Use the AI engineering pack

Install the AI engineering pack, run its first task, and follow a typical session step by step.

Adopt and build AI systems: readiness assessment, use-case triage, rollout and acceptable-use policy, plus agent loop design, subagent orchestration, spend budgets, agent security review, eval harnesses, and AI-usage reporting.

Reach for it when: A team wants to adopt AI tools and needs to know whether it is ready, where to start, what the rules are, and how to roll out.

1. Install it

npx skilldrop-cli install --pack ai-engineering                 # Claude Code, your user folder
npx skilldrop-cli install --pack ai-engineering --project       # Claude Code, this repo
npx skilldrop-cli install --pack ai-engineering --ide cursor    # or kiro, codex, antigravity, copilot
npx skilldrop-cli install --pack ai-engineering --local         # this repo, hidden from git

In Claude Code you can also add the marketplace once (/plugin marketplace add sananthanarayan/skilldrop) and run /plugin install ai-engineering@skilldrop.

It brings core with it, so the shared skills are there too.

2. Run the first task: find out whether a team is ready to adopt AI tools, and what blocks it first

Paste this into your agent:

Are we ready for AI? Our support team has 12 people on Zendesk, no AI tools today, and a legal team worried about customer data.

How to tell it worked: ai-readiness-assessment scores six dimensions (data, tooling, skills, governance, process, culture) with evidence for each, and ranks the gaps that block adoption first.

If nothing happens: If ai-readiness-assessment does not activate, ask for it by name and check that its folder exists in your skills folder (~/.claude/skills/ by default).

3. A typical session

Bring:

• the team or organisation in scope and what the answer will feed (a go/no-go, a budget, a sequence)
• evidence about current tools, data, policies and practices
• the candidate AI use cases
• any regulatory or contractual limits on data
• ai-readiness-assessment: Describe the team, its tools and data, and the concerns already raised. You get: Scores from 0 to 4 on data, tooling, skills, governance, process and culture, each with an evidence line, the gaps ranked by what blocks first, and a one-sentence posture. You decide: Decide whether to go ahead, and at what scope, from the stated posture.
• ai-use-case-triage: List the candidate use cases. You get: A ranked portfolio scored on value, feasibility and risk with the weights shown, one first slice with the observable that proves or kills it, and a not-yet list with promotion conditions. You decide: Confirm the first slice.
• ai-usage-policy: Give the population, the tools and any data rules already in force. You get: A policy at the length your audience needs: what's allowed first, every restriction paired with what to do instead or who decides, what to do if data has already gone in, and no claim about a tool, owner or law that you didn't give it.
• ai-adoption-rollout: Name the chosen tool or workflow and who it is for. You get: A rollout in waves with enablement per cohort, named champions, a comms plan that says what will not change, and an adoption gate on every wave. You decide: Each wave's gate must be met before the next cohort opens.

You end with: A readiness baseline, a chosen first use case, a usage policy, and a gated rollout plan.

Next

• Every skill in the AI engineering pack: what each one makes, needs and hands off to
• The pack's page, with one-click copy for every command
• Upgrade installed skills when a new version ships

Edit this page on GitHub · View source