sales-copy

审查 · 66
已收录

Write sales pages, email sequences, and direct-response copy that converts through clarity and specificity rather than manipulation. Use for launches, offers, and conversion-focused email. Enforces the EW anti-AI rules, proof standards, and the writer's voice profile.

Verified installs0
Stars28
版本1.0.0
质量62/100 · 有潜力
信任66/100 · 仅限沙盒
审计77/100 · 需审查

供给资产档案

研究与知识工作

Deep research, source comparison, literature review, RAG, knowledge search, and reports.

浏览赛道

场景

研究 Agent

I need my agent to research a topic, compare sources, and produce a concise report.

适配 Agent

Claude Code + CLI + Codex

适用于 Codex、Claude Code、Cursor、CLI 或自定义 Agent。

安装

就绪

npx skills add Deupaxx/EveryDay-Writer --skill sales-copy

维护状态

新鲜

距上次推送 3 天

风险

需审查

The SKILL.md references core dependency files (core/anti-ai-rules.md, core/ai_slop_commandments.md, core/voice-profile.md) that are not included in the skill directory itself. This is acceptable if the skill is used within the full repository, but it may hinder standalone reuse.

GitHub 质量

28

62/100 质量 · 74/100 信任

覆盖标签

研究研究 Agentagent-skill

审查说明

The SKILL.md references core dependency files (core/anti-ai-rules.md, core/ai_slop_commandments.md, core/voice-profile.md) that are not included in the skill directory itself. This is acceptable if the skill is used within the full repository, but it may hinder standalone reuse. · Low GitHub adoption signal

Agent 采用评分卡

一眼查看信任、审计与安装准备度

这些分数综合公开仓库元数据、OpenAgentSkill 审查信号、维护新鲜度与安装准备度。它用于候选筛选,不替代人工审查。

质量

有潜力
62

有用的候选项,但采用前应与替代方案比较。

信任

仅限沙盒
66

有用但信任信号不足或混杂的候选项。在结果闭环证明任务匹配前,请保持在隔离工作区内使用。

审计

需审查
77

对安装准备度、安全元数据、维护情况与采用风险的机器可读审查。

OpenAgentSkill 信任评分 v5

安装前需人工审查

仅在沙盒中运行,并在用于真实工作前比较接近的替代方案。

CodexClaude CodeCursorOpenAgentSkill CLI

Stars

28 个 GitHub Stars

仓库活跃度

28 个 Star,5 个 Fork

维护状态

距上次推送 3 天

许可证

MIT

安装

npx skills add Deupaxx/EveryDay-Writer --skill sales-copy

安装安全性

标准软件包或运行时安装路径

权限范围

公开元数据中未发现高风险权限范围

Agent 结果

暂未有 Agent 结果数据

文档

Usable metadata, review docs

风险摘要

生产前审查

  • The SKILL.md references core dependency files (core/anti-ai-rules.md, core/ai_slop_commandments.md, core/voice-profile.md) that are not included in the skill directory itself. This is acceptable if the skill is used within the full repository, but it may hinder standalone reuse.
  • Low GitHub adoption signal
  • Quality score needs review
  • GitHub adoption: 28 GitHub stars

安装准备度

安装路径可用

  • 安装路径可用
  • 仓库证据可用
  • 已声明许可证
  • 暂无 Agent 验证结果证据

Agent 可读元数据

这个 Skill 的机器可读决策数据。

使用此区块或内嵌 JSON 判断 Agent 是否应安装该 Skill、选择替代方案,或先请求人工审查。

打开 JSON

适用任务

  • Content automation 工作流
  • Claude Code 团队
  • builders willing to evaluate younger projects
  • Summarize source material

适用 Agent

CodexClaude CodeCursorOpenAgentSkill CLICLI

安装决策

命令
npx skills add Deupaxx/EveryDay-Writer --skill sales-copy
策略
审查
人工审查

信任与风险

信任
66/100
审计
77/100
风险级别
需审查

结果闭环

端点
/api/agent/outcome
事件 ID
resolve
结果
5

安装命令

npx skills add Deupaxx/EveryDay-Writer --skill sales-copy

不适用场景

  • 需要厂商支持 SLA 的团队
  • production agents without a repository review
  • Low GitHub adoption signal
  • The SKILL.md references core dependency files (core/anti-ai-rules.md, core/ai_slop_commandments.md, core/voice-profile.md) that are not included in the skill directory itself. This is acceptable if the skill is used within the full repository, but it may hinder standalone reuse.
  • Quality score needs review

Agent 安全 v2

57/100 · 安装前审查

实验性审查

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

Test manually in an isolated workspace and compare against safer alternatives.

