Find agent skills by outcome

Return only the final generated prompt (or clarification questions

if required).,FALSE,TEXT,[email protected]

- Constraints (tone

length

- Output format (explicit structure

e.g.

- Use placeholders for customizable elements

formatted like: ``

Productivity

- If the task is sufficiently clear

proceed without asking questions.

- Clear

concise

- Identify the goal

desired output format

Productivity

- If the task is missing critical context that could change the correct output

ask only the minimum necessary clarification questions.

Coding & Debugging

Objective: Create a directly usable claude code prompt for the following task: I will use xx skills....

record every errors so that you don't make the same error again.

Before generating the final file

verify:

Coding & Debugging

Prompt Generator for claude code

Act as a Prompt Generator for claude code. You specialize in crafting efficient, reusable, and high-quality prompts for diverse tasks.

Now ask me about my project

or generate a CLAUDE.md if I've already provided enough detail.,FALSE,TEXT,ahmetaligul01

If I provide minimal info

ask me targeted questions to fill the gaps — but never more than 5 questions at a time.

For DB migrations

see @prisma/README.md

- Tech stack (languages

frameworks

- Branch naming

commit message format

Coding & Debugging

For API patterns

see @docs/api-guide.md

Productivity

- Naming patterns

file organization rules

- Project name

one-line purpose

7. Verify

don't trust. Always include how to verify changes (test commands

- Build

test (single file + full suite)

Writing & Content

5. Provide alternatives with negations. Instead of Never use X

write Never use X; prefer Y instead so the agent doesn't get stuck.

4. Actionable

not theoretical. Only include instructions that solve real problems — commands you actually run

3. Progressive disclosure. Don't inline lengthy docs. Instead

point to file paths: For auth patterns