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.
-
hainamchung Bundle Agent Assistant Docs Business📊 Business Docs — Business documentation files. Use when user types /docs:business.
- hainamchung Bundle Agent Assistant Ask Fast 2
⚡ Quick Answer — Direct response from codebase context. Use when user types /ask:fast.
- hainamchung Bundle Agent Assistant Ask Hard 2
⚡⚡⚡ Research Answer — External research with comprehensive analysis. Use when user types /ask:hard.
- hainamchung Bundle Agent Assistant Fix Fast 2
⚡ Quick Fix — Rapid issue resolution. Use when user types /fix:fast.
- hainamchung Bundle Agent Assistant Fix Hard 2
⚡⚡⚡ Full Fix — Complete issue resolution with research. Use when user types /fix:hard.
- hainamchung Bundle Agent Assistant Fix Team 2
🔺 Team Fix — Golden Triangle adversarial collaboration. Use when user types /fix:team.
- hainamchung Bundle Agent Assistant Code Fast 2
⚡ Quick Implementation — Direct coding without planning phase. Use when user types /code:fast.
- hainamchung Bundle Agent Assistant Code Hard 2
⚡⚡⚡ Full Development Cycle — Plan → Implement → Test → Review. Use when user types /code:hard.
-
agentient Skill MCP Protocol Compliance Testing 2MCP Protocol Compliance Testing Skill
- hainamchung Bundle Agent Assistant Design Hard
⚡⚡⚡ Full Design — Complete design process with research. Use when user types /design:hard.
- hainamchung Bundle Agent Assistant Design Team
🔺 Team Design — Golden Triangle adversarial collaboration. Use when user types /design:team.
- hainamchung Bundle Agent Assistant Report Fast
⚡ Fast Report — Quick status updates and summaries. Use when user types /report:fast.
- hainamchung Bundle Agent Assistant Report Hard
⚡ Detailed Report — Comprehensive project analysis and documentation. Use when user types /report:hard.
- hainamchung Bundle Agent Assistant Report Team
🔺 Team Report — Golden Triangle adversarial collaboration. Use when user types /report:team.
- hainamchung Bundle Agent Assistant Review Fast
⚡ Quick Review — Fast PR/file review. Use when user types /review:fast.
- hainamchung Bundle Agent Assistant Review Hard
⚡⚡⚡ Full Review — Deep code analysis with architecture review. Use when user types /review:hard.
- hainamchung Bundle Agent Assistant Review Team
🔺 Team Review — Golden Triangle adversarial collaboration. Use when user types /review:team.
-
alexandrbasis Skill Prc 4Review and address code review comments on PR. Use when asked to 'address review comments', 'fix PR feedback', 'handle review comments', 'respond to PR comments', or 'address CR comments'. NOT for initiating code review (use /sr), NOT for task-based implementation with CR mode (use /si).
- alexandrbasis Skill Sbs 4
Interactive teaching guide for learning while working. Use when asked to 'teach me', 'walk me through', 'explain step by step', 'guide me through', 'show me how', 'learn while doing', 'I want to understand', 'help me learn', 'can you explain how', 'what does this do and why', or when the user expresses desire to understand a topic deeply rather than just get a quick answer. Also trigger when the user wants to learn a new tool, library, pattern, or workflow hands-on — even if they don't use the word "teach". NOT for open-ended brainstorming (use /brainstorm), NOT for quick one-off explanations (just answer directly), NOT for debugging (use /dbg).
- alexandrbasis Bundle Tdd 4
Test-driven development with red-green-refactor loop using vertical slices. Use when building features or fixing bugs with TDD, when /si or /si-quick needs canonical TDD discipline, when user mentions "red-green-refactor", "tracer bullets", "test-first", or asks for integration-style tests. Forbids horizontal slicing (all tests then all implementation). Use as a standalone skill only when explicitly requested by the user; automatic selection is not authorization. Portable clients may not enforce this host-level restriction.
- alexandrbasis Skill Udoc 4
Update documentation for a completed implementation and, when the repository uses one or the user requests it, update its changelog. NOT for creating new product docs (use /product).
- alexandrbasis Skill Quick 4
Apply a small change with known scope or a diagnosed bug fix using a compact task record. Use for quick fixes, configuration edits and bounded refactors; use /ct when the work needs unresolved design or coordinated implementation planning.
- alexandrbasis Bundle Setup 4
Configure claudops for a specific repository after copying the workflow or installing the plugin. Use for first setup, requested reconfiguration, or unresolved project placeholders in claudops files.
- hainamchung Bundle Agent Assistant Code Team 2
🔺 Team Code — Golden Triangle adversarial collaboration. Use when user types /code:team.
- hainamchung Bundle Agent Assistant Cook Fast 2
⚡ Quick Feature — Rapid feature implementation. Use when user types /cook:fast.
- hainamchung Bundle Agent Assistant Cook Hard 2
⚡⚡⚡ Full Feature — Complete feature development lifecycle. Use when user types /cook:hard.
- hainamchung Bundle Agent Assistant Cook Team 2
🔺 Team Feature — Golden Triangle parallel agent collaboration. Use when user types /cook:team.
- hainamchung Bundle Agent Assistant Docs Core 2
💻 Core Docs — Essential technical documentation files. Use when user types /docs:core.
- hainamchung Bundle Agent Assistant Plan Fast 2
⚡ Quick Plan — Fast planning without deep research. Use when user types /plan:fast.
- hainamchung Bundle Agent Assistant Plan Hard 2
⚡⚡⚡ Full Plan — Research-backed comprehensive planning. Use when user types /plan:hard.
- hainamchung Bundle Agent Assistant Plan Team 2
🔺 Team Plan — Golden Triangle adversarial collaboration. Use when user types /plan:team.
- hainamchung Bundle Agent Assistant Test Fast 2
⚡ Quick Test — Fast testing for specific scope. Use when user types /test:fast.
- hainamchung Bundle Agent Assistant Test Hard 2
⚡⚡⚡ Full Test — Comprehensive QA with quality gates. Use when user types /test:hard.
- hainamchung Bundle Agent Assistant Test Team 2
🔺 Team Test — Golden Triangle adversarial collaboration. Use when user types /test:team.
- hainamchung Bundle Agent Assistant Brainstorm Fast
⚡ Quick Ideation — Rapid idea generation. Use when user types /brainstorm:fast.
- hainamchung Bundle Agent Assistant Brainstorm Hard
⚡⚡⚡ Deep Ideation — Research-backed exploration. Use when user types /brainstorm:hard.
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 agent-assistant-docs-business, agent-assistant-ask-fast, agent-assistant-ask-hard. 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.