Skip to content
Get packs

AI and ML Workflow Bundle

Guides an agent through planning LLM apps, RAG, AI agents, ML pipelines and AI observability by routing to other skills.

Source Download skill
Repository
sickn33/agentic-awesome-skills
Stars
49,023
Licence
MIT
Files
1 file

What it does

This is a routing guide rather than a tool. When installed, it gives the agent a seven-phase checklist for building AI products: designing the application, integrating LLMs, building retrieval (RAG) systems, developing AI agents, setting up ML pipelines, adding observability and evaluation, and considering security. For each phase it names other specialised skills to call and suggests steps, so the agent knows which expert workflow to follow next. It does not itself contain code, scripts or connections to any service.

Great for

  • Developers planning a new LLM-powered application or RAG system who want a structured sequence of steps
  • Teams setting up AI observability, evaluation and MLOps and wanting a checklist of what to cover
  • People who want help choosing which AI-related skill to use for a given task

Skip it if

  • Simple one-off questions about AI, since the bundle is only a checklist and points to other skills that must be installed separately; the referenced skills are not included in this file
  • Production deployment decisions without expert review, because the file itself says outputs are not a substitute for environment-specific testing or expert review
  • Projects handling sensitive data without first defining data permissions, since the file asks for these to be set but does not enforce them

Try asking

  • “Help me plan an LLM app that answers questions over our company documents using RAG”
  • “Walk me through designing a multi-agent system with CrewAI or LangGraph”
  • “Create an observability and evaluation plan for our LLM feature using Langfuse”
  • “Give me a checklist for securing and monitoring an AI feature before launch”
Step-by-step guide: how to use AI and ML Workflow BundleInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    ai-ml.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip ai-ml.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip ai-ml.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Ask for one phase at a time (for example only RAG design) so the agent does not load every linked skill.
  • Name your data sensitivity and latency or cost limits up front, since the workflow asks for these before implementation.
  • Treat the checklist items as prompts to verify, not as completed work; check each one in your own environment.

What's inside

  • SKILL.md

Redistributed unmodified from sickn33/agentic-awesome-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.