通过 API 解析

Browser automation

Skill may drive a browser or interact with web pages.

网络访问

Skill 可能访问远程页面、API、仓库或外部服务。

文件系统访问

Skill 可能读取或写入项目文件、文档、生成产物或本地工作区状态。

  • The SKILL.md references core dependency files (core/anti-ai-rules.md, core/ai_slop_commandments.md, core/voice-profile.md) that are not included in the skill directory itself. This is acceptable if the skill is used within the full repository, but it may hinder standalone reuse.

安装目标

在你的 Agent 工作流中安装此 Skill

通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。

skill install

OpenAgentSkill CLI

Resolve policy, run the source installer safely, and report a verified install receipt.

$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install deupaxx-sales-copy

Agent 解析计划

让 Agent 在安装前验证匹配度。

Resolve API 返回首选 Skill、替代方案、安全策略、审计说明、安装目标和可直接执行的提示词,无需抓取此页面。

打开文本计划

Agent 应检查

  • 从 Resolve API 检查任务匹配与替代方案。
  • 检查审计评分、信任评分和安全策略警告。
  • 检查 Codex、Claude Code、Cursor 或 CLI 的安装目标兼容性。

复制提示词

Task: Use sales-copy in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20sales-copy%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/deupaxx-sales-copy/install
Install command: npx skills add Deupaxx/EveryDay-Writer --skill sales-copy
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.

Agent 交接

把安装路径交给 Agent,而不是再给一个目录页。

通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。

打开安装 API

Agent 提示词

Use sales-copy for this task. Review https://www.openagentskill.com/api/skills/deupaxx-sales-copy/install, then install with: npx skills add Deupaxx/EveryDay-Writer --skill sales-copy

Registry 元数据

用于自动选择 Skill 的 Agent 可读档案。

本页通过 Registry API 提供相同的决策、信任、审计、场景和安装信号,让 Agent 无需抓取界面即可排序。

打开 Manifest

适配 Agent

62/100

Content automation

平台

Claude Code

审计报告

需审查 · 77/100

对安装准备度、安全元数据、维护情况与采用风险的机器可读审查。

查看审计报告查看评估报告

Agent 决策面板

Fallback candidate for Content automation

先用此 Skill 做原型验证,并保留备选方案。

62
就绪度
原型验证
阶段

栈中角色

备选候选

主要匹配

Content automation

信任标签

先做原型验证

安装路径

命令已就绪

适用场景

  • Content automation 工作流
  • Claude Code 团队
  • builders willing to evaluate younger projects

证据

  • 仓库近期活跃
  • 已提供安装命令或 GitHub 仓库
  • 62/100 质量档案
  • 3 个 OpenAgentSkill 交互事件

先审查

  • Low GitHub adoption signal
  • The SKILL.md references core dependency files (core/anti-ai-rules.md, core/ai_slop_commandments.md, core/voice-profile.md) that are not included in the skill directory itself. This is acceptable if the skill is used within the full repository, but it may hinder standalone reuse.

实施路径

  1. 1在沙盒 Agent 中安装它,并端到端完成一次Content automation任务。
  2. 2Compare output quality, latency, and failure behavior against at least one alternative.
  3. 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.

信任档案

仅限沙盒

有用但信任信号不足或混杂的候选项。在结果闭环证明任务匹配前,请保持在隔离工作区内使用。

66
OpenAgentSkill 信任评分

GitHub 采用度

检查

28 个 GitHub Stars

Star/Fork 活跃度

检查

28 个 Star,5 个 Fork; 当前元数据中没有议题活跃度信息

近期维护

通过

距上次推送 3 天

许可证清晰度

通过

MIT

积极信号

  • AI 审查已通过
  • 安装路径可用
  • 仓库证据可用
  • 近期维护的仓库
  • 安装命令未发现明显高风险模式
  • 结果闭环已就绪,但需要首次真实 Agent 运行

