brand-voice

brand-voice is a skill for Claude Code, Codex from open-octo/octo-agent. It costs 200 tokens per session (1,896 once invoked), scanned A, original, MIT.

A writing guide that learns how a brand normally sounds from existing material, then applies that style to new text. It keeps the brand’s voice consistent while allowing the level of formality to change by situation.

In plain words
What is it for?
It helps define a brand voice, rewrite content to match it, check whether copy is on-brand, and keep wording consistent across channels.
Why use it?
It removes the guesswork and drift that can make each piece of content sound like it came from a different company.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps define a brand voice, rewrite content to match it, check whether copy is on-brand, and keep wording consistent across channels.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/open-octo/octo-agent/brand-voice
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 open-octo/octo-agent --skill brand-voice
Clone the repo
git clone --depth 1 https://github.com/open-octo/octo-agent

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.

agentmods badge for brand-voice

README.md
[![agentmods](https://agentmods.dev/badge/skills/open-octo/octo-agent/brand-voice/github.svg)](https://agentmods.dev/skills/open-octo/octo-agent/brand-voice)
Your own site
<a href="https://agentmods.dev/skills/open-octo/octo-agent/brand-voice"><img src="https://agentmods.dev/badge/skills/open-octo/octo-agent/brand-voice/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.

agentmods 80×15 button for brand-voice

Your own site · 80×15
<a href="https://agentmods.dev/skills/open-octo/octo-agent/brand-voice"><img src="https://agentmods.dev/badge/skills/open-octo/octo-agent/brand-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 200 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,896 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00200 $0.01896
Opus 5 $0.00100 $0.00948
Sonnet 5 $0.00040 $0.00379
Haiku 4.5 $0.00020 $0.00190

Measured 8d ago against content hash a87c54f055a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

brand-voice 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 8d 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.

internal/skills/experts/brand-voice/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

品牌声音(Brand Voice)

让该专家产出的每一条文案都落在同一个声音里。核心是"声音恒定、语气可调"(Voice constant, tone flexes)——先提炼一份品牌声音指南,再把它应用到所有文案。

先判断:用户是要"定声音"还是"用声音"

  • 定声音:用户还没有品牌声音指南,或想重做。走「提炼指南」。
  • 用声音:用户已有指南(本会话生成过,或提供了),只想按它写、按它改。走「应用指南」。
  • 校准某一条:用户给出具体文案,问"这是不是我们的调性"。走「应用指南」+「校验」。

不知道时说清楚,别默认。用户只是随口说"写得有调性一点"时,先快速提炼一份轻量指南再写。


提炼指南(生成品牌声音指南)

1. 收集素材

从已有的东西里提炼,不要凭空造。按优先级问/拿:

  • 已有的、用户喜欢的文案:过去写得好、用户认可的内容(社媒帖、广告语、产品介绍、Slogan)。
  • 产品/品牌资料:产品定位、目标人群、价格档位、竞品。
  • 语气形容:用户用形容词描述想要的调性("专业但不冷""亲和""高级""接地气"),以及明确不要的("别太emo")。
  • 说话的人:这声音是"一个人"还是"一个品牌"?用第一人称吗?(决定口吻来源。)

如果用户懒得多给,就从当前对话/上下文 + 产品资料里提炼一版草稿,标注「推断,可修改」,别卡住。

2. 单源提炼

有充足素材时,逐条抽出特征:

  • 反复出现的用词、句长、标点习惯
  • 是否用梗、emoji、英文缩写
  • 是陈述型还是互动型,是"我们很牛"还是"你被看见"
  • 例子:直接摘一段用户认可的原文作为"像我们"的范例

3. 合成指南

输出一份紧凑的「品牌声音指南」,固定用这个模板:

## 品牌声音指南

### 一句话定位
[用一句话说清这个声音像谁。例:一个懂数据、说话不绕弯的资深顾问,专业但不端着。]

### We Are / We Are Not(核心人格锚点)
| 我们是 | 我们不是 |
|--------|----------|
| [例:专业] | [例:冷冰冰/爹味] |
| [例:真诚] | [例:套路/夸大] |
| [例:利落] | [例:啰嗦/堆砌] |
| [例:有温度] | [例:过度emo/卖惨] |

