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.
-
okooo5km Bundle CoupongoUse this skill when Codex needs to operate CouponGo, the AI-friendly CLI for managing Stripe coupons and promotion codes. Trigger for tasks involving `coupongo`, Stripe coupon or promotion-code listing, creation, update, deletion, batch generation, configuration inspection, `coupongo schema`, `coupongo doctor`, or agent-safe non-interactive CouponGo workflows.
-
open-gsd Skill Run And Die TestsRun a project's Node tests without leaking orphaned processes onto this machine. Use whenever you would run `node --test`, `npm test`, or `npm run test` — call `gsd-test run` instead of spawning the test process locally. Also use when a run comes back reaped, or when a previous local test run left hung `node` processes behind.
-
open-horizon-labs Bundle CessApply Counterexample-Supplemented Sketches (CESS) to open-world agent and software synthesis. Use when a user mentions CESS, Sketch-CE, counterexample-supplemented sketches, evolved sketches, compiled projections, simulation-driven correction, or asks to make an agent-generated system improve from reviewed failures without losing earlier behavior.
-
oktsec Bundle AuditSecurity audit for AI-built code. Runs 130+ checks across OWASP Top 10, auto-detects your stack, and produces a graded report (A-F) with exact code fixes. Covers secrets, injection, auth, database access control, AI/LLM security, payments, and infrastructure.
-
opencoredev Skill Mobbin CLIThis skill should be used when the user asks to "use Mobbin", "find UI references", "search app screens", "search flows", "search website sections", "gather mobile UI inspiration", "gather dashboard references", or do Mobbin-backed product and interface research from an agent. It teaches agents to use the npm-installed Mobbin CLI instead of relying on a mounted Mobbin MCP server.
-
opencoredev Skill QuickboardUse the QuickBoard MCP to create and draw on live whiteboards. Create boards, add shapes/text/arrows, use mermaid for simple flows, and share live URLs with users.
-
opendatalab Bundle Mineru Document ExplorerMinerU Document Explorer — Agent-native knowledge engine. Use when users ask to search their documents, look up information in PDFs/DOCX/PPTX/Markdown, navigate inside large documents, extract tables/figures, or build wiki knowledge bases. Provides three tool groups: information retrieval (query, get, multi_get, status), document deep reading (doc_toc, doc_read, doc_grep, doc_query, doc_elements, doc_links), and knowledge ingestion (wiki_ingest, doc_write, wiki_lint, wiki_log, wiki_index).
Audited -
openafw Skill MoltguardMoltGuard — Protect you and your human from prompt injection, data exfiltration, and malicious commands. Source: https://github.com/openguardrails/openguardrails/tree/main/moltguard
-
opendcai Bundle One Eval驱动 One-Eval 对 API 或本地模型做端到端评测,覆盖纯文本、多模态、代码生成、函数调用和 Agent benchmark。当用户想评测模型在一个或多个 benchmark 上的表现、比较分数、补充 metric,或生成图文评测报告时使用本 skill。
-
oracle Bundle Dtrace LinuxGenerate and validate runnable DTrace scripts for Linux debugging and performance investigations in an agentic coding framework capable of using SKILLs. Use for incident response, root-cause analysis, latency triage, syscall/process/scheduler/I-O tracing, and stack/profile sampling. Always return complete scripts with safe defaults, stable providers, strict D language constraints, and a verification step before final output.
736 -
orange-county-ai Bundle TincanMessage or ping another herdr agent, coordinate agents, name yourself, send an agent message across hosts, or find who else is running. Use when the user mentions tincan, asks to notify an agent, coordinate work with another agent, claim an agent name, send a cross-host message, or asks who is active.
-
orange2ai Bundle Disk RaccoonmacOS 缓存清理 Agent(小浣熊)。对 Mac 上的开发工具缓存、应用缓存做只读体检, 按缓存地图的安全等级判断哪些能删,经用户确认后执行清理。 Use when: 用户说磁盘满了、清理缓存、Mac 空间不够、某个应用占了几十个 G、 帮我瘦身、cache cleaner、磁盘体检。只管缓存,不做应用卸载和系统优化。
-
orangeviolin Bundle 01fish LLM Radar用 7 个客观 benchmark(GSM8K / MATH / MMLU / MMLU-Pro / C-Eval / IFEval / HumanEval)快速评测任意 OpenAI 兼容 API 的大模型。支持 DeepSeek 官方 / OpenRouter / 硅基流动 / 火山引擎 / 自部署 vLLM,一键多模型横评 + 单模型深度 profile。
-
orangeviolin Bundle Ip Coach个人 IP 起号教练。通过 7 阶段深度访谈引导用户找到自己的内容生态位、平台规则、第一个里程碑和承诺机制,产出一份可持续喂给 agent 的"起号档案",并自动调用 /goal skill 把第一个里程碑拆解成可执行的自动计划系统,持续陪伴执行。当用户说"起号"、"做自媒体"、"做个人 IP"、"做个人品牌"、"不知道写什么"、"怎么开始"、"帮我定位"、"/ip-coach"、"/起号"时触发。也适用于用户在"我该不该做自媒体"、"我没什么可写的"、"我不知道我的生态位是什么"这类自我怀疑时的场景。
-
opengeos Skill CLI Anything GeoaiAI-powered geospatial analysis CLI. Segment satellite imagery, detect objects, classify images, detect changes, download data, and manage raster/vector operations -- all from the command line with JSON output for agent integration.
-
opengeos Skill CLI Anything SamgeoCLI harness for segment-geospatial — segment satellite/aerial imagery with SAM models from the command line
-
openghz Bundle Python Config StyleWrite Python configuration, command-line, and class-initialization code in the user's house style: pydantic config classes (frozen, with attribute docstrings as the field docs), Hydra for whole-application config wiring via `_target_` + `instantiate`, pydantic-settings (`CliApp`) for small-script CLIs, and a single `config` parameter in every `__init__`. Use this whenever writing or refactoring Python that defines a configuration model, parses command-line arguments, structures a class or top-level function around its settings, or chooses between Hydra and pydantic-settings — even if the user never names the libraries. Triggers on: "add a config", "write a config class", "make a CLI for this script", "add command-line args", "pydantic config", "hydra config", "refactor this to take a config", "配置类", "加个配置", "写个命令行", "加命令行参数", "把它改成吃 config 的", and similar Python config / CLI / class-init work.
-
openghz Bundle Npx Skill InstallInstall agent skills with `npx skills` the safe, no-duplicate-work way. Before installing, it checks (in one shot) whether the skill is already installed and whether every agent's skills directory is symlinked onto one shared hub — so you install ONCE instead of once per agent. Use this whenever the user wants to add, install, or set up a skill via `npx skills` / the skills CLI, hands over a skills repo or a skill name to install, asks why a skill isn't showing up in some agents, or wants to share one skills folder across Claude Code / Codex / Cursor / Gemini / Copilot / OpenCode. Triggers on: "install this skill", "add the X skill", "npx skills add", "set up this skills repo", "安装这个技能", "装一下这个 skill", "把这个技能装上", "用 npx skills 安装", "让所有 agent 都能用这个技能", "技能装了吗 / 是不是已经安装了", "把各个 agent 的 skills 目录软链接到一起".
-
orosha-ai Bundle Agent Observability DashboardAgent Observability Dashboard 📊
-
orosha-ai Bundle Agent Trust ValidatorAgent Trust Validator 🛡️
-
ozgurcd Skill GographGo repository intelligence for Claude Code. Use when reading, navigating, editing, reviewing, or refactoring a Go codebase. Exposes 64 query, analysis, and workflow capabilities through the local gograph MCP server, including bounded first-call exploration, AST-aware call graphs, blast-radius analysis, impact, and security-flow candidates.
Audited -
p404 Bundle Monodraw LLMDraw a diagram as a real editable Monodraw document, not a picture. Use for draw me a diagram of this, sketch this architecture in ASCII, turn this ASCII or text diagram into a real diagram, recreate this screenshot as a diagram, recreate or debug a `.monopic` or `.monojson` file. Boxes become draggable frames, arrows become attached connectors. Use it even when Monodraw is never named. Not for charts or plots, which are dataviz; not for a diagram drawn inside a web artifact, which is artifact-diagramming; not for UI mockups or wireframes, which is design.
-
openghz Bundle Rembg Bg RemovalRemove image backgrounds with rembg, producing transparent-PNG cutouts. Use this whenever the user wants to remove/erase/delete a background, cut out or isolate a subject, make a transparent PNG, extract a foreground object, or batch-process a folder of images into cutouts — including phrasings like "抠图", "去背景", "remove background", "cut out this object", "make this transparent", "isolate the product", or when they hit rembg errors (missing onnxruntime backend, CUDA/libcudart version mismatch, gradio proxy crash). It sets up an ISOLATED conda/venv environment (never touching existing envs), installs the correct GPU (CUDA 12) or CPU backend for the machine, prefetches models, and runs single-image or whole-folder background removal.
-
openhands Bundle Skin AppThis instance's skin is a Datadog infra-health dashboard (monitors, error-log patterns, per-app CPU/memory) with one-click agent-assisted fixes. Use this to understand what the dashboard shows, which APIs back it, and how "Fix" conversations originate.
-
osodevops Bundle Keito Time TrackTrack billable AI coding-session time to Keito through the Keito CLI. Use when the user asks to set up repository time tracking, install or configure the Keito skill, log agent work, check tracking status, pause or resume tracking, disable tracking, or review today's source=agent time entries.
-
pablodiegoo Bundle Data Pro SkillMarket research data analysis meta-prompt. Transforms raw quantitative and qualitative data into dense, Tufte-style analytical documents. Document-driven. Invisible agent loop: Statistician -> Critic -> Tufte Designer. Commands: /dps-setup, /dps-cross, /dps-inject-open, /dps-export. Modes: /dps-mode:quant, /dps-mode:quali, /dps-mode:strategy. Requires constitution.md.
-
ospocc Bundle HowopenThis skill allows the agent to perform an "Open Source Health Check" on the current project. It analyzes the technology stack, programming language distribution, and open-source licenses of dependencies.
-
othmanadi Bundle Ableton LiveConnect and operate the Loophole Bridge (Ableton Live MCP server). Use when the user wants to check Live/bridge prerequisites, wire an MCP client to Loophole, or run a Live editing recipe (humanize, build arrangement, batch rename, chord from prompt). Triggers: "is my Ableton bridge working", "set up loophole", "connect Claude to Ableton", "/doctor", "/setup".
-
openjiuwen-ai Bundle Agent Memory1 0 Skill通过 HTTP API 调用 agent-memory1.0 记忆服务,召回与写入历史处理记忆
-
openmined Skill Syfthub CLIExecute SyftHub CLI commands for privacy-preserving AI interactions. Use when the user wants to (1) authenticate with SyftHub platform, (2) browse or list AI endpoints and users, (3) query AI models with RAG (retrieval-augmented generation), (4) manage aggregator or accounting service configurations, (5) update the CLI, or (6) any task involving the `syft` command-line tool. Triggers on requests like "login to syfthub", "list endpoints", "query alice/gpt", "syft ls", "syft query", or any mention of the syft CLI.
-
openmoss Bundle ImclawIMClaw 跨网通信能力 — 让 AI Agent 具备实时聊天能力。用于:(1) Agent 需要与其他 Agent 实时通信,(2) 管理群聊,(3) 订阅和接收群聊消息,(4) 构建聊天机器人或协作 Agent。触发词:imclaw、跨网通信、agent 聊天、群聊、实时消息、龙虾。
-
parthjadhav Bundle Image Read CacheOptimizes image reading by caching LLM-generated content as XMP metadata inside image files. Use BEFORE reading any image file (.png, .jpg, .jpeg, .webp, .gif, .bmp). Reduces token usage by ~90% on repeated image reads. Triggers on: image, screenshot, picture, photo, .png, .jpg, .jpeg, read image, view image, look at image.
254 -
pasky Skill Agent SetupInitialize or update setup for pi-side-agents (running asynchronous agents spawned/controlled from main session)
Audited -
othmanadi Bundle Planning With TeamsManus-style context engineering for Agent Teams. Coordinate multiple Claude Code instances with shared planning files. Use when complex tasks need parallel work (code review, debugging, feature development). Requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1.
-
openprose Bundle MyceliumHidden layer of structured git notes for agent collaboration. When working in any git repo, check for notes on objects you touch before acting, and leave notes after meaningful work. Uses git notes directly — helper script and workflow scripts included.
-
passportxyz Bundle Repo WikiPersistent, agent-maintained repo wiki — the durable state-of-the-repo, not short-term plans. Lives at /wiki/ in the repo root. TRIGGER when: exploring unfamiliar code, completing a significant task, noticing outdated documentation, planning architectural changes, or when the user asks about project knowledge/documentation. Also triggers for wiki maintenance or verification requests.
Audited
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 moltguard, one-eval, agent-memory1.0_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.