Skip to content
Agent Orchestration
Skill

/prompt-engineer

LLM prompts - design, evaluate, tune instructions.

BOOST
@sipyourdrink-ltdsipyourdrink-ltd@sipyourdrink-ltd
From plugin
bernstein
1.2k26 skills1 agent3 commands1 hook
+1

Claude Code

$ npx -y skills add sipyourdrink-ltd/bernstein --skill prompt-engineer --agent claude-code

SKILL.md

prompt-engineer.SKILL.md
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.
Read it on GitHub ↗
Stats
PythonJavaScriptNodeReactBashDockerCloudflareGitGitHubAnthropicGeminiMCP
1,210
Stars
186
Forks
Active
Maintenance
Python
Language
Apache-2.0
License
Last commit
Created

Repo: sipyourdrink-ltd/bernstein

In this plugin
26 skills3 commands1 agent1 hook1 MCP
See everything inside
@sipyourdrink-ltd
Ships withbernstein

The open-source governance layer for AI agents: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run

1.2k26 skills1 agent1 MCP
Get the whole plugin

Stars on GitHub

Momentum

stars in total
1.2k
Star history of sipyourdrink-ltd/bernstein on GitHub, a chart by star-history.com
See what's trending this week

Other skills on bernstein.

See all 26 skills in bernstein

More skills from other plugins.

1password

1password

Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.

clawdis2w393k
@steipete@steipeteInstall Skill
computer-use

computer-use

Drives the GUI of a visible local app window through `orca computer`: accessibility tree, clicks, typing, menus, dialogs, and…

orca2w111k
@stablyai@stablyaiInstall Skill
agentmail

agentmail

Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by…

paperclip2w109k
@paperclipai@paperclipaiInstall Skill
adr-create

adr-create

Create a new Architecture Decision Record with sequential numbering and AgentDB registration

ruvnet-ruflo2w80k
@ruvnet@ruvnetInstall Skill

Questions about prompt-engineer.

Which coding agents can use prompt-engineer?
prompt-engineer installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.