prompt-engineering
This guide provides best practices for designing, testing, and refining prompts for AI-powered features. It is intended for developers integrating LLMs (like OpenAI, Anthropic, or Gemini) into web applications. - **Clarity:** Write prompts that are clear, specific, and unambiguous.
Install / Use
npx skills add js-promptly3d/promptly3d-aiInstalls into whichever agent you are using.
Cursor Rules
Cursor IDE rules (v2)
Quality Score
Category
AI & Machine LearningSupported Platforms
Our assessment of prompt-engineering
prompt-engineering scores 51/100 on our quality scale, 932nd of 963 AI & Machine Learning skills we index.
Its Cursor Rules is 1.5 KB long, split into 7 sections and no code examples: moderately detailed.
It has no GitHub stars yet, so there is no community track record; judge it on its content.
Maintenance, license and trust
- We could not determine when the repository was last updated.
- Our last check on 2026-10-20 found the source still online.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 68/100, with 3 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-09-24. Automated pattern scan on 2026-09-24. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
prompt-engineering compared with similar skills
All 4 of these similar skills score higher than prompt-engineering; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| prompt-engineering (this skill)by js-promptly3d | 51 | 0 | — | Cursor Rules |
| claude-memby thedotmack | 100 | 113.5k | today | CLAUDE.md |
| taste-skillby Leonxlnx | 100 | 110.6k | 1d ago | CLAUDE.md |
| Understand-Anythingby Egonex-AI | 100 | 90.9k | 10d ago | CLAUDE.md |
| headroomby headroomlabs-ai | 100 | 78.9k | today | CLAUDE.md |
Frequently asked questions
- How do I install prompt-engineering?
- Run
npx skills add js-promptly3d/promptly3d-ai. The install tabs above show the steps for each supported agent. - Which AI agents does prompt-engineering work with?
- It is written for Cursor and Gemini CLI, as a Cursor Rules file. Other agents that read the same format can often use it too.
- Is prompt-engineering safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 68/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is prompt-engineering still maintained?
- We could not determine when the repository was last updated.
Skill content
View source on GitHubPrompt Engineering Rules
Introduction
This guide provides best practices for designing, testing, and refining prompts for AI-powered features. It is intended for developers integrating LLMs (like OpenAI, Anthropic, or Gemini) into web applications.
General Principles
- Clarity: Write prompts that are clear, specific, and unambiguous.
- Context: Provide relevant context and examples in the prompt to guide the model.
- Instruction: Use explicit instructions (e.g., “List 5…”, “Summarize the following…”).
- Format: Specify the desired output format (e.g., JSON, Markdown, plain text).
- Iterate: Test and refine prompts based on real outputs and user feedback.
Types of Prompts
- Zero-shot: No examples, just instructions.
- Few-shot: Include 1–3 examples to guide the model.
- Chain-of-thought: Ask the model to reason step-by-step.
- Role-based: Assign a persona or role to the model for more targeted responses.
Testing & Evaluation
- Maintain a prompt library with effective prompts and their results.
- Test prompts with edge cases and real user data.
- Document prompt changes and their impact on results.
Security & Ethics
- Avoid prompts that could elicit sensitive or harmful outputs.
- Sanitize user input before including it in prompts.
- Log and review AI outputs for quality and safety.
References
- https://platform.openai.com/docs/guides/prompt-engineering
- https://anthropic.com/prompt-engineering
- https://www.promptingguide.ai/
Related Skills
claude-mem
113.5kPersistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
taste-skill
110.6kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
Understand-Anything
90.9kGraphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
headroom
78.9kCompress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.