System Prompt Engineering & Few-Shot Design

What it does

System Prompt Engineering & Few-Shot Design is a Cursor skill: a SKILL.md playbook that AgenticKit installs at .cursor/skills/prompt-engineering. Cursor's agent loads it when the task matches the skill description, instead of stuffing the same rules into every chat.

Production prompt engineering techniques for Cursor rules, LLM agents, and automated code generators with high reliability and zero hallucinations.

Role assignment, XML delimiters, few-shot examples, and deterministic schemas. The file is domain knowledge, not a slash macro. You do not type it. The agent reads it when the job is prompt engineering.

Why it exists

Default Cursor has no memory of how your team ships code, schema, and tests. Founders paste the same conventions into chat, then watch the model drift on the next turn. This skill exists so those conventions live on disk and load only when relevant.

It ships in the Engineering Kit. It is wired to the AI & Vector Engineer (ai-engineer) and Technical Lead & System Architect (tech-lead) agents. It is wired to the /ai-feature: AI Integration & Vector Pipeline Builder and /define-brand-voice: Brand Voice & Style Guide Creator commands. That graph is the point: the skill is the standard, the agent is the role, the command is the trigger.

When to use it

• Use System Prompt Engineering & Few-Shot Design when the work is specifically about role assignment, xml delimiters, few-shot examples, and deterministic schemas.
• Load it before a long session that will touch this surface more than once. A one-line edit does not need the full playbook.
• Use it on production SaaS work (multi-tenant apps, paid features, anything that will be reviewed) rather than a throwaway prototype.

When not to use it

• Do not treat the skill as a replacement for a slash command. Skills teach. Commands run a pipeline.
• Do not paste the whole SKILL.md into chat. If Cursor is not loading it, fix the description or invoke the matching command.
• Do not use it as a generic 'write better code' rule. Scope is this domain only.

Example workflow

1. Install the Engineering Kit so .cursor/skills/prompt-engineering lands in the repo.
2. Open a new Cursor agent chat pointed at the files this skill governs.
3. Ask the AI & Vector Engineer (ai-engineer) to read the skill, or run /ai-feature: AI Integration & Vector Pipeline Builder.
4. Review the first artifact against the practices below. If it violates one, stop and correct the file. Do not prompt 'just finish it'.
5. Commit the skill-guided files with the rest of the slice so the next session inherits the same standard.

Example usage

Example prompt: "Read .cursor/skills/prompt-engineering and apply it to this change. Do not invent extra conventions."

Or trigger the pipeline: /ai-feature: AI Integration & Vector Pipeline Builder. That command is written to load this skill.

Check the output against: Structure system prompts with clear XML tags: <context>, <rules>, <examples>

Example output

• The skill itself does not write a single output file. It changes what the agent is allowed to produce in code, schema, and tests.
• When you run /ai-feature: AI Integration & Vector Pipeline Builder, expect repo files plus notes under docs/, not a chat-only answer.

Best practices

• Structure system prompts with clear XML tags: <context>, <rules>, <examples>
• Provide 2-3 high-quality few-shot examples demonstrating input/output contracts
• Instruct models to think step-by-step before producing the final code or answer
• Explicitly state negative constraints (e.g. 'Do NOT use external CSS libraries')

Common mistakes

• Ignoring "Structure system prompts with clear XML tags: <context>, <rules>, <examples>" and hoping a later prompt will clean it up.
• Copying the skill into .cursor/rules as always-on. That burns context and fights Cursor's load-on-match design.
• Running two overlapping skills that contradict each other in the same turn.
• Letting the agent skip tests or types because 'the skill is about architecture'.