Token导航 LogoToken导航TokenDH.com
效率需要联网clawhub未标认证来源可访问clear审计通过

social-growth-agent社会成长剂

Agent Skill

social-growth-agent 用于整理文档、README、Markdown 和说明材料,适合在 OpenClaw 中需要把零散信息整理成结构清晰的文档时使用。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。

总安装

4,027

周安装

173

GitHub Stars

公开资料未说明

下载量

1,412
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

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:social-growth-agent(社会成长剂)
来源仓库:https://github.com/utromaya-code/social-growth-agent
安装命令:
openclaw skills install social-growth-agent
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 OpenClaw 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。

ClawHubOpenClaw
openclaw skills install social-growth-agent

简介

根据反垃圾邮件规则规划社交媒体内容日历与话题排期。

  • 适合需要系统化内容运营的品牌与个人IP增长场景。
  • 输入目标后生成90天增长计划与每日发布建议。
  • 需定期人工复核内容合规性,避免触发平台限流机制。
  • social-growth-agent 属于效率类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

name
social-growth-ops
description
Plans, drafts, and schedules social media content (posts, reels, threads) with strict anti-spam and safety rules. Use when the user asks for a content calendar, captions, posting schedules, cross-post drafts, or automation via n8n/integrations. Never auto-post without explicit user confirmation.

Social Growth Ops

Purpose

Turn the agent into a reliable “content operator”:

  • Content calendar planning
  • Post drafting in your brand voice
  • Safety checks (anti-spam, duplication, platform constraints)
  • Scheduling handoff to n8n/workflow runners

When to Use

Use this skill when the user requests any of:

  • A social content plan/calendar
  • Captions for TikTok/Instagram/YouTube Shorts/X posts
  • Hashtags, titles, hooks, CTAs
  • “Repurpose this into 10 posts” / cross-post pack
  • A posting schedule and batching strategy
  • Automation instructions for n8n workflows

Non-Goals / Safety Limits

  • No auto-follow / no auto-DM / no account actions without explicit confirmation.
  • No posting without the user confirming the exact post text(s) and target(s).
  • No aggressive scraping or bypassing platform protections.
  • No financial/crypto actions inside social autopilot.

Brand Voice Inputs

Before drafting, ask (or infer from history) these inputs:

  • Audience: (who is it for)
  • Offer: (what you sell / promote)
  • Tone: (e.g., friendly, expert, edgy, minimalist)
  • Language: (RU/EN/mixed)
  • Prohibited content: (topics, claims, style)
  • Posting frequency: (per day / per week)
  • Target platforms: (Telegram channel, X, Instagram, TikTok, YouTube Shorts, etc.)

If inputs are missing, produce a short questions list and stop.

Workflow

1) Build a Content Calendar

Generate a table with:

  • Date/time slot (relative if exact timezone unknown)
  • Platform
  • Content type (post/reel/thread/short)
  • Hook style (1 sentence)
  • Goal (engagement, lead capture, authority)
  • Asset needed (image/video/script/link) or “text only”

Output: calendar.md-style structure.

2) Produce a Draft Pack

For each slot, draft:

  • Primary text (caption/poem/script)
  • 3 hook variants (for A/B testing)
  • Hashtags (platform-appropriate limit)
  • CTA (soft / hard CTA options)
  • Repurpose notes: how to reuse for other platforms

Output as numbered drafts with stable IDs.

3) Safety + Anti-Spam Checks

Before scheduling:

  • Detect duplicates across drafts and propose rewrites
  • Ensure no repeated identical CTA
  • Ensure claims are not unverified (recommend soft phrasing)
  • Ensure platform length constraints are respected
  • Ensure no banned keywords list is violated (if provided)

Output: “pass/fail” with exact reasons if fail.

4) Scheduling / Automation Handoff

If the user approves:

  • Provide an n8n workflow trigger spec (inputs only)
  • Provide a “payload JSON” format to hand to n8n
  • Include idempotency keys to avoid double-posting

If the user does not approve, stop and request confirmation.

Confirmation Contract (Required)

Never proceed to schedule or “post” unless the user explicitly says:

CONFIRM SOCIAL POST

And also provides:

  • Target platform(s)
  • Exact post text(s) (or the IDs of drafts to post)
  • When to publish (or “publish now”)

Output Format

Always respond with the following sections:

  1. ## Proposed Plan
  2. ## Draft Pack
  3. ## Safety Check
  4. ## Approval Required
  5. ## n8n Handoff Spec (if approved)

Example “User Approval”

User: “CONFIRM SOCIAL POST. Publish drafts 1, 2, 3 to X tomorrow 10:00 and Telegram at 12:00.”

Assistant: creates scheduling payloads and idempotency keys.

Guardrails

  • Do not reveal secrets (API tokens, cookies, passwords).
  • Do not attempt to bypass rate limits.
  • Prefer “compose now, schedule later” with explicit approval.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

95.95%
按下载量换算1,355

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills