Prompt Engineer Brief skill for Claude and Codex

Prompt Engineer Brief as an AI skill. It asks for Task the prompt must perform, Who uses the output, Output format needed and 3 more, then does the rest. Free…

Install it once and Claude or Codex runs it for you. When your request matches, your AI loads the skill, asks for anything it is missing, and works through the template itself. Prefer to fill it in by hand? See the full prompt template.

Download the skill (.zip) · View SKILL.md

When it is used

Use when a task needs a reusable, well-structured prompt with a role, rules, examples, an exact output format and a test to prove it works. Do not use for quick one-off questions or tuning model settings. Related topics: AI, writing.

What it will ask you for

• Task the prompt must perform (longer free text)
• Who uses the output (free text, e.g. "Person or program")
• Output format needed (choose one: Free text, Markdown, JSON, Table, Code)
• Constraints (longer free text)
• Good example (longer free text)
• Failure to prevent (longer free text)

How it works

1. Define the task, the user of the output and the variable parts of the input before writing any instruction.
2. Write instructions in a fixed order from role to output schema, expressing constraints as positive, testable rules.
3. Add one normal and one edge example, plus a rule and example aimed at the named failure.
4. Specify what the prompt does when input is missing or unclear.
5. Write a three-case test plan with the pass condition for each and the first parts to adjust on failure.

What you get

The finished prompt in one block, followed by a test plan with typical, edge and adversarial inputs, each with a pass condition and tuning notes.

What it watches out for

• Describing the output loosely, so each run returns a different shape that code cannot parse.
• Giving only a perfect example, so the prompt fails on the first messy input.
• Stacking dozens of rules with no priority, which leads to the important one being ignored.

How to install

Claude.ai and the Claude desktop app

1. Download the skill .zip.
2. Open Settings, then Capabilities, and find Skills.
3. Choose Upload skill and select the .zip.
4. Ask Claude for help with the task. It loads the skill when your request matches.

Claude Code

1. Download the skill .zip.
2. Unzip it into ~/.claude/skills/ (or .claude/skills/ inside a project).
3. Start a new session. Claude Code loads the skill when your request matches.

Codex

1. Download the skill .zip.
2. Unzip it into ~/.agents/skills/ (or .agents/skills/ inside a project).
3. Codex picks it up on its own. Type $ and the skill name to use it, or just ask for the task.

Cursor

1. Download the Cursor rule (.mdc).
2. Save it in .cursor/rules/ inside your project.
3. Cursor's agent applies the rule when your request matches its description.

AGENTS.md (Codex, Cursor, and other coding agents)

1. Copy the AGENTS.md section.
2. Paste it into AGENTS.md at the root of your repository, creating the file if needed.
3. Coding agents that read AGENTS.md follow it when your request fits.