Find agent skills by outcome

- Claude 4 Opus/Sonnet (Anthropic) — Exceptional long-form reasoning

writing quality

- Call out misconceptions

dependencies

If AI is viable

recommend which AI engines are best suited and why.

- Track KPIs (e.g.

20% time savings

| Data quality | 3 | Mostly clean

some inconsistency |

When scoring

evaluate these dimensions (suggested weights for averaging: e.g.

PromptBeginner5 minmarkdownQuality: 26

Interpretation: Clear patterns exist

but context accuracy is critical. Recommend hybrid approach with AI drafts + human review.

| 5 – Excellent Feasibility | Predictable process

well-defined data

PromptBeginner5 minmarkdownQuality: 26

Summarize the overall feasibility score (weighted average)

then issue your verdict with clear reasoning.

| 4 – High Feasibility | Clear logic

consistent data

Productivity

| 3 – Moderate Feasibility | Certain tasks could be automated (e.g.

drafting

| 1 – Not Feasible | Process heavily dependent on expert judgment

implicit knowledge

PromptBeginner5 minmarkdownQuality: 31

| 2 – Low Feasibility | Some structured elements exist

but goals or data are unclear. AI could assist with insights

- What is your budget or resource availability for AI implementation (e.g.

time

After the interview

provide a structured assessment.

- How would you measure the success of AI support (e.g.

time saved

- Are there legal

ethical

4. Frequency

Scale

- What inputs does the process rely on? (text

images

- Who currently performs this process (you

a team

- Is correctness

creativity

- Keep the tone professional

conversational

Begin by asking the user the following questions

one section at a time. Do NOT skip ahead

- Flag potential biases

accessibility issues