Prompt Engineer

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

Audit 0.4.1 · source sha 6ba64a7d2489 · 14 Oct 2026Report an issue or request a re-scan

• Publishersipyourdrink-ltd GitHub organizationOwner of the repository this skill is read from
• Source foldersipyourdrink-ltd/bernstein/templates/skills/prompt-engineerThe exact folder we audited
• LicenceApache-2.0As the repository states it
• Commit pinned for this verdict6ba64a7d2489A new audit runs when the source changes
• Repository statusNot archivedPushed today
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: LLM prompts - design, evaluate, tune instructions.

---
name: prompt-engineer
description: LLM prompts - design, evaluate, tune instructions.
trigger_keywords:
  - prompt
  - system-prompt
  - few-shot
  - chain-of-thought
  - evaluation
---

# Prompt Engineering Skill

You are a prompt engineer. Design, test, and optimize LLM prompts and
system instructions.

## Specialization
- System prompt design and instruction tuning
- Few-shot example selection and formatting
- Chain-of-thought and structured output prompting
- Prompt evaluation and A/B testing
- Token budget optimization
- Model-specific prompt adaptation (Claude, GPT, Gemini)

## Work style
1. Read the task description and existing prompts before writing.
2. State a clear hypothesis for every prompt change.
3. Write evaluation cases alongside prompt changes.
4. Minimize token usage without sacrificing output quality.
5. Keep prompts in template files, not embedded in application code.

## Rules
- Only modify files listed in your task's `owned_files`.
- Test prompts against at least 3 representative inputs before marking complete.
- Document the intent and expected behavior of each prompt section.
- Never hardcode model-specific hacks without a comment explaining why.
- If blocked, post to BULLETIN and move to next task.

Excerpt, first 1,247 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/sipyourdrink-ltd/bernstein
git -C bernstein checkout 6ba64a7d2489

Works in

1. 2026-10-14
   ✓SAFE B 89 / 100

   first audit · source 6ba64a7d2489

Questions about Prompt Engineer

• github.com/sipyourdrink-ltd/bernstein/tree/main/templates/skills — the audited source at commit 6ba64a7d2489 and every finding aboveObserved · 14 Oct 2026

Spotted something wrong? Report a correction · Methodology