安装前审查

  • The SKILL.md references core dependency files (core/anti-ai-rules.md, core/ai_slop_commandments.md, core/voice-profile.md) that are not included in the skill directory itself. This is acceptable if the skill is used within the full repository, but it may hinder standalone reuse.
  • Low GitHub adoption signal
  • Quality score needs review
  • GitHub adoption: 28 GitHub stars
  • Stars/forks activity: 28 stars, 5 forks; issue activity unavailable in current metadata
  • 暂未有真实 Agent 结果报告
  • 无人值守安装前需要人工审查

建议操作

仅在沙盒中运行,并在用于真实工作前比较接近的替代方案。

质量档案

有潜力 适用于 Agent 工作流的候选

有用的候选项,但采用前应与替代方案比较。

62
GitHub Stars
28
新鲜度
3 天前
安装就绪
许可证
MIT
安装前审查: Low GitHub adoption signal · The SKILL.md references core dependency files (core/anti-ai-rules.md, core/ai_slop_commandments.md, core/voice-profile.md) that are not included in the skill directory itself. This is acceptable if the skill is used within the full repository, but it may hinder standalone reuse.

工作流匹配

在这些场景使用此 Skill

工作流匹配

加入完整工作流

替代方案短名单

安装前对比

可能适合该任务的相近 Skill。

对比全部

概览

--- name: sales-copy description: | Write sales pages, email sequences, and direct-response copy that converts through clarity and specificity rather than manipulation. Use for launches, offers, and conversion-focused email. Enforces the EW anti-AI rules, proof standards, and the writer's voice profile. license: MIT metadata: version: "0.3.0" ---

# EW Skill — Sales Copy

**Dependency chain. Read these in order before writing anything:**

1. `core/anti-ai-rules.md` (read fully; Section 0 sets the standard, 0.1 sets precedence, 0.2 forbids fabrication, 9 and 10 stop over-correction) 2. `core/ai_slop_commandments.md` (mechanism reference and diagnostic checklist) 3. `core/voice-profile.md` (this writer's voice fingerprint; if `Completed: No`, stop and run onboarding) 4. Any `.md` files the user has dropped in `references/`

This chain applies on direct invocation (`/ew:sales-copy`) exactly as it does on dispatch through `/ew`. Direct invocation skips routing, not constraints.

---

## WHAT THIS SKILL IS FOR

Sales pages, email sequences, and direct response copy. Writing that exists to produce a measurable outcome: a purchase, a booking, a subscription, an enrollment.

Sales copy is the most honest form of writing because it can't hide its intent. It either converts or it doesn't. The number tells you. The discipline here is writing that moves people toward something they genuinely need — not manipulating them into something they don't.

Manipulation is not this skill's tool. Clarity, specificity, and legitimate persuasion are.

---

## THE STRUCTURAL SPINE: THE CUSTOMER AS PROTAGONIST

The Triad of Craft and the writing commandments converge on one insight for sales copy: the customer is the protagonist, not the product. The product is the key knowledge found at the midpoint of their journey. The copy must tell their story, not yours.

**The sales copy as hero's journey:**

**Ordinary World:** The customer's life before. The problem that exists. The pain that is real. State it more specifically than they've heard it before — this is what creates the "they understand me" moment that earns trust.

**Inciting Incident:** The moment their ordinary world is no longer acceptable. What made them start looking? What made the pain acute enough to act? Naming this is the difference between copy that resonates and copy that gets scrolled past.

**The Woods:** What they've already tried. What failed. Why the usual solutions don't work for this specific problem. This section is often skipped — it shouldn't be. Acknowledging failed attempts proves you understand the problem deeply.

**Key Knowledge:** The mechanism. Why this product/service works where others didn't. Not a feature list — the one insight about the problem that makes the solution make sense.

**New Equilibrium:** Life after. Specific. Grounded. Not "transform your business" — "you stop writing from scratch every time and start from a brief that already has the argument."

---

## THE OPENING

The sole purpose of the first sentence is to get the reader to read the second sentence.

The opening must do one of three things: name the reader's problem so specifically they feel seen, challenge a belief they hold, or present a specific outcome they want. No preamble. No warm-up. The reader made the decision to stay or go in the first three seconds.

**What works:**

**The problem, stated precisely:** "You've bought three copywriting courses. Your conversion rate is the same as when you started."

