What is prompt-engineering?
prompt-engineering is a Claude skill by NeoLabHQ that widely used prompt engineering techniques and patterns, including Anthropic best practices and agent persuasion principles. It is listed under Agents & automation and has 1,780 GitHub stars.
| Type | Claude skill |
|---|---|
| Author | NeoLabHQ |
| Repository | NeoLabHQ/context-engineering-kit |
| Popularity | 1,780 GitHub stars |
| Category | Agents & automation |
| Security | Low risk (92/100) |
| Rank | #650 of 1,262 Claude skills; #44 in Agents & automation |
| SKILL.md length | 559 lines |
| License | GPL-3.0 |
| Last commit | 2026-08-26 |
| Stars this week | +28 |
Is prompt-engineering safe to install?
prompt-engineering scores 92/100 on the MCPMods security check: Low risk. No checks raised a concern. It passed 7 of 9 checks.
Skill results come from a static scan of its SKILL.md for instruction overrides, hidden actions, risky commands and credential access.
| Check | Result |
|---|---|
| No instruction-override phrases | Pass |
| No hidden actions | Pass |
| No pipe-to-shell installers | Pass |
| No obfuscated code | Pass |
| No destructive commands | Pass |
| Reads keys or credentials | Note |
| No network requests | Pass |
| Runs shell commands | Note |
| Installs no packages | Pass |
What the scan matched
- credentials:
credentials - shell:
```bash - scripts:
scripts/migrate.py
How do I install prompt-engineering?
- Install with the skills CLI. Works for Claude Code and other agents that read skills.
npx skills add https://github.com/NeoLabHQ/context-engineering-kit --skill prompt-engineering
- Or copy it by hand. Claude Code loads any folder with a SKILL.md from ~/.claude/skills.
git clone https://github.com/NeoLabHQ/context-engineering-kit cp -r context-engineering-kit/plugins/customaize-agent/skills/prompt-engineering ~/.claude/skills/prompt-engineering
- Use it. Claude loads the skill when a task matches its description. You can also name it in your prompt.
Use the prompt-engineering skill to …
Or ask Claude to set it up
Paste this into Claude Code and it installs prompt-engineering for you:
Install the "prompt-engineering" skill from https://github.com/NeoLabHQ/context-engineering-kit/tree/master/plugins/customaize-agent/skills/prompt-engineering into ~/.claude/skills, then tell me in one line what it does.
More from NeoLabHQ/context-engineering-kit
This repository has 8 Claude skills on MCPMods.
- write-concisely: Applies the famous *The Elements of Style* book principles to make documentation and writing clearer and more profession (Low risk)
- review: Comprehensive PR code review using specialized agents: bug-hunter, security-auditor, code-quality-reviewer, contracts-re (Not scanned)
- reflexion: Self-refinement loop that forces the LLM to reflect on previous output and correct itself. (Not scanned)
- sdd: Spec-driven development workflow that transforms prompts into production-ready implementations through structured planni (Not scanned)
- ddd: Domain-driven development skills that also include Clean Architecture, SOLID principles, and design patterns. (Not scanned)
- sadd: Dispatches independent subagents for individual tasks with code review checkpoints between iterations for rapid, control (Not scanned)
- kaizen: Applies continuous improvement methodology with multiple analytical approaches, based on Japanese Kaizen philosophy and (Low risk)