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 social-copygit 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/social-copy)<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.
<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>- 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 | $0.00199 | $0.01689 |
| Opus 5 | $0.00100 | $0.00844 |
| Sonnet 5 | $0.00040 | $0.00338 |
| Haiku 4.5 | $0.00020 | $0.00169 |
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.
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:
- 标题
- 封面/首句大字(如果适用)
- 正文
- 话题标签(小红书/微博)
- 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。
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 · 97 lines · 199 tokens per session scan A 1f1ff2d21617
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.
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.