Prompt Engineer

What it does

When your agent uses it

• Designing prompts for a new LLM application
• Improving an existing prompt's accuracy or cutting its token use
• Writing a system prompt with a persona and guardrails
• Creating JSON schemas for function calling or JSON mode
• Building a test set and metrics to compare prompt versions

Example prompts

• “Rewrite our support-ticket classifier prompt with few-shot examples and test it against the labeled tickets in tickets.csv.”
• “Write a system prompt for a billing assistant with a friendly persona and clear guardrails.”
• “Cut the token count of this extraction prompt without lowering accuracy.”
• “Design a JSON schema for a function call that returns invoice line items.”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Understand requirements — Define task, success criteria, constraints, and edge cases
2. 2Design initial prompt — Choose pattern (zero-shot, few-shot, CoT), write clear instructions
3. 3Test and evaluate — Run diverse test cases, measure quality metrics
4. 4Iterate and optimize — Make one change at a time; refine based on failures, reduce tokens, improve reliability
5. 5Document and deploy — Version prompts, document behavior, monitor production

What it can do on your machine

Read from SKILL.md and the folder at commit 1be15d8. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • github.com
  • synergetic.solutions
  • jeffallan.github.io

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Prompt Engineer loads about 1.5k tokens when it runs, and up to ~27k if it reads all its reference files. Until then it costs about 131 tokens; SKILL.md has 457 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~131

When it runs · the whole SKILL.md, loaded when a task matches

~1.5k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~27k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Jeffallan/claude-skills at commit 1be15d8, republished under its MIT licence (© Jeffallan). 457 words, ~1,509 tokens.

name

prompt-engineer

description

Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot learning, creating system prompts with personas and guardrails, building JSON/function-calling schemas, or developing prompt evaluation frameworks to measure and improve model performance.

license

MIT

metadata.author

https://github.com/Jeffallan

metadata.company

https://synergetic.solutions

metadata.version

1.2.0

metadata.domain

data-ml

metadata.triggers

prompt engineering, prompt optimization, chain-of-thought, few-shot learning, prompt testing, LLM prompts, prompt evaluation, system prompts, structured…

metadata.role

expert

metadata.scope

design

metadata.output-format

document

metadata.related-skills

test-master, rag-architect, debugging-wizard

Classify the sentiment of the following review as Positive, Negative, or Neutral.

Review: {{review}}
Sentiment:

Classify the sentiment of the following review as Positive, Negative, or Neutral.

Review: "The battery life is incredible, lasts all day."
Sentiment: Positive

Review: "Stopped working after two weeks. Very disappointed."
Sentiment: Negative

Review: "It arrived on time and matches the description."
Sentiment: Neutral

Review: {{review}}
Sentiment:

Summarize this document.

{{document}}

Summarize the document below in exactly 3 bullet points. Each bullet must be one sentence and start with an action verb. Do not include opinions or information not present in the document.

Document:
{{document}}

Summary:

© Jeffallan, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (references) in skills/prompt-engineer of Jeffallan/claude-skills.

• SKILL.md
• references/context-management.md
• references/evaluation-frameworks.md
• references/prompt-optimization.md
• references/prompt-patterns.md
• references/structured-outputs.md
• references/system-prompts.md

Open the folder on GitHubat commit 1be15d8