**The specific outcome:** "A sales page that converts at 8% when your current one converts at 1.2%."

**The challenge:** "Most sales pages fail before the reader reaches the first CTA — and it's not the CTA that's broken."

**What doesn't work:** - "Are you tired of...?" — exhausted opener, signals template - "Imagine a world where..." — futurism invitation, signals AI - "I used to struggle with this too..." — false vulnerability, signals performance - Long story openers that bury the point past the 300-word mark

---

## SPECIFICITY IS THE PROOF

In sales copy, specificity is the mechanism of trust. Every vague claim is a credibility debit. Every specific claim is a credibility credit.

**The specificity upgrade:**

❌ "This program has helped hundreds of businesses grow." ✅ "47 solo consultants used this to book their first $5,000 client within 90 days."

❌ "Our clients see amazing results." ✅ "Amara increased her newsletter conversion rate from 1.8% to 6.3% in 60 days using only the cold traffic sequence in Module 3."

The number, the name, the timeframe, the specific mechanism — these are what make claims land. Without them, you're asking the reader to trust you on faith. Most won't.

**Name the mechanism:** Don't just say the product works — explain briefly *why* it works. The mechanism is what separates a claim from an argument. ❌ "This headline formula gets clicks." ✅ "This headline formula works because it triggers pattern interruption — the reader's brain stops scanning when it encounters something that doesn't fit the template it was expecting."

---

## OBJECTION ARCHITECTURE

Every unconverted reader is a reader with an unaddressed objection. Your copy must find and answer the three to five objections that kill the most conversions — before the reader has to ask.

**The main objections in most sales situations:** 1. "Is this for someone like me?" — Too broad, won't work in my situation 2. "Will this actually work?" — Skepticism about the mechanism or promise 3. "Can I trust you?" — Credibility gap, insufficient proof 4. "Is it worth the cost?" — ROI isn't clear 5. "Is now the right time?" — Urgency isn't real

**Address each with specifics, not reassurance.** Reassurance ("We're confident you'll love it!") doesn't address objections — it papers over them. The reader can feel the difference.

Objection: "I've tried things like this before and they didn't work." Reassurance: "We think you'll be pleasantly surprised!" Address: "Most [category] courses teach the framework without the implementation step. This one starts at implementation. Here's what that looks like on day one:"

---

## PROOF ARCHITECTURE

Proof is not a section at the bottom of the page. It is distributed throughout the copy, placed nearest to the claim it supports.

**Types of proof, in descending order of power:** 1. **Specific named results with numbers and timeframes** — the most trusted form 2. **Named testimonials with specific outcomes** — not "John changed my business," but "John's launch converted at 4.2% where his previous launch was at 0.9%" 3. **Your own demonstrated expertise** — specific, named, verifiable 4. **Mechanism explanation** — showing you understand *why* it works 5. **Social proof (numbers, logos, media)** — useful but weakest without specifics

**Never use:** - Anonymous testimonials - Testimonials with only first name and last initial - Testimonials that only praise the person, not the result - Claims you can't substantiate

---

## EMAIL SEQUENCES

An email sequence is a conversation across time. Each email must earn the right to send the next one.

**The first email's job:** Establish why the reader is here and what they'll get. Not a full pitch — a clear reason to open the next one.

**Middle emails:** Deepen the argument. Each email handles one aspect of the case for action. One idea per email. Every email ends with a forward pointer that makes the next one feel necessary.

**The sales email:** After the relationship and the argument are built. The offer, stated clearly and honestly. The mechanism, the proof, the CTA. One CTA. No hedge. No apology for selling.

**Subject lines:** Write for the opened inbox of someone who doesn't know what's inside. The subject line earns the open; the first line earns the read.

---

## WHAT THIS SKILL DOES NOT DO

This skill does not generate false urgency ("only 3 spots left" when there are unlimited spots), manufacture scarcity, or write copy that misrepresents what the product does. These techniques work once and destroy trust permanently.

If the offer is good, honesty converts. If the offer requires manipulation to convert, the offer is the problem — not the copy.

---

## POST-GENERATION REVIEW

After producing any draft, stop. Re-read `core/anti-ai-rules.md` Sections 1–7 with the draft in front of you. Go line by line through the pre-publish checklist in Section 7. Fix every failure before presenting the output.

Sales copy that reads as AI-generated destroys the trust it needs to convert. The review pass is not quality control — it is the product.

