
Writing prompts
How to write LLM system prompts: role, structured output, injection resistance.
- Scripts
- None
- Platforms
- Claude Code, Codex, Cursor
- GitHub stars
- 155
- Last commit
- today
- License
- ISC
- Listing updated
- today
When your agent uses it
How to write LLM system prompts: role, structured output, injection resistance.
From the skill's SKILL.md. Your agent reads this description to decide when to load the skill.
What it can access
From a static check of its 1 file (10 KB) on GitHub on 17 November 2026. Nothing was run. Read the files before you install a skill: it can tell your agent to run anything its tools allow.
Install
This skill ships in the nlpm plugin. In Claude Code, add the marketplace and install the plugin (it may include other skills too):
/plugin marketplace add xiaolai/nlpm
/plugin install nlpm@xiaolaiOr copy only this skill to ~/.claude/skills/writing-prompts:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/xiaolai/nlpm.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/writing-prompts &&
cp -R "$tmp/skills/nlpm/writing-prompts" ~/.claude/skills/writing-prompts &&
rm -rf "$tmp"For one project only, put the folder in .claude/skills/writing-prompts inside it instead.
Copy the skill folder to ~/.agents/skills/writing-prompts to use it in every repository:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/xiaolai/nlpm.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/writing-prompts &&
cp -R "$tmp/skills/nlpm/writing-prompts" ~/.agents/skills/writing-prompts &&
rm -rf "$tmp"For one repository only, put the folder in .agents/skills/writing-prompts inside it instead.
Copy the skill folder to ~/.cursor/skills/writing-prompts to use it in every project:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/xiaolai/nlpm.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/writing-prompts &&
cp -R "$tmp/skills/nlpm/writing-prompts" ~/.cursor/skills/writing-prompts &&
rm -rf "$tmp"For one project only, put the folder in .cursor/skills/writing-prompts inside it instead.
Run in a terminal (add --scope workspace to install it for the current workspace only):
gemini skills install https://github.com/xiaolai/nlpm.git --path skills/nlpm/writing-promptsOr copy the folder to ~/.gemini/skills/writing-prompts yourself.
For GitHub Copilot in VS Code, copy the skill folder to ~/.copilot/skills/writing-prompts:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/xiaolai/nlpm.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/writing-prompts &&
cp -R "$tmp/skills/nlpm/writing-prompts" ~/.copilot/skills/writing-prompts &&
rm -rf "$tmp"For one project only, put the folder in .github/skills/writing-prompts inside it instead.
Get the folder:
git clone --depth 1 https://github.com/xiaolai/nlpm.gitThen copy nlpm/skills/nlpm/writing-prompts into your agent's skills folder as writing-prompts. Agents that support SKILL.md read one folder per skill.
Writing prompts FAQ
How do I install Writing prompts in Claude Code?
Copy the skill folder from GitHub to ~/.claude/skills/writing-prompts to use it in all your projects, or to .claude/skills/writing-prompts in one project. Or install the nlpm plugin, which includes it: /plugin marketplace add xiaolai/nlpm, then /plugin install nlpm@xiaolai.
Does Writing prompts run scripts?
No. It is instructions only, with no scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.
Which AI agents can use Writing prompts?
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.
What are the best alternatives to Writing prompts?
The closest alternatives to Writing prompts are Academy guide, MCP builder, Claude API, Nano banana pro openrouter and Generate image.
More from xiaolai/nlpm

Universal NL conventions: SKILL.md open spec, AGENTS.md, vague quantifiers, naming.
- Open source
- 155 GitHub stars

Antigravity and Gemini CLI artifact schemas: .gemini/ paths, extensions, hooks.
- Open source
- 155 GitHub stars

Claude Code artifact schemas: plugin.json, frontmatter, hooks, settings, tools.
- Open source
- 155 GitHub stars
- AI models and LLM tooling

Codex CLI artifact schemas: config.toml, .codex-plugin, skills, hooks, AGENTS.md.
- Open source
- 155 GitHub stars

Multi-agent workflow patterns: parallel dispatch, pipelines, QC gates, retries.
- Open source
- 155 GitHub stars

NL artifact anti-patterns: vague quantifiers, bare prohibitions, oversized skills.
- Open source
- 155 GitHub stars
Alternatives to Writing prompts

Academy guide
SkillStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching cour
- 196K GitHub stars
- AI models and LLM tooling

MCP builder
SkillGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-design
- 196K GitHub stars
- AI models and LLM tooling

Claude API
SkillReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model
- 196K GitHub stars
- AI models and LLM tooling

Generate or edit images via OpenRouter with the Gemini 3 Pro Image model
- Open source
- 41.3K GitHub stars
- Design and media


Phoenix evals
SkillBuild and run evaluators for AI/LLM applications using Phoenix.
- Open source
- 41.3K GitHub stars
- AI models and LLM tooling



