social-copy

social-copy is a skill for Claude Code, Codex from open-octo/octo-agent. It costs 199 tokens per session (1,689 once invoked), scanned A, original, MIT.

A social-media writing aid that adapts copy to a specific platform's format and audience. It covers platforms such as Xiaohongshu, WeChat public accounts, short-video scripts, Weibo, and private social posts.

In plain words
What is it for?
Use it to write posts, headlines, short-video scripts, product-discovery notes, and calls to action while avoiding unsupported claims and common advertising restrictions.
Why use it?
It avoids treating every platform as the same by matching the opening, length, tone, keywords, tags, and requested reader action to the platform.

Skill for Claude CodeCodex

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

Good fit Use it to write posts, headlines, short-video scripts, product-discovery notes, and calls to action while avoiding unsupported claims and common advertising restrictions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/open-octo/octo-agent/social-copy
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 social-copy
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 social-copy

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/open-octo/octo-agent/social-copy"><img src="https://agentmods.dev/badge/skills/open-octo/octo-agent/social-copy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 199 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,689 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 $0.00199 $0.01689
Opus 5 $0.00100 $0.00844
Sonnet 5 $0.00040 $0.00338
Haiku 4.5 $0.00020 $0.00169

Measured 8d ago against content hash 1f1ff2d21617, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

social-copy 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/social-copy/SKILL.md · 97 lines

What it actually says

社媒平台文案(Social Copy)

同一句话换了平台,说法完全不同。这个 skill 让你写出的内容先适配平台,再谈文笔。开头先说清:哪个平台、给谁看、想要什么动作(点赞/评论/收藏/关注/下单)。不确定平台就先问,别用一套通用模板糊弄。


通用红线(所有平台都别碰)

  • 广告法违禁词:最好、第一、国家级、顶级、绝无仅有、全网最低、史上最强、治愈、防癌、祛除(万一涉及功效/医疗,只能用"辅助/改善"且不承诺)。
  • 不编数据:销量、客户数、效果——没有真实来源就写"实测""据我了解",或不写具体数字。
  • 不截图编口碑、不盗用别人内容。
  • 各平台防限流用语:小红书/抖音对"硬广、引流到微信、极端营销"敏感,别在正文里甩"加 v x"。引流话术放评论区或主页,且要隐蔽。

各平台方言

小红书(种草笔记)

小红书是"搜索 + 种草"双引擎,既写给人看,也写给小红的搜索算法看。

标题(≤20 字,带 1-2 个 emoji):

  • 制造具体场景:"用了 3 个月,痘印真的淡了"
  • 给结果 + 反差:"200 块拼出了 2000 块的质感"
  • 戳痛点 + 承诺:"油皮夏天不脱妆的秘诀"
  • 用数字:"3 招让出租屋变有格调"
  • 标题别做标题党——被点进去发现货不对板,限流 + 掉粉。

正文

  • 口语化、分段、多留白,别一大坨。
  • 开头 1-2 句说清"这篇给谁看、能解决啥"(搜索友好)。
  • 中间给干货/感受,穿插真实场景细节(越具体越可信)。
  • 结尾引导互动:"你们有没有一样的烦恼?" / "觉得有用就收藏"。
  • 关键词埋点:把用户会搜的词(品牌名、品类、痛点、场景)自然塞进标题、正文首段、话题标签里,帮系统识别。

话题标签:5-8 个,大小词都带(# 品类大词 + # 具体场景 + # 品牌词)。

封面:正文另给一句"封面大字",通常是标题的浓缩或最抓眼球的一句。

示例:种草一款咖啡 标题:被这杯咖啡治愈的早晨 ☕️ 打工人续命水 首段:作为一个每天早八的人,我真的离不开这杯。之前喝公司楼下那家又贵又酸…… 话题:#咖啡 #打工人 #早八 #平价好物

公众号(长文)

靠标题定打开率,但别做标题党——打开率是第一步,转发率才决定一篇能不能起来。

标题:具体 + 有悬念 + 说人话。忌"震惊!""一定要看"这类。 开头:前 3 句定生死,用一个具体场景/反差/问题抓住人,别铺垫。 正文:动宾结构短句,多写"人话金句",每段一个观点,留白。 结尾:给行动指令(点「在看」/ 转发给需要的人 / 留言)。 排版:小标题、加粗、留白,手机上看着舒服。

短视频口播/脚本(抖音、视频号、小红书视频)

前 3 秒钩子:不废话,直接抛结果/冲突/反常识。可以先把结论说了再慢慢解释("我这辈子最后悔的就是……")。 中间:节奏感,一句一个信息点,别太长句;画面切点。 结尾:明确行动指令("关注我,下期讲……" / "评论区扣 1")。 口播要能一气说完:写完念一遍,卡壳的长句就拆短。

微博

158 字内要劲道。带 #话题#、@ 相关方,蹭热点要快(热点有时效,宁早勿晚)。

  • 观点鲜明、有金句、可转发。
  • 贴热点要"贴得自然",硬蹭会显油腻。

朋友圈(私域)

跟公域不同,朋友圈是给"已经认识你的人"看的。

  • 克制:别刷屏、别像广告,真实、有烟火气。
  • 分享"我"的体验/观点,而不是"卖货"。
  • 一条有价值的日常,胜过十条硬广。

产出格式

一次给 2-3 个版本(呼应"多版本供选择"),每版标注角度(比如"情绪共鸣版" vs "干货实用版" vs "反差猎奇版"),方便用户挑。

版本结构:

  1. 标题
  2. 封面/首句大字(如果适用)
  3. 正文
  4. 话题标签(小红书/微博)
  5. 这一版主打的角度+ 适合的人群

给平台加分的细节

  • 小红书:emoji 别乱塞,一版里 2-4 个就够,塞满反而像营销号。
  • 违禁词自查:写完把"最好、第一、绝对、顶级、最顶"这类极限词过一遍,换成"我自己觉得、实测下来"。
  • 目标人群:同一篇内容写给"学生党"和"宝妈"完全两个说法,开工前先锁定一个。

这个 skill 是结合常见社媒平台运营经验的原创整合,非直接搬运单一开源 skill。

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 · 97 lines · 199 tokens per session scan A 1f1ff2d21617

Subscribe to this mod's changes

social-copy is a skill published in the GitHub repository open-octo/octo-agent (99 stars, last pushed yesterday), licensed MIT. It adds 199 tokens to every session and 1,689 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