Brief Output

精简回答、技术说明与工程文档,删除冗余信息与 AI 味表达,只保留完成任务所需的必要事实与技术决策。适用于精简输出、压缩改写、去除 AI 腔调以及全文一致性修订。

9 stars 1 forksAI, LLMs & Agents

Install

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

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

From the SKILL.md

# Brief Output Skill

先给结论。只保留读者完成当前任务所需的信息。删除后若不影响理解、实施或必要验证,一律删除。

## 工作流程

1. **结论前置**:开门见山给出直接结论或操作结果。不写寒暄、引言和铺垫。
2. **评估必要性**:逐句检查信息价值。先判断能否删除,再做润色。无需保留的信息直接删除,不改写为其他形式。
3. **剔除冗余与修辞**:删除比喻、口号、假想争论、过度承诺、讨论过程以及未要求的延展建议。
4. **精炼结构与表格**:同一事实只定义一次。表格某列取值全部相同时,提炼为表前一句话说明,并删除该重复列。删除与正文或表格重复的括注、样例和总结。
5. **全文一致性复核**:用户指出一处冗余或风格问题时,检查全文同类问题。用户认可简洁稿后,后续修订保持同等信息密度,不补回已删说明。

## 表达与删减规则

- **语言规范**:使用短句、主动语态和固定术语。一句话只表达一个要点。不使用分号连接无关复合句。
- **保留核心事实**:保留真实例外条件、约束、错误处理、不确定性和结论强度。不通过删除关键事实制造虚假确定性。
- **明确区分状态**:严格区分现有系统行为、本次方案设计与已实施结果。
- **消除代词指代**:将“该方案”、“上文所述”等会话指代替换为可独立理解的对象名称、文件路径或链接。
- **设计文档边界**:
  - 只写本次必要设计。已有机制满足需求时,一句说明沿用并注明来源,不重复展开设计。
  - 源码与配置能解决的技术决策由设计直接确定,不列为业务待确认项。
  - 不因精简或审查新增通用防护、恢复机制、边缘场景和冗余验证。
  - 默认不附部署计划、测试方案、证据清单或分析报告,除非用户明确要求。

## AI 冗余模式与替换指南

| 冗余模式 | 表现特征 | 处理方式 |
|---|---|---|
| 铺垫与寒暄 | “总的来说”、“值得注意的是”、“在开始之前...” | 删除,直接陈述事实 |
| 虚假承诺与空话 | “后续将进一步完善并确保系统高可用稳健运行...” | 仅保留有依据的具体机制,无依据直接删除 |
| 模板空章节 | 章节下仅写“不涉及”或“无” | 删除整节(除非用户明确要求保留完整模板骨架) |
| 重复定义 | 表格定义字段后,正文再次逐一复述每一字段 | 保留权威表格或单处定义,删除重复复述 |
| 过程性元话语 | “经过上一轮审查分析,我们得出以下改动...” | 删除审查过程,直接陈述最终确定的技术事实 |

## 校验清单

完成输出前,逐项核对:

1. 核心结论是否位于第一句?
2. 是否已删除所有空泛引言、比喻和推销式修辞?
3. 所有技术事实是否仅定义一次,无前后重复复述?
4. 是否保留了真实的安全约束、边界条件与失败处理规则?
5. 全文同类冗余是否均已清除?
Read the full skill on GitHub

Details

Skill name
brief-output
Path
.claude/skills/brief-output/SKILL.md
License
MIT
Repo updated
14 November 2026

FAQ

What does the Brief Output skill do?

精简回答、技术说明与工程文档,删除冗余信息与 AI 味表达,只保留完成任务所需的必要事实与技术决策。适用于精简输出、压缩改写、去除 AI 腔调以及全文一致性修订。

How do I install the Brief Output skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add lingengyuan/my-skills --skill brief-output. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Brief Output popular?

It lives in lingengyuan/my-skills, which has 9 GitHub stars and 1 forks.

Related skills

Google Go Style

9

lingengyuan/my-skills

按 Google Go Style 编写、重构或审查 Go 代码。用于命名、注释、接口、错误处理、并发、包组织与可维护性决策。

Software Development

Insight Collector

9

lingengyuan/my-skills

Analyze URLs, source code, images, technical documents, or notes, and archive reusable insights, code snippets, and architecture patterns into a knowledge base. Use when collecting knowledge, archiving technical articles, saving reusable code, or recording insights (收录, 记录一下).

Software Development

Insights Report

9

lingengyuan/my-skills

Generate a usage insights report from local Claude Code, Codex, pi, and omp session transcripts. Use when the user asks for an insights report, session analysis, usage review, "how do I work with agents", or runs /insights-report.

AI, LLMs & Agents

Cc Audit

10

thatmike1/claude-skills

Audits Claude Code setup and usage patterns, flagging anti-patterns (wrong launch dirs, context bloat, orphaned memories, missing CLAUDE.md) with severity-ranked fixes. Use when user says audit, health check, setup check, cc audit, or wants to improve their Claude Code workflow.

AI, LLMs & Agents

Arena

10

thatmike1/claude-skills

Give several T3 child candidates the same prompt, rank them against a rubric written before they run, pick a base and graft the best of the rest into it. Run with /arena when one attempt at a non-trivial artifact would lock in the wrong shape.

AI, LLMs & Agents

Gpt Pro

10

thatmike1/claude-skills

Hand a question to ChatGPT's Pro model or its image generator through the user's own chat window, off the Codex meter — the agent packs the prompt and context, the user pastes it and copies the answer back. Use when a plan or design wants a second opinion from another model family, for a large divergent idea run, for self-contained 3D or math-heavy code, for an image, or when the user says gpt-pro or asks to put something to ChatGPT.

AI, LLMs & Agents

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