Home / open-octo / octo-agent · GitHub

brand-voice SKILL.md skillA

brand-voice from open-octo/octo-agent is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add open-octo/octo-agent/brand-voice@git:20260831.acbf459

Pins git:20260831.acbf459 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
open-octo/octo-agent
Path
internal/skills/experts/brand-voice/SKILL.md
Versions recorded
1
Latest version
git:20260831.acbf459, committed Aug 31, 2026
Size
6,475 bytes
Repository stars
140
License
MIT

提炼并应用品牌声音（Brand Voice）。当用户要求"让文案符合品牌调性""定一下咱们的语气""按我们的风格写""这是我们的 on-brand 文案吗""写得更像我们""统一口吻""别这么官方/别这么网络梗"时使用。它先帮用户从已有素材里提炼出一份"品牌声音指南"，再把这份指南套用到每一条文案上，确保多次产出依然稳定、一个调性。不适合：纯找素材（交给用户直接提供），也不适合一次性写文案不带品牌约束（直接用 Copywriting skill）。触发词："品牌声音 / 品牌调性 / 语气 / 人设 / 口吻 / on-brand / 像我们 / 统一风格 / 太官方 / 太像 AI / 品牌人格"。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 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：

```markdown
## 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）
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add open-octo/octo-agent/brand-voice@sha256:a87c54f055a8935c

The line at the top of this page pins the label git:20260831.acbf459, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_swouosip5uib2mvb.svg)](https://markdownregistry.com/a/art_swouosip5uib2mvb)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Aug 31, 2026.

versioncommittedcommitsizeaudit
git:20260831.acbf459 latest2026-08-31 acbf459 6,475 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (6475 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

open-octo/octo-agent · 140 stars · license MIT · pushed 2026-11-02 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_swouosip5uib2mvb
GET https://markdownregistry.com/api/v1/resolve?ref=open-octo/octo-agent/brand-voice
GET https://markdownregistry.com/api/v1/blob/a87c54f055a8935cc8e385d9741b16938f0932a9f7082f8173ce8a95d2eee0ec

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from open-octo/octo-agent

CLAUDE.md CLAUDE.md file
open-octo/octo-agent · CLAUDE.md
git:20261014.4ebb825 · audit A · 140 stars
artifact-design SKILL.md skill
open-octo/octo-agent · internal/skills/defaults/artifact-design/SKILL.md · Design guidance for any HTML/Markdown file shown in octo's Artifacts panel — reports, dashboards, architecture/system…
git:20260923.bfb1a61 · audit B · 140 stars
channel-manager SKILL.md skill
open-octo/octo-agent · internal/skills/defaults/channel-manager/SKILL.md · Configure IM platform channels (Feishu, Weixin/WeChat, WeCom, DingTalk, Discord, Telegram) for octo. Guides the user…
git:20260924.b98ea0b · audit B · 140 stars
code-review SKILL.md skill
open-octo/octo-agent · internal/skills/defaults/code-review/SKILL.md · Review local code changes. Uses an isolated sub-agent for unbiased analysis when the main agent wrote the code; reviews…
git:20260920.c947ee9 · audit A · 140 stars
config-setup SKILL.md skill
open-octo/octo-agent · internal/skills/defaults/config-setup/SKILL.md · Configure octo's global settings through guided conversation — set up AI model endpoints (providers, API keys, models)…
git:20260924.b98ea0b · audit B · 140 stars
cron-task-creator SKILL.md skill
open-octo/octo-agent · internal/skills/defaults/cron-task-creator/SKILL.md · Create, inspect, run, edit, enable/disable, and delete octo's scheduled cron tasks — recurring agent prompts stored in…
git:20261012.05c8065 · audit B · 140 stars
deep-research SKILL.md skill
open-octo/octo-agent · internal/skills/defaults/deep-research/SKILL.md
git:20260807.58b8c70 · audit B · 140 stars
expert-agent-manager SKILL.md skill
open-octo/octo-agent · internal/skills/defaults/expert-agent-manager/SKILL.md · Manage octo's agent profiles through conversation — create, modify, delete, list, and bind agents to IM chats by…
git:20260924.b98ea0b · audit A · 140 stars
genui SKILL.md skill
open-octo/octo-agent · internal/skills/defaults/genui/SKILL.md · Render structured, glanceable, interactive UI in the chat instead of plain text — dashboards, stat cards, filterable…
git:20260923.e099c80 · audit A · 140 stars
grill-me SKILL.md skill
open-octo/octo-agent · internal/skills/defaults/grill-me/SKILL.md
git:20260713.070d20e · audit B · 140 stars
image-gen SKILL.md skill
open-octo/octo-agent · internal/skills/defaults/image-gen/SKILL.md · Acquire images as files — generate them with an AI image model (14 providers: OpenAI/gpt-image, Gemini, Qwen, Zhipu…
git:20260907.f18641e · audit A · 140 stars
implement SKILL.md skill
open-octo/octo-agent · internal/skills/defaults/implement/SKILL.md · Implement a technical design by decomposing it into dependency-ordered vertical slices, executing each with TDD…
git:20260711.2cb5a53 · audit A · 140 stars

Every file in open-octo/octo-agent

Other files named brand-voice

brand-voice SKILL.md skill
affaan-m/ecc · docs/ja-JP/skills/brand-voice/SKILL.md · 実際のポスト、エッセイ、ローンチノート、ドキュメント、またはサイトコピーからソース派生の執筆スタイルプロファイルを構築し、コンテンツ、アウトリーチ、ソーシャルワークフロー全体でそのプロファイルを再利用します。ユーザーが一般的なAI執筆トロー…
git:20261020.014fcae · audit A · 293,827 stars
brand-voice SKILL.md skill
affaan-m/ecc · .agents/skills/brand-voice/SKILL.md · Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that…
git:20260918.c752aac · audit A · 293,827 stars
brand-voice SKILL.md skill
cbrock84/headcount · plugins/marketing/skills/brand-voice/SKILL.md · Captures how a person or brand actually writes and turns it into reusable voice instructions every other content skill…
git:20260901.b973f20 · audit A · 2,543 stars
brand-voice SKILL.md skill
hashgraph-online/awesome-codex-plugins · plugins/Colin4k1024/tsp/skills/brand-voice/SKILL.md · Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that…
git:20260512.6523792 · audit A · 1,501 stars
brand-voice SKILL.md skill
rampstackco/claude-skills · skills/brand-voice/SKILL.md · Develop or document a complete brand voice and tone system covering voice attributes, tone shifts by context…
git:20260810.1d637e9 · audit A · 1,013 stars
brand-voice SKILL.md skill
ericrisco/rsc-harness · skills/brand-voice/SKILL.md · Use when defining how a brand SOUNDS as a reusable system: adjectives turned into linguistic rules, four tone…
git:20261011.c7821cd · audit A · 429 stars
brand-voice SKILL.md skill
runxhq/runx · skills/brand-voice/SKILL.md · Build a scoped brand voice packet from source material so downstream agents can write, review, and adapt content…
git:20261023.420f372 · audit A · 105 stars
brand-voice SKILL.md skill
cofoundy/brand-skills · skills/brand-voice/SKILL.md · Define a brand's verbal identity — tone, voice, writing style, vocabulary, and messaging rules. Use when the user says…
v1.0.0 · audit A · 68 stars

Browse by kind, by grade A, or by owner.