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.
-
aibot88 Bundle Load Mbox Mail Archives Into Sqlite For Offline Search AuditUse mbox-to-sqlite when an agent needs to work across an email archive as structured data instead of parsing one message at a time. The agent imports a mailbox into SQLite, then hands the resulting database to search, reporting, and cross-dataset workflows without depending on a live mail provider.
3 - aibot88 Bundle Manage Elevenlabs Agents As Versioned Local Config Files Ins
Initialize, authenticate, and edit ElevenLabs agent configs from local files when you want agent definitions in code review instead of only in a hosted UI.
3 - aibot88 Bundle Package Docs Repos And Pdfs Into Installable Agent Skills Wi
Turn documentation sites, GitHub repos, and PDFs into installable agent skill packages when hand-authoring a reusable skill would be slow or inconsistent.
3 - aibot88 Bundle Persist Reusable Coding Agent Memory Across Sessions With En
Keep searchable long-term memory for coding agents in a local SQLite store and expose it through MCP when sessions keep forgetting prior decisions, conventions, and useful findings.
3 - aibot88 Bundle Preflight Agent Specs For Prompt Injection Risk Across Promp
Describe an agent in `agent_spec.yaml`, run deterministic prompt-injection analysis, generate mitigations, and validate defenses before rollout.
3 - aibot88 Bundle Prevent Broken Github Actions Workflows Before CI Runs With
Use actionlint when an agent needs to inspect GitHub Actions workflow files before a push or pull request lands. The skill checks syntax, expressions, action inputs, runner labels, cron patterns, and a few security footguns so the agent can stop bad workflow changes before CI burns time.
3 - aibot88 Bundle Probe AI Agents For Dangerous Tool Chains And Execution Side
Test agent systems for graph-discovered tool-chain vulnerabilities, silent side effects, and multi-phase trust exploits before deployment.
3 - aibot88 Bundle Probe Ml And LLM Systems For Regressions And Vulnerabilities
Run automated red-team and failure scans against an LLM or RAG app before users find the breakage.
3 - aibot88 Bundle Provision OAUTH Capable Microsoft Agent Identities With Entr
Create Microsoft Entra Agent Identity blueprints, principals, and agent identities with the right beta Graph permissions, sponsor rules, and sidecar-based auth patterns.
3 - aibot88 Bundle Red Team Agent Workflows For Jailbreaks Prompt Injection And
Run local adversarial attack passes against agents, RAG pipelines, and chatbots to surface concrete failure classes before production rollout.
3 - aibot88 Bundle Run Agents In Disposable Microvm Sandboxes With Network Allo
Launch risky agent work inside disposable microVMs when you need stronger isolation, sealed egress, and host-side secret injection instead of direct host access.
3 - aibot88 Bundle Scan Agent Skill Folders For Risky Patterns And Missing Safe
Run a pre-trust security pass over skill packs and prompt bundles before they get shared, merged, or deployed.
3 - aibot88 Bundle Scan Agent Workflows For Tools MCP Exposure And Adversarial
Use Agentic Radar to statically scan agent workflows, map tools and MCP servers, generate shareable security reports, and optionally run adversarial runtime tests before rollout.
3 - aibot88 Bundle Scan Agentic Codebases For Exposed Tools MCP Usage And Mappe
Generate a reviewable security report for a supported agent workflow before deployment by scanning its code, tools, MCP usage, and known vulnerability surface.
3 - aibot88 Bundle Scan Claude Code Configs For Secrets Permission Drift And Un
Audit a Claude Code setup before use by flagging hardcoded secrets, broad allow rules, risky hooks, and dangerous MCP server config.
3 -
frank-luongt Bundle MCP Builder 5<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle Nemo Curator 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle Prompt Guard 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle Tensorrt LLM 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle Model Merging 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle Model Pruning 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle Enhance Prompt 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle LLM Evaluation 5
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle Nemo Evaluator 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle Nemo Guardrails 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle Prompt Engineer 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle Agent Evaluation 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle LLM App Patterns 5
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle Stable Diffusion 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle Transformer Lens 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle Agent Tool Builder
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle RAG Implementation 5
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Skill Agent Tool Builder 2
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle Embedding Strategies 5
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle Multi Agent Patterns 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle Multi Agent Brainstorming 5
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
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 load-mbox-mail-archives-into-sqlite-for-offline-search-audits-an, manage-elevenlabs-agents-as-versioned-local-config-files-instead, package-docs-repos-and-pdfs-into-installable-agent-skills-with-s. 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.