What is output-formatting?

A set of rules for controlling an AI assistant’s answer length, format, and writing style.

Use it when designing prompts for chatbots, command-line tools, mobile assistants, or design generators that need consistent, direct output.

It helps prevent repetitive openings, unnecessary formatting, and answers that are too long or too short for the device or task.

output-formatting — Skill for Claude Code and Codex by kangarooking

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.

Any agent

npx skills add kangarooking/system-prompt-skills --skill output-formatting

Clone the repo

git clone --depth 1 https://github.com/kangarooking/system-prompt-skills

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/kangarooking/system-prompt-skills/output-formatting/github.svg)](https://agentmods.dev/skills/kangarooking/system-prompt-skills/output-formatting)

Your own site

<a href="https://agentmods.dev/skills/kangarooking/system-prompt-skills/output-formatting"><img src="https://agentmods.dev/badge/skills/kangarooking/system-prompt-skills/output-formatting/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/kangarooking/system-prompt-skills/output-formatting"><img src="https://agentmods.dev/badge/skills/kangarooking/system-prompt-skills/output-formatting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,630 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00110	$0.01630
Opus 5	$0.00055	$0.00815
Sonnet 5	$0.00022	$0.00326
Haiku 4.5	$0.00011	$0.00163

Measured 11d ago against content hash 06e1a57c73e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

output-formatting 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 11d 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.

output-formatting/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

输出格式与风格控制

R — 原文 (Reading)

多个 AI 供应商系统提示词中共同浮现的输出控制模式：按复杂度自适应长度、按平台定制格式、用反"AI slop"启发式规则消除机械化表达。Claude Mobile 按屏幕尺寸分四档长度；Gemini CLI 限制三行以内；Meta AI 禁用"Here's a..."等套话；Le Chat 用表格替代列表；Claude Design 禁用圆角容器和 Inter/Roboto 字体。

I — 方法论骨架 (Interpretation)

复杂度分级 — 按问题深度映射输出长度档位（一句话 / 短列表 / 两三段 / 完整文档）
平台感知 — 检测目标载体（CLI / 移动端 / 桌面 / API），应用对应格式约束
前置答案原则 — 结论先行，解释后置；"Always lead with the answer"
反 AI slop 规则集 — 禁止套话开头、无意义表情符号、过度格式化、破折号滥用
领域标记语言 — 为特定平台定制标记（Notion 压缩 URL {{1}}、GPT-4o image_group JSON）
格式降级策略 — 默认散文体，仅在必要时使用列表/表格，绝不"为了好看而格式化"
引用密度控制 — 代码引用使用 file_path:line_number 格式，摘要限制在 1-2 句

A1 — 案例分析 (Past Application)

案例: Claude Mobile 屏幕尺寸自适应输出

问题: 移动端屏幕空间有限，长回复导致用户需要大量滚动，体验差
设计模式的使用: Claude Mobile 系统提示词定义了四级长度策略：简单问题 → 1-2 句话；操作指南 → 短列表；实质性问题 → 2-3 段；复杂主题 → 不超过两屏。同时强制"答案先行"原则
结论: 该策略在有限屏幕空间内最大化信息密度，用户可快速获取核心答案，需要时再向下滚动查看细节

案例: Meta AI 反套话策略

问题: AI 回复普遍带有"Here's a..."、"Great question!"等机械化开场白，用户反感
设计模式的使用: Meta AI 系统提示词明确禁止此类套话，要求使用扁平列表、表格呈现结构化数据，禁止破折号，保持直接风格
结论: 消除 AI slop 后用户满意度显著提升，说明格式控制不仅是美学问题，更是体验核心

A2 — 触发场景 (Future Trigger) ★

用户在什么情境下需要?

设计聊天机器人系统提示词时，需要控制回复长度和格式
为 CLI 工具定义输出规范，要求简洁无废话
为移动端 AI 助手适配屏幕尺寸约束
设计品牌专属的 AI 输出风格指南（如设计工具中禁止特定字体和视觉元素）
构建多平台 AI 产品，需要为不同载体定义差异化输出策略

语言信号

"回复太长了/太啰嗦了"
"输出格式需要适配手机屏幕"
"不要那些 AI 常用的套话"
"简洁一点，像终端工具那样输出"
"品牌风格指南要求避免..."

与相邻 skill 的区分

与 conversation-flow 的区别: 本 Skill 聚焦输出的"形式"（长度/格式/风格），conversation-flow 聚焦交互的"流程"（路由/澄清/自主度）
与 context-management 的区别: context-management 管理输入侧的 token 预算，本 Skill 管理输出侧的格式密度

E — 可执行步骤 (Execution)

定义复杂度分级表 — 完成标准: 建立至少三档长度映射（简单/中等/复杂），每档有明确的句子数或行数上限，并与目标平台视口尺寸挂钩
编写反 AI slop 黑名单 — 完成标准: 列出至少 10 条禁止项（套话开场白、无意义表情符号、过度格式化、破折号滥用、Inter/Roboto 字体、圆角容器等），每条附带替代方案
设计平台格式规范 — 完成标准: 为每个目标平台（CLI/移动端/桌面/API）定义默认格式模式（如 CLI 默认三行散文体、移动端默认答案先行+短列表），包含领域专用标记语法说明
建立格式降级规则 — 完成标准: 明确"默认散文体 → 必要时列表 → 复杂时表格 → 极少时代码块"的升级路径，以及每级的使用触发条件

Read the full file on GitHub · 88 lines

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.

11d ago First seen · 88 lines · 110 tokens per session scan A 06e1a57c73e3

Subscribe to this mod's changes

output-formatting is a skill published in the GitHub repository kangarooking/system-prompt-skills (183 stars, last pushed 4mo ago), licensed MIT. It adds 110 tokens to every session and 1,630 once invoked, about $0.0006 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.

Building agents Prompt Injection agent-design ai ai-agents cangjie-skill context-management prompt-engineering 公众号

gpt-image-2-prompt-engine

A structured prompt-writing tool for GPT-Image-2, using reusable JSON templates and a four-step workflow. It is designed for controlled commercial images such as product photos, posters, infographics, brand visuals, UI screenshots, and character designs.

anbeime/skill · 146 tokens

output-formatting