prompt-writing

prompt-writing is a skill for Claude Code from ModelEngine-Group/nexent. It costs 51 tokens per session (592 once invoked), scanned A, original, MIT.

A skill for creating and improving YAML prompts for AI assistants. YAML is a text format that organizes settings and multi-line instructions.

In plain words
What is it for?
Use it when writing system prompts, user prompts, prompt templates, or other AI instructions that need sections, placeholders, and validation.
Why use it?
It helps prompts stay structured, readable, consistently formatted, and safe to reuse with variables.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

About the project

Nexent is a zero-code platform for creating AI agents from natural-language instructions, combining tools, skills, memory, orchestration, constraints, feedback loops, and control planes. It is intended for people who need to build and deploy agents without writing orchestration code. The catalogue entries are rules and skills for working with Nexent.

ModelEngine-Group/nexent · 5,850 stars · on GitHub · modelengine-group.github.io

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/modelengine-group/nexent/prompts-writing
Any agent
npx skills add ModelEngine-Group/nexent --skill prompts-writing
Clone the repo
git clone --depth 1 https://github.com/ModelEngine-Group/nexent

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for prompt-writing

README.md
[![agentmods](https://agentmods.dev/badge/skills/modelengine-group/nexent/prompts-writing.svg)](https://agentmods.dev/skills/modelengine-group/nexent/prompts-writing)
Your own site
<a href="https://agentmods.dev/skills/modelengine-group/nexent/prompts-writing"><img src="https://agentmods.dev/badge/skills/modelengine-group/nexent/prompts-writing.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 592 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.00592
Opus 5 $0.00026 $0.00296
Sonnet 5 $0.00010 $0.00118
Haiku 4.5 $0.00005 $0.00059

Measured 6d ago against content hash 82a5f2834f10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

prompt-writing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/prompts-writing/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Writing

Create and optimize YAML-based prompts for AI assistants following industry best practices.

Quick Start

Standard YAML Prompt Structure

system_prompt: |-
  # Section with ### header
  ## Subsection with ## header
  Content with clear structure.
  
  **Bold key concepts**
  
  - Bullet points for requirements
  - Consistent indentation (2 spaces)
  
  1. Numbered lists for sequences
  2. Use when order matters

user_prompt: |
  Direct instructions with {{ variable placeholders }}

Key Principles

  1. Structure: Use |- for multi-line system prompts, | for user prompts
  2. Templating: Use {{ variable }} for dynamic content
  3. Separators: Use --- sparingly, only between major sections
  4. Language: Keep prompts in consistent language (English recommended for templates)

Quality Checklist

Before finalizing any prompt, verify:

  • No unclosed braces {{ without }}
  • No excessive separators (---, ***)
  • Consistent heading hierarchy (#####)
  • Clear variable placeholders with descriptive names
  • Proper YAML indentation preserved
  • No HTML tags in Markdown content
  • Lists have parallel structure

Common Patterns

System Prompt with Sections

system_prompt: |-
  ### Role Definition
  You are a professional [role name]. Your task is to [core responsibility].
  
  ### Requirements
  1. First requirement
  2. Second requirement
  3. Third requirement
  
  ### Guidelines
  - Do this
  - Don't do that
  - Always do this
  
  ### Output Format
  Respond in plain text without separators.

Jinja2 Template Variables

user_prompt: |
  Please analyze the following {{ document_type }}:
  
  Name: {{ filename }}
  Content: {{ content }}
  
  Summary ({{ max_words }} words):

References

Read the full file on GitHub · 100 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 100 lines · 51 tokens per session scan A 82a5f2834f10

Subscribe to this mod's changes

prompt-writing is a skill published in the GitHub repository ModelEngine-Group/nexent (5,850 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 592 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

extended-thinking

Use Claude's extended thinking (reasoning) mode effectively — budget tokens, interleaved thinking with tool use, when it helps, when it wastes tokens, and how to inspect the thinking trace. Use this skill when building reasoning-heavy features (math, code generation, multi-step planning), debugging why a model is…

latestaiagents/agent-skills · 101 tokens

long-context-1m

Use Claude's 1M-token context window effectively — when to use it, how to structure inputs for recall, how to price it, and how to combine with prompt caching to keep it affordable. Use this skill when building apps that feed large codebases, long documents, or entire conversation histories to Claude, or when weighing…

latestaiagents/agent-skills · 109 tokens

prompt-injection-guard

Use this skill when securing AI applications against prompt injection. Activate when the user needs to prevent prompt injection attacks, validate AI inputs, implement input sanitization, or protect against adversarial prompts.

latestaiagents/agent-skills · 47 tokens

prompt-linter

Checks new prompt versions for unsafe patterns, format drift, registry consistency.

suhaas/earnings-edge · 17 tokens

azure-openai-to-responses

Migrate Python apps from Azure OpenAI Chat Completions to the Responses API. Covers AzureOpenAI/AsyncAzureOpenAI client migration to the v1 endpoint, streaming, tools, structured output, multi-turn, EntraID auth, and model compatibility checks. Python-focused, Azure OpenAI-specific. USE FOR: migrate to responses API…

microsoft/ai-agents-for-beginners · 185 tokens

flow-nexus-neural

Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus.

ruvnet/ruflo · 21 tokens