## PRE-LAUNCH CHECKLIST

- [ ] Does the opening name the reader's specific problem or desired outcome in the first 3 sentences? - [ ] Is the customer the protagonist — or is the product? - [ ] Is every claim backed by a specific number, name, or mechanism? - [ ] Are testimonials named and outcome-specific? - [ ] Are the top 5 objections addressed with specifics, not reassurance? - [ ] Is the mechanism explained — not just claimed? - [ ] Is there one clear CTA per section? - [ ] Have you run Sections 1–7 of `core/anti-ai-rules.md`? - [ ] Is all urgency or scarcity real — not manufactured? - [ ] Does the copy end having proved something, or just asserted it?

技术详情

版本
1.0.0
许可证
MIT
最近更新
2026年8月20日
发布时间
2026年8月20日

决策摘要

备选候选

62
就绪
原型验证
阶段

仓库近期活跃

审计

安装审查

安装与采用审查

77
需审查
安全性
81/100
维护状态
100/100
安装
92/100
打开完整审计查看评估报告

Agent 验证证据

Agent 验证证据

来自解析、审查、安装和一次小范围运行后的结果报告。

0
已验证
Needs first agent run自动安装: 先审查最近: 未知
成功率
近期失败
结果
0
输出质量
失败
0
不相关
0
安装次数
0
风险拦截
0
需要配置
0
生产环境
0

暂时没有 Agent 结果数据。首次 Agent 执行可以通过 /api/agent/outcome 报告成功、需要设置、风险拦截、失败或不相关。

安装

加入 Agent 工作流

免费且开源. 在生产 Agent 中安装前请先审查报告。

增长闭环

分享工具包

X

为 sales-copy 准备的场景化草稿,可手动发布到 X。

策展说明
sales-copy: Write sales pages, email sequences, and direct-response copy that converts through clarity an...

28 stars

https://www.openagentskill.com/skills/deupaxx-sales-copy?ref=x
打开 X 草稿
可选:带安装命令的回复
Listing + install path for sales-copy:
https://www.openagentskill.com/skills/deupaxx-sales-copy?ref=x

Install: npx skills add Deupaxx/EveryDay-Writer --skill sales-copy
打开回复草稿

收录来源

Registry 收录

可认领

此列表来自公开来源,维护者认领获批前不会标记为官方。

创作者
Deupaxx
收录方
OpenAgentSkill 社区索引

归属链接指向公开仓库或创作者主页。创作者可认领列表以更新所有权信号。

认领此 Skill

所有者认领

认领此 Skill 页面

这条 Registry 收录 列表归属于 Deupaxx,但尚未标记为官方。认领后可增加已验证所有者信号,使后续发布、安装和审计更新更值得信赖。

创作者外链工具包

将证据徽章加入你的 README

在开发者评估仓库的位置展示规范页面、当前信任与审计信号,以及真实的 Agent 验证证据。

[![Listed on OpenAgentSkill](https://www.openagentskill.com/api/badge/deupaxx-sales-copy?metric=listed&label=Listed)](https://www.openagentskill.com/skills/deupaxx-sales-copy)
[![OpenAgentSkill Trust](https://www.openagentskill.com/api/badge/deupaxx-sales-copy?metric=trust&label=Trust)](https://www.openagentskill.com/skills/deupaxx-sales-copy)
[![OpenAgentSkill Audit](https://www.openagentskill.com/api/badge/deupaxx-sales-copy?metric=audit&label=Audit)](https://www.openagentskill.com/skills/deupaxx-sales-copy/audit)
[![Agent Proven](https://www.openagentskill.com/api/badge/deupaxx-sales-copy?metric=proven&label=Agent%20Proven)](https://www.openagentskill.com/skills/deupaxx-sales-copy)

作者

D

Deupaxx

@deupaxx

平台适配

健康信号

GitHub Stars
28
质量评分
34/100
最近 GitHub 推送
2026年8月20日
框架提示
未知
OpenAgentSkill 浏览量
3
复制安装命令
0
跳转点击
0

社区信号

告诉我们这个 Skill 是否对你的 Agent 工作流有帮助。汇总反馈会持续改善排序。

信任与安全

仅限沙盒

66
  • GitHub 采用度28 个 GitHub Stars检查
  • Star/Fork 活跃度28 个 Star,5 个 Fork; 当前元数据中没有议题活跃度信息检查
  • 近期维护距上次推送 3 天通过
  • 许可证清晰度MIT通过
  • README/SKILL.md 完整度公开元数据需要更完整的 README/SKILL.md 上下文信息
  • 依赖与运行时风险公开元数据中未发现主要依赖风险提示通过