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.
AI & ML
5,020 skills
26bb Crewai
Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies.
0
26bb Hf MCP
Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use Gradio Spaces as AI tools. Available when connected to the HF MCP server.
0
26bb Hf Mem
Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub
0
26bb Jobgpt
Job search automation, auto apply, resume generation, application tracking, salary intelligence, and recruiter outreach using the JobGPT MCP server.
0
26bb Molykit
CRITICAL: Use for MolyKit AI chat toolkit. Triggers on: BotClient, OpenAI, SSE streaming, AI chat, molykit, PlatformSend, spawn(), ThreadToken, cross-platform async, Chat widget, Messages, PromptInput, Avatar, LLM
0
26bb Seaborn
Seaborn is a Python visualization library for creating publication-quality statistical graphics. Use this skill for dataset-oriented plotting, multivariate analysis, automatic statistical estimation, and complex multi-panel figures with minimal code.
0
cjthompson Skill Testing
Use when creating test scenarios for a skill, setting up a tests/ directory for a plugin or package, running skill tests against a subagent, or verifying whether a SKILL.md changes agent behavior
1 · bundle
cjthompson Python Simple Scripts
Use before any Bash command that invokes Python, including Bash(python3 ...), Bash(python ...), python3 -c, python -c, Python heredocs, and temporary .py helper files. Also use whenever an agent creates a one-off Python script to inspect, transform, validate, or summarize data during a coding session, even when the user did not ask for Python or for a script.
1 · bundle
cjthompson Orchestration Strategy
Use when facing multiple implementation tasks that could benefit from parallelization or when deciding between solo, parallel agent, sequential subagent, or agent team approaches
1 · bundle
rulebase-co Rulebase Setup
Use to get access to Rulebase and connect an AI client to it — signing up, finding your data region, installing the Rulebase MCP server in Claude Code, Claude Desktop or Cursor, and creating an API key for the REST API. Trigger for "connect Claude to Rulebase", "install the Rulebase MCP", "set up the Rulebase connector", "create a Rulebase API key", "how do I sign up for Rulebase", "Rulebase returns 401", "no token provided", or when Rulebase tools are missing from a session.
1 · bundle
rulebase-co Cx Career Pathing
Use to design support career progression with IC and lead tracks, skill gates instead of tenure alone, and paths that do not treat leaving the phones as the only promotion. Trigger for "career pathing", "progression framework for support", "IC track", "how do agents get promoted", "support ladder", "team lead vs senior agent", or fixing promotion bottlenecks and title inflation.
1
rulebase-co Cx Incentive Design
Use to design support incentives that improve behaviour without destroying the metric — pairing pay with guardrails, naming gaming modes, and choosing measures that survive Goodhart pressure. Trigger for "incentive plan", "agent bonus scheme", "SPIFF design", "pay for QA score", "what metric should we bonus", CSAT incentives, or reviewing whether a comp change is driving gaming.
1
rulebase-co Rulebase QA Coverage Audit
Use to audit QA coverage and scorecard health in a Rulebase workspace via the Rulebase MCP server. Trigger for "audit our QA coverage", "which agents or channels aren't being evaluated", "are our QA scores meaningful", "is our scorecard working", QA blind spots, score distribution or ceiling effects, and checking whether QA scores relate to SLA or complaint outcomes.
1 · bundle
rulebase-co Cx Handle Time Analysis
Use to analyse average handle time, resolution time or time-in-queue without being misled by the skew, and to find where time actually goes. Trigger for "why is our AHT increasing", "our call handling times are up", "which contact reasons take longest", "how long do tickets take", handle time by agent or team, or an AHT target being set.
1
rulebase-co Cx Knowledge Base Audit
Use to audit a help centre or knowledge base against the conversations customers actually have, finding coverage gaps, stale articles and unused content. Trigger for "what should we write help articles about", "audit our knowledge base", KB coverage gaps, self-service deflection content, or preparing a knowledge base to ground an AI support agent.
1 · bundle
rulebase-co Cx Bot Safety Audit
Use to audit a customer-facing support bot or AI agent for harm rather than for volume — manipulation and prompt-injection attempts, customers stranded without a human, fabricated answers, and unsafe commitments or disclosures. Trigger for "are people trying to jailbreak our bot", "show me attempts to manipulate the assistant", "is our bot giving wrong answers", "customers stuck with the bot and never got a human", or reviewing an AI agent before or after launch.
1
theheavenlyd3mon Hooked UX
Design habit-forming product loops using the Hook Model (Trigger, Action, Variable Reward, Investment). Use when the user mentions "users arent coming back", "engagement loops", "habit formation", "push notifications", "variable rewards", "daily active users", "habit zone", or "user retention loops". Also trigger when designing notification strategies, building streaks or progress systems, or analyzing why users stop using a product after initial signup. Covers ethics evaluation and onboarding for habits. For friction reduction and B=MAP, see improve-retention. For viral sharing, see contagious.
28 · bundle
theheavenlyd3mon Native MCP
MCP client: connect servers, register tools (stdio/HTTP).
28 · bundle
theheavenlyd3mon Langchain
Expert skill for building LLM applications with LangChain — LCEL chains, RAG pipelines, agent orchestration, LangGraph integration, LangSmith observability, and production deployment via LangServe. Use when working with LangChain or comparing LLM application frameworks.
28 · bundle
theheavenlyd3mon Langgraph
Build multi-agent AI systems with LangGraph — the low-level orchestration framework for stateful, graph-based agent workflows. Covers supervisor, swarm, and hierarchical multi-agent patterns; subgraph composition; state management (checkpointers/stores); persistence; evals; and production debugging. Reach for this when designing agent architectures that need cycles, conditional branching, parallel execution, or human-in-the-loop patterns.
28 · bundle
theheavenlyd3mon Huggingface Accelerate
Run PyTorch training across GPUs with minimal changes.
28 · bundle
theheavenlyd3mon CLI Builder
Build or refactor CLI tools designed for AI agent consumption: non-interactive, flag-driven, idempotent, with --json output and --dry-run preview. Use when creating a new script the agent will call, adding agent-friendly flags to an existing tool, or debugging why an agent keeps failing to use your CLI.
28 · bundle
theheavenlyd3mon Forgejo CLI
CLI for Forgejo API — issues, PRs, repos, labels, webhooks, Actions runners. Dual auth (AGENT/USER).
28 · bundle
theheavenlyd3mon Karpathy Guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
28 · bundle
ichichuang Mcporter
Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.
0 · bundle
ichichuang Native MCP
Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Hermes Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.
0 · bundle
ichichuang Clip
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.
0 · bundle
ichichuang Ascii Art
Generate ASCII art using pyfiglet (571 fonts), cowsay, boxes, toilet, image-to-ascii, remote APIs (asciified, ascii.co.uk), and LLM fallback. No API keys required.
0 · bundle
ichichuang Godmode
Jailbreak API-served LLMs using G0DM0D3 techniques — Parseltongue input obfuscation (33 techniques), GODMODE CLASSIC system prompt templates, ULTRAPLINIAN multi-model racing, encoding escalation, and Hermes-native prefill/system prompt integration. Use when a user wants to bypass safety filters, jailbreak a model, or red-team model robustness.
0 · bundle
ichichuang Kanban Worker
Pitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.
0
ichichuang Serving Llms Vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
0 · bundle
ichichuang Whisper
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
0 · bundle
ichichuang Guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
0 · bundle
ichichuang Outlines
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library
0 · bundle
ichichuang Codex
Delegate coding tasks to OpenAI Codex CLI agent. Use for building features, refactoring, PR reviews, and batch issue fixing. Requires the codex CLI and a git repository.
0 · bundle
ichichuang Kanban Orchestrator
Decomposition playbook + specialist-roster conventions + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.
0
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 python-simple-scripts, crewai, hf-mcp. Rankings shift as installs change; sort this page by "Most downloaded" 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 add <owner>/<name>, or copy the file into your agent's skills directory.