### 声音恒定 vs 语气可调
- **恒定(Voice)**:人格、价值观、We Are / We Are Not、禁用语——**所有平台、所有内容都一样**。
- **可调(Tone)**:正式度、能量、专业深度——**随平台和受众变化**。

### 语气-场景矩阵(Tone by Context)
| 场景 | 正式度 | 能量 | 专业深度 | 示例句 |
|------|--------|------|----------|--------|
| 小红书种草 | 低 | 高 | 低 | "[示例]" |
| 公众号长文 | 中 | 中 | 中 | "[示例]" |
| 商务邮件/提案 | 高 | 中 | 高 | "[示例]" |
| 短视频口播钩子 | 低 | 高 | 低 | "[示例]" |

### 术语与措辞
- **偏好用词**:[例:说"体验"不说"使用",说"帮你"不说"我司"]
- **禁用词**:[例:遥遥领先、赋能、打造闭环、震惊体、绝对最强]

### 范例(最像我们的文字)
> [摘一段用户认可的原稿,作为"像我们"的黄金样本]

每条 We Are 特征尽量配一句证据/来源;没有证据就标注「推断」。

4. 不确定的,写进"待定问题"

无法从素材判断的,别硬编进指南。单列一节:

### 待定问题(Open Questions)
1. **甜度/梗的浓度**
   - 发现:素材里梗很多,但不确定产品调性是否允许
   - 建议:先按「轻量梗 + 克制」处理
   - 需要你定:正式 vs 俏皮?

每条待定都要附一个建议默认值,让用户"确认或推翻",不留下死路。


应用指南(把声音套到文案上)

1. 先定义这次任务

写之前明确:内容类型(社媒/公众号/邮件/标题)、受众(谁看、什么段位)、核心信息(要点)、形式约束(字数/篇幅/是否要 emoji)。

2. 套用恒定的声音

  • 读一遍「We Are / We Are Not」,所有内容贴着"我们是"写,避开"我们不是"。
  • 用偏好用词,绝不碰禁用词。
  • 让人格贯穿全文,不虎头蛇尾。

3. 按场景调节语气

查语气-场景矩阵,设定本次的正式度/能量/专业深度。调整的是语气强度,不是人格身份——同一段话可以更正式或更俏皮,但"是谁在说话"不变。

Read the full file on GitHub · 137 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.

  1. 8d ago First seen · 137 lines · 200 tokens per session scan A a87c54f055a8

Subscribe to this mod's changes

brand-voice is a skill published in the GitHub repository open-octo/octo-agent (99 stars, last pushed yesterday), licensed MIT. It adds 200 tokens to every session and 1,896 once invoked, about $0.0010 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 2026-09-03.

Related

Other skills, from other repositories

ha-mac-control

Hope Agent native macOS desktop control — the standard maccontrol status / diagnostics / apps / dock / spaces / snapshot / visual / windows / menu / clipboard / dialog loop, target-first action rules, no-blind-coordinate policy, and recovery for stale AX/window/menu/dialog state. Load whenever using maccontrol, or…

shiwenwen/hope-agent · 139 tokens

ha-skill-creator

Create, edit, improve, or audit Hope Agent skills. Use when the user wants to: (1) create a new skill from scratch, (2) edit or improve an existing skill, (3) review or clean up a SKILL.md file, (4) run evaluations to test skill effectiveness, (5) optimize skill descriptions for better trigger accuracy. Trigger…

shiwenwen/hope-agent · 106 tokens

ha-browser

Hope Agent browser automation — the standard status → tabs → snapshot → act loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the browser tool. Trigger on: user asks the agent to open / control / click / scrape /…

shiwenwen/hope-agent · 140 tokens

ha-logs

A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.

shiwenwen/hope-agent · 183 tokens

ha-pet-import

Safely import, select, switch, or enable a compatible desktop pet in Hope Agent. Resolve packages from any origin, including local folders, zip archives, pet.json plus a sprite, PNG/WebP atlases, chat attachments, repository or cloud files, direct HTTPS artifact URLs, and download pages. Use whenever a user asks to…

shiwenwen/hope-agent · 109 tokens

feishu

A toolkit for working with Feishu, also called Lark, a workplace collaboration platform. It covers documents, spreadsheets, files, wikis, approvals, calendars, and contacts.

shiwenwen/hope-agent · 189 tokens