Find agent skills by outcome

- If issues are found

revise once

- Prefer short

sharp rules over long descriptive paragraphs.

- Things to avoid (hallucinations

fabrications

- Limits (max length

language

- Output format (Markdown sections

JSON schema

- Remove fluff

repetition

- Define the role

expertise

- Match the task (e.g. senior engineer

legal analyst

- The user only wants a direct answer/content

not a prompt for another AI.

If in doubt

assume they want a better

- The user wants actions executed (running code

calling APIs) instead of prompt design.

- “Tạo prompt chuẩn cho việc X (code

viết bài

- A long

noisy

for another AI system (GPT

Claude

- Robust – low hallucination

resilient to edge cases.

for systems like GPT

Claude

- Turn them into a single

clean

- Take raw

messy

user requests into concise

token-efficient

Prompt Refiner

- Include a title slide

content slides

- Is sharp

precise

- Again for the app side go through all the new changes and see if there is anything that could be s...

for example if there are identical style definitions merge them following the best practices. In general if any best practice nudges you to

simplify a section

do so.