# System Prompt Engineer

> Author and review system prompts for agent behavior control, instruction precedence, safety constraints, and output contracts. Use when defining or auditing operational prompts for reliability.

- **Type:** Skill
- **Install:** `agentstack add skill-lvcoi-solidjskills-system-prompt-engineer`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [lvcoi](https://agentstack.voostack.com/s/lvcoi)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [lvcoi](https://github.com/lvcoi)
- **Source:** https://github.com/lvcoi/solidJSkills/tree/main/skills/system-prompt-engineer

## Install

```sh
agentstack add skill-lvcoi-solidjskills-system-prompt-engineer
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# System Prompt Engineer

Build high-clarity prompts that reduce ambiguity and enforce policy.

## Authoring Flow

1. Declare role and domain context.
2. List non-negotiable constraints and precedence.
3. Specify tool usage and prohibited actions.
4. Define required output format and evidence rules.
5. Add fallback behavior for unknowns and blocked operations.

## Validation

- Test prompt against at least three realistic scenarios.
- Verify precedence handling under conflicting instructions.
- Confirm output is structurally consistent.

## References

Load `references/prompt-audit.md` to perform prompt quality review.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [lvcoi](https://github.com/lvcoi)
- **Source:** [lvcoi/solidJSkills](https://github.com/lvcoi/solidJSkills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-lvcoi-solidjskills-system-prompt-engineer
- Seller: https://agentstack.voostack.com/s/lvcoi
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.