Prompt Writer

Use this skill when the user asks to write, improve, or revise a prompt for an LLM. Triggers on system prompts, agent and role prompts (support assistants, person imitation, ghostwriter bots), instructions for repeatable tasks (extraction, transformation, classification), grading prompts, tasks for coding agents, and Claude Project instructions. Also triggers on "make Claude do X", "set up an assistant for Y", "write instructions so that the bot Z", "prompt for coding agent", "напиши промпт", "сделай инструкцию для модели", "помоги настроить ассистента", "улучши этот промпт", "промпт для Claud

5 stars 2 forksAI, LLMs & Agents Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add Londeren/claude-plugins

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add Londeren/claude-plugins --skill prompt-writer
Manual install
git clone --depth 1 https://github.com/Londeren/claude-plugins.git /tmp/claude-plugins
mkdir -p ~/.claude/skills
cp -r /tmp/claude-plugins/plugins/prompt-writer/skills/prompt-writer ~/.claude/skills/prompt-writer

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Prompt Writer

A skill for writing high-quality LLM prompts (especially for Claude), based on close reading of the Claude system prompts (Opus 4.7, Fable 5, Opus 5) and how attention uses a prompt.

## When this skill is active

The user wants to create or improve an instruction for an LLM. It can be a system prompt, a role prompt, an agent instruction, a prompt template, a Claude Project setup, or a specific prompt for a repeatable task. The skill follows a process: understand the task → determine the type → apply the template → audit the draft → deliver the final version.

## The process

### Step 1: Understand the task

If the user gave a detailed spec with examples, goals, audience, and constraints, do NOT ask clarifying questions, start immediately with inline assumptions. Second-guessing a detailed request hurts.

If the spec is vague ("write a prompt for an assistant"), ask the minimum number of questions needed to determine the prompt type. No more than 2-3 questions at a time.

The minimum that has to be known before starting:
- What the prompt is supposed to do
- Which model or tool the prompt is written for. If it is not stated, assume Claude, mark that assumption inline in the result, and do not spend a question on it. The rules of this skill are calibrated for Claude; for other tools they apply as they are, with no adaptation
- What format and length of output the user expects
- The success criterion, how the user will know the prompt worked
Read the full skill on GitHub

Details

Skill name
prompt-writer
Path
plugins/prompt-writer/skills/prompt-writer/SKILL.md
License
MIT
Repo updated
28 September 2026

FAQ

What does the Prompt Writer skill do?

Use this skill when the user asks to write, improve, or revise a prompt for an LLM. Triggers on system prompts, agent and role prompts (support assistants, person imitation, ghostwriter bots), instructions for repeatable tasks (extraction, transformation, classification), grading prompts, tasks for coding agents, and Claude Project instructions. Also triggers on "make Claude do X", "set up an assistant for Y", "write instructions so that the bot Z", "prompt for coding agent", "напиши промпт", "сделай инструкцию для модели", "помоги настроить ассистента", "улучши этот промпт", "промпт для Claud

How do I install the Prompt Writer skill?

Claude Code plugin: /plugin marketplace add Londeren/claude-plugins. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Prompt Writer popular?

It lives in Londeren/claude-plugins, which has 5 GitHub stars and 2 forks.

Related skills

Book to Skill

5

Londeren/claude-plugins

Use when the user wants to turn a knowledge source in Markdown (a book, manual, course, lecture notes, transcript) into a Claude skill, or to extract a method, methodology, or playbook from a large text into reusable agent instructions. Triggers on "make a skill from this book", "extract the methodology", "turn this into a playbook", "distill this source into a SKILL.md", "сделай скилл из книги", "перегони методичку в скилл", "извлеки методологию", "собери инструкцию по книге", "дистиллируй источник", and when the user brings a large .md with someone else's method and wants a working tool even

AI, LLMs & Agents

Infostil Redaktura

5

Londeren/claude-plugins

Редактирует и пишет деловой текст по информационному стилю Ильяхова и Сарычевой — от диагностики полезного действия до чистки слов, синтаксиса, абзацев и структуры. Используй, когда просят «отредактируй текст», «сократи», «убери воду», «сделай понятнее», «перепиши по-человечески», «почисти канцелярит», «напиши текст о себе / о компании / пресс-релиз / холодное письмо / промостраницу / слайды / отчёт руководителю», «почему этот текст не читают», «сделай по Ильяхову», а также для отзыва на вакансию, объявления, рассылки, лендинга и ответа гражданину. Не используй для художественного текста и для

Other

Infostyle

5

Londeren/claude-plugins

Use when working with Russian non-fiction text — editing, shortening, de-watering, or writing it from scratch. Triggers - "отредактируй текст", "сократи", "убери воду", "перепиши по-человечески", "инфостиль", "Главред", "почисти канцелярит", "сделай понятнее", "текст о себе", "текст о компании", "отчёт руководителю", "пресс-релиз", "холодное письмо", "слайды", "лендинг", "промостраница", "объявление для жильцов", "письмо клиенту". Also when a draft reads as marketing fluff, bureaucratese, or "много слов, а смысла нет". Not for fiction, poetry, lyrics, legal instruments, or English-language cop

Marketing, Sales & Business

Nba Agent

5

Gainsight-Central/gainsight-ai-cookbook

Customer-agnostic next-best-action agent for CSMs. Use when the user says "start the NBA agent" or "run the NBA agent", asks to set up or configure the NBA agent for a customer, or asks for drafted outreach emails for the accounts in their book. Checks for a saved customer configuration first and asks for anything missing, then asks the user to define a goal (adoption is the first use case), finds the accounts that raised it, grounds each recommendation in real account context, drafts one personalized email per recipient, shows a funnel with drill-downs, and stops for CSM approval. All custome

AI, LLMs & Agents

Naiyue Thinking

5

tlzmw001/naiyue-skills

按耐阅的个人工程判断方式分析问题并组织行动。用于架构或方案取舍、项目学习与复杂机制解释、skill/prompt/agent 系统设计、代码审查、具有下游影响的决策,以及重复问题复盘。强调当前仓库事实、来源与产物边界、最小可用路径、AI 与确定性机制的职责分工,并保留用户对重要结论的最终确认。不用于纯事实查询、机械格式转换、无需判断的一步操作或闲聊。

AI, LLMs & Agents

Agents

9

zllovesuki/cloudflare-agent-skills

Build Cloudflare Agents SDK applications for autonomous multi-step tool use, AIChatAgent chat agents, Durable Object-backed state, tools, scheduling, callable methods, WebSockets, SQL state, and constrained agent behavior. Use when RAG or Workflows are not enough.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.