Automated summary
Expert prompt engineering skill for crafting effective prompts for LLM coding agents across multiple tools, producing strategy documents and ready-to-use prompt artifacts.
Strengths
- Adapts prompts to target tool conventions (Claude Code, Cursor, Codex, etc.)
- Uses proven techniques from prompting research
- Provides strategy documents and ready-to-use artifacts
- Can iterate and refine using reference docs
Limitations
- May require understanding of specific tool context
- Effectiveness depends on clarity of user intent
- Might not cover tool-specific quirks outside documented conventions
Use when you need to create highly effective prompts for coding agents, especially when adapting to different tool interfaces or complex tasks.
Avoid when simple direct prompts suffice, or when the tool's built-in prompt patterns are adequate.
Security analysis
SafeThe skill only provides meta-level guidance on writing prompts for AI coding tools. It uses read-only and search tools (Read, Glob, Grep, WebFetch, WebSearch) and has no ability to execute commands or modify system state.
No concerns found
How this analysis is madeExamples
Create an expert prompt for Cursor to implement a user authentication system using JWT. The prompt should follow Cursor's conventions and include step-by-step instructions, error handling, and testing guidelines.Write a strategy document and ready-to-use prompt for Claude Code to refactor a legacy Python module. Include research-based prompting techniques and ensure the prompt is tailored to Claude Code's capabilities.I need a prompt that works for both Claude Code and Codex to generate unit tests for an API. Adapt the prompt to each tool's conventions and provide two versions.name: prompt-writing description: > Expert prompt engineering for LLM coding agents. Use when writing prompts for Claude Code, Cursor, Aider, Cline, OpenCode, Gemini, or Codex. Produces strategy documents and ready-to-use prompt artifacts. allowed-tools:
- Read
- Write
- Edit
- Glob
- Grep
- WebFetch
- WebSearch
Prompt Writing
Expert prompt engineering for LLM coding tools.
Capabilities
- Write prompts for Claude Code, Cursor, Aider, Cline, OpenCode, Gemini, Codex
- Adapt output to target tool conventions
- Use proven techniques from prompting research
Reference Docs
Load on-demand:
- @docs/techniques/*.md - Prompting techniques
- @docs/tools/*.md - Tool-specific conventions
- @docs/anti-patterns.md - Common pitfalls
- @docs/refinement-strategies.md - Iteration approaches
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/prompt-engineering-for-llm-coding-agents-mm5t8amp/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/prompt-engineering-for-llm-coding-agents-mm5t8amp' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/prompt-engineering-for-llm-coding-agents-mm5t8amp/download' --output '.skill-downloads/prompt-engineering-for-llm-coding-agents-mm5t8amp/SKILL.md.part' && mv '.skill-downloads/prompt-engineering-for-llm-coding-agents-mm5t8amp/SKILL.md.part' '.skill-downloads/prompt-engineering-for-llm-coding-agents-mm5t8amp/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/prompt-engineering-for-llm-coding-agents-mm5t8amp/SKILL.md' && test -s '.skill-downloads/prompt-engineering-for-llm-coding-agents-mm5t8amp/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/prompt-writing' && cp -R '.skill-downloads/prompt-engineering-for-llm-coding-agents-mm5t8amp' '.claude/skills/prompt-writing'Cursor
test -f '.skill-downloads/prompt-engineering-for-llm-coding-agents-mm5t8amp/SKILL.md' && test -s '.skill-downloads/prompt-engineering-for-llm-coding-agents-mm5t8amp/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/prompt-writing' && cp -R '.skill-downloads/prompt-engineering-for-llm-coding-agents-mm5t8amp' '.cursor/skills/prompt-writing'Codex
test -f '.skill-downloads/prompt-engineering-for-llm-coding-agents-mm5t8amp/SKILL.md' && test -s '.skill-downloads/prompt-engineering-for-llm-coding-agents-mm5t8amp/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/prompt-writing' && cp -R '.skill-downloads/prompt-engineering-for-llm-coding-agents-mm5t8amp' '.agents/skills/prompt-writing'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/prompt-engineering-for-llm-coding-agents-mm5t8amp'openskills read 'prompt-engineering-for-llm-coding-agents-mm5t8amp'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/prompt-engineering-for-llm-coding-agents-mm5t8amp/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.