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.
npx skills add open-octo/octo-agent --skill copy-editinggit clone --depth 1 https://github.com/open-octo/octo-agentWrote 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.
[](https://agentmods.dev/skills/open-octo/octo-agent/copy-editing)<a href="https://agentmods.dev/skills/open-octo/octo-agent/copy-editing"><img src="https://agentmods.dev/badge/skills/open-octo/octo-agent/copy-editing/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.
<a href="https://agentmods.dev/skills/open-octo/octo-agent/copy-editing"><img src="https://agentmods.dev/badge/skills/open-octo/octo-agent/copy-editing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00186 | $0.01691 |
| Opus 5 | $0.00093 | $0.00846 |
| Sonnet 5 | $0.00037 | $0.00338 |
| Haiku 4.5 | $0.00019 | $0.00169 |
Grade A, and why
copy-editing 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.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
文案打磨（Copy Editing）
通过多轮聚焦的"扫一遍"逐层改进文案，不指望一次读改完。核心：改是增强，不是重写——保留作者的声音，只把清晰度、说服力、具体程度提上去。
动手前先确认
最多问 2-3 个：
- 目标动作：这条要读者做什么？（决定"零风险"和 CTA 该优先扫哪）
- 受众：谁看、什么认知？（校准"所以呢""具体""情绪"三遍）
- 风格基准：有没有品牌调性/风格要求？（决定"语气"这一遍怎么判）
用户甩来一句"随便改改"，就先按通用标准 + 把假设列开头。
七遍打磨法（Seven Sweeps）
按顺序走七遍，每遍只管一个维度。每改完一遍，回头确认前面几遍没被改坏。
第一遍：清晰度
- 每句话能不能一次读懂？长句拆开。
- 代词指代是否清楚（"它"到底指谁）？
- 黑话、内部词有没有解释？一句话塞了三个观点就拆。
| 问题 | 改法 |
|---|---|
| 一句超过 30 字 | 拆成两句 |
| 抽象表述 | 换成具体例子 |
| 重点埋在中间 | 挪到段首 |
| 未定义缩写 | 首次出现写全称 |
第二遍：语气与声音
- 现在这个声音统一吗？会不会一段俏皮、一段官方？
- "我们"和"我司"混用？→ 统一。
- 收缩率、句式是否来回横跳？
- 有没有忽然冒出来一句不合调的梗？
第三遍：So What（所以呢）
- 每个卖点是不是都回答"我凭什么要在意"？
- 光讲功能没有后果的，补一句"哪意味着……"。
| 只讲功能 | 功能+利益点 |
|---|---|
| "我们用了 AI 分析" | "我们的 AI 能把你会漏掉的洞挖出来，让你决策快一半" |
| "实时看板" | "现在就能看到正在发生什么，不用等上周的报表" |
第四遍：证明给我
- 每个说法是不是有依据？
- 实名客户反馈 > 具体数字 > 案例引用 > 第三方认证 > 模糊说法（"客户都说好"）。
| 证明强度 | 例子 |
|---|---|
| 强 | "Stripe 营销 VP 陈莎：'把我们的搭建时间砍了 60%'" |
| 强 | "2847 个团队每天在用" |
| 弱（标记出来） | "行业领先""深受喜爱"——没有来源就标出来，别瞎补证据 |
凡是要用户才能提供的证据（真实客户名、真实数字），明确标注"需你补充"，你能改措辞但不能编证据。
第五遍：具体
模糊词换成可验证的具体数字。
| 模糊 | 具体 |
|---|---|
| 省时间 | 每周省 4 小时 |
| 很多客户 | 2847 个团队 |
| 很快 | 14 天见效 |
| 流程更顺 | 周报从 4 小时压到 15 分钟 |
| 服务好 | 平均响应 2 小时 |
| 好用 | 10 分钟上手，不用写代码 |
| 便宜 | 每月 29 元起 |
铁律：没法说具体的，多半是废话，砍掉或换成可验证的东西。
第六遍：情绪
文案让读者有感觉了吗？
- 痛点场景画得生动
- 前后对比让人有获得感
- 见证区释放"同侪压力"（别人都在用）
- 微故事（1-2 句具体画面）
第七遍：零风险
靠近 CTA 的所有摩擦力都拆掉了吗？
- 点了之后会发生什么很清楚
- 异议在 CTA 的"两屏内"就被处理
- 信任信号可见（退款、认证、人数）
- 下一步写具体（"开始 14 天免费试用"不是"立即开始"）
- 风险逆转写明白（无理由退款、免绑卡、随时取消）
这遍优先于一切——先把 CTA 周围改好，再去抠前面的段落。
快速精简版（不想走七遍）
- 删废话：非常、真的、其实、就是、基本上、可以说
- 弱动词换强：利用→用、有利于→帮、实现→做成
- 被动改主动："报表由系统生成" → "系统自动生成报表"
- 一句一个观点
- 检查 CTA 有没有行动力
常见问题与改法
| 症状 | 改法 |
|---|---|
| 一堆功能列在哪，没讲为什么 | 每个后面补"哪意味着……" |
| 企业腔 | 问一句"一个正常人会怎么说？" |
| 开头弱 | 用读者的痛点/想要的结局开头，别讲公司历史 |
| CTA 藏太深 | 提前、放显眼、多次出现 |
| 没证明 | 加具体数据、实名反馈、案例引用 |
| 空泛 | 说清是谁、怎么做、多少 |
| 恨不得啥都讲 | 只留最关键的 3-5 个利益点 |
| "最高提升 50%"这类虚词 | 给中位数/典型值，带上下文 |
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.
- 8d ago First seen · 134 lines · 186 tokens per session scan A beec80852503
copy-editing is a skill published in the GitHub repository open-octo/octo-agent (97 stars, last pushed yesterday), licensed MIT. It adds 186 tokens to every session and 1,691 once invoked, about $0.0009 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.
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…
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…
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 /…
ha-logs
A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.
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…
feishu
A toolkit for working with Feishu, also called Lark, a workplace collaboration platform. It covers documents, spreadsheets, files, wikis, approvals, calendars, and contacts.