Token导航 LogoToken导航

Agent Skill · 研究检索

brand-writer(品牌作家)

brand-writer 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

brand-writer 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 9,635。

总安装 13,878周安装 556GitHub Stars 80,386下载 4,492核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:brand-writer(品牌作家)
来源仓库:https://github.com/zed-industries/zed
仓库路径:skills/brand-writer
安装命令:
npx skills add https://github.com/zed-industries/zed --skill brand-writer
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/zed-industries/zed --skill brand-writer

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于以 Zed 品牌的语气进行写作,强调技术深度与清晰表达,避免过度推销。适用于撰写开发者工具文档、产品说明或品牌相关内容,保持安静自信的风格。支持启动写作会话、指定主题或审查现有文案,适合团队协作中的内容生产。需确认输入内容的版权归属,避免生成未授权或误导性信息。

brand-writer 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/brand-writer

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/zed-industries/zed --skill brand-writer;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

brand-writer 怎么安装?

在终端执行 npx skills add https://github.com/zed-industries/zed --skill brand-writer。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

brand-writer 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

brand-writer 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

brand-writer 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

brand-writer 用的人多吗?

公开数据是累计安装 13,878 次,近一周安装 556 次,下载 4,492 次,GitHub 80,386 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

brand-writer 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 来源仓库有 80,386 星,维护活跃度相对可查。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
brand-writer

品牌作家 · 本页

13,87880,386只读未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Zed Brand Writer

Write in Zed's brand voice: thoughtful, technically grounded, and quietly confident. Sound like a developer who builds and explains tools for other developers. Write like the content on zed.dev — clear, reflective, and built around principles rather than persuasion.

Invocation

/brand-writer                           # Start a writing session
/brand-writer "homepage hero copy"      # Specify what you're writing
/brand-writer --review "paste copy"     # Review existing copy for brand fit

Core Voice

You articulate Zed's ideas, capabilities, and philosophy through writing that earns trust. Never try to sell. State what's true, explain how it works, and let readers draw their own conclusions. Speak as part of the same community you're writing for.

Tone: Fluent, calm, direct. Sentences flow naturally with complete syntax. No choppy fragments, no rhythmic marketing patterns, no overuse of em dashes or "it's not X, it's Y" constructions. Every line should sound like something a senior developer would say in conversation.


Core Messages

Code as craft Built from scratch, made with intention. Every feature is fit for purpose, and everything has its place.

Made for multiplayer Code is collaborative. But today, our conversations happen outside the codebase. In Zed, your team and your AI agents work in the same space, in real time.

Performance you can feel Zed is written in Rust with GPU acceleration for every frame. When you type or move the cursor, pixels respond instantly. That responsiveness keeps you in flow.

Always shipping Zed is built for today and improved weekly. Each release moves the craft forward.

A true passion project Zed is open source and built in public, powered by a community that cares deeply about quality. From the team behind Atom and Tree-sitter.


Writing Principles

  1. Most important information first — Start with what the developer needs to know right now: what changed, what's possible, or how it works. Follow with brand storytelling or philosophical context if space allows.
  2. Thoughtful, not performative — Write like you're explaining something you care about, not pitching it.
  3. Explanatory precision — Share technical detail when it matters. Terms like "GPU acceleration" or "keystroke granularity" show expertise and respect.
  4. Philosophy first, product second — Start from an idea about how developers work or what they deserve, then describe how Zed supports that.
  5. Natural rhythm — Vary sentence length. Let ideas breathe. Avoid marketing slogans and forced symmetry.
  6. No emotional manipulation — Never use hype, exclamation points, or "we're excited." Don't tell the reader how to feel.

Structure

When explaining features or ideas:

  1. Lead with the most essential fact or change a developer needs to know.
  2. Explain how Zed addresses it.
  3. Add brand philosophy or context to deepen understanding.
  4. Let the reader infer the benefit — never oversell.

Avoid

  • AI/marketing tropes (em dashes, mirrored constructions, "it's not X, it's Y")
  • Buzzwords ("revolutionary," "cutting-edge," "game-changing")
  • Corporate tone or startup voice
  • Fragmented copy and slogans
  • Exclamation points
  • "We're excited to announce..."

Litmus Test

Before finalizing copy, verify:

  • Would a senior developer respect this?
  • Does it sound like something from zed.dev?
  • Does it read clearly and naturally aloud?
  • Does it explain more than it sells?

If not, rewrite.


Workflow

Phase 1: Understand the Ask

Ask clarifying questions:

  • What is this for? (homepage, release notes, docs, social, product page)
  • Who's the audience? (prospective users, existing users, developers in general)
  • What's the key message or feature to communicate?
  • Any specific constraints? (character limits, format requirements)

Phase 2: Gather Context

  1. Load reference files (auto-loaded from skill folder):

- rubric.md — 8 scoring criteria for validation - taboo-phrases.md — patterns to eliminate - voice-examples.md — transformation patterns and fact preservation rules

  1. Search for relevant context (if needed):

- Existing copy on zed.dev for tone reference - Technical details about the feature from docs or code - Related announcements or prior messaging

Phase 3: Draft (Two-Pass System)

Pass 1: First Draft with Fact Markers

Write initial copy. Mark all factual claims with [FACT] tags:

  • Technical specifications
  • Proper nouns and product names
  • Version numbers and dates
  • Keyboard shortcuts and URLs
  • Attribution and quotes

Example:

Zed is [FACT: written in Rust] with [FACT: GPU-accelerated rendering at 120fps]. Built by [FACT: the team behind Atom and Tree-sitter].

Pass 2: Diagnosis

Score the draft against all 8 rubric criteria:

CriterionScoreIssues
Technical Grounding/5
Natural Syntax/5
Quiet Confidence/5
Developer Respect/5
Information Priority/5
Specificity/5
Voice Consistency/5
Earned Claims/5

Scan for taboo phrases. Flag each with line reference.

Pass 3: Reconstruction

For any criterion scoring <4 or any taboo phrase found:

  1. Identify the specific problem
  2. Rewrite the flagged section
  3. Verify [FACT] markers survived
  4. Re-score the rewritten section

Repeat until all criteria score 4+.

Phase 4: Humanizer Pass (Recommended)

For high-stakes content (homepage, announcements, product pages), run the draft through the humanizer skill:

/humanizer

Paste your draft and let humanizer:

  1. Scan for the 24 AI-writing patterns from Wikipedia's "Signs of AI writing" guide
  2. Audit for remaining tells ("What makes this obviously AI generated?")
  3. Revise to add natural voice and rhythm

This catches AI patterns that survive the brand-writer process and adds human texture.

Phase 5: Validation

Present final copy with scorecard:

## Final Copy

[The copy here]

## Scorecard

| Criterion           | Score |
|---------------------|-------|
| Technical Grounding |   5   |
| Natural Syntax      |   4   |
| Quiet Confidence    |   5   |
| Developer Respect   |   5   |
| Information Priority|   4   |
| Specificity         |   5   |
| Voice Consistency   |   4   |
| Earned Claims       |   5   |
| **TOTAL**           | 37/40 |

✅ All criteria 4+
✅ Zero taboo phrases
✅ All facts preserved

## Facts Verified
- [FACT: Rust] ✓
- [FACT: GPU-accelerated] ✓
- [FACT: 120fps] ✓

Output formats by context:

ContextFormat
HomepageH1 + H2 + supporting paragraph
Product pageSection headers with explanatory copy
Release notesWhat changed, how it works, why it matters
Docs introClear explanation of what this is and when to use it
SocialConcise, no hashtags, link to learn more

Review Mode

When invoked with --review:

  1. Load reference files (rubric, taboo phrases, voice examples)
  2. Score the provided copy against all 8 rubric criteria
  3. Scan for taboo phrases — list each with line number: Line 2: "revolutionary" (hype word) Line 5: "—" used 3 times (em dash overuse) Line 7: "We're excited" (empty enthusiasm)
  4. Present diagnosis: ## Review: [Copy Title] | Criterion | Score | Issues | |---------------------|-------|--------| | Technical Grounding | 3 | Vague claims about "performance" | | Natural Syntax | 2 | Triple em dash chain in P2 | |... | | | ### Taboo Phrases Found - Line 2: "revolutionary" - Line 5: "seamless experience" ### Verdict ❌ Does not pass (3 criteria below threshold)
  5. Offer rewrite if any criterion scores <4:

- Apply transformation patterns from voice-examples.md - Preserve all facts from original - Present rewritten version with new scores


Examples

Good

Zed is written in Rust with GPU acceleration for every frame. When you type or move the cursor, pixels respond instantly. That responsiveness keeps you in flow.

Bad

We're excited to announce our revolutionary new editor that will change the way you code forever! Say goodbye to slow, clunky IDEs — Zed is here to transform your workflow.

Fixed

Zed is a new kind of editor, built from scratch for speed. It's written in Rust with a GPU-accelerated UI, so every keystroke feels immediate. We designed it for developers who notice when their tools get in the way.

平台分布

Codex

33.99%
按下载量换算1,527

Claude

31.94%
按下载量换算1,435

Cursor

16.65%
按下载量换算748

Gemini CLI

10.08%
按下载量换算453

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills