bundle Multi Platform Rewrite Assistant
单 Agent 帮用户把一篇已有内容直接改写成适配小红书、公众号、X/Twitter 等多平台风格的可发布稿件。
-
farmage Bundle MCP Developer 2Use when building, debugging, or extending MCP servers or clients that connect AI systems with external tools and data sources. Invoke to implement tool handlers, configure resource providers, set up stdio/HTTP/SSE transport layers, validate schemas with Zod or Pydantic, debug protocol compliance issues, or scaffold complete MCP server/client projects using TypeScript or Python SDKs.
-
wcpaka-lgtm Bundle Blender 3dUse when working with Blender: MCP, bpy, addons, renders.
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 llm-serving-capacity-planner, perf-nsight-compute-analysis, improve-codebase-architecture. 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.