Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计通过

post-writer帖子作者

Agent Skill

post-writer 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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

194

周安装

8

GitHub Stars

520

下载量

63
CodexClaudeCursorGemini CLI

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

unknown

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:post-writer(帖子作者)
来源仓库:https://github.com/charlie947/social-media-skills
仓库路径:skills/post-writer
安装命令:
npx skills add https://github.com/charlie947/social-media-skills --skill post-writer
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 npx skills 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。

skills.shnpx skills
npx skills add https://github.com/charlie947/social-media-skills --skill post-writer

简介

用于查找、检索和筛选相关信息以支持内容创作。

  • 适合根据关键词或任务场景快速定位候选结果。
  • 可辅助获取写作模板、风格指南或行业术语参考。
  • 安装前建议确认权限范围和维护状态。post-writer 属于研究检索类 Skill,可作为该场景下的辅助能力补充。
  • 注意是否会触发联网、命令执行或文件读写操作。

SKILL.md

Post Writer

CRITICAL: Auto-start on load

The moment this skill triggers, go straight to Step 1. Do not summarise the skill. Do not explain what it does. Do not list the files it references. Jump to input gathering immediately.

Step 1. Gather inputs

Check the project for about-me.md and voice.md. Read both. If either is missing, tell the user to run the Voice Builder skill first ("say build my voice"), then stop.

If both files exist, call AskUserQuestion with this exact JSON:

[
  {
    "question": "What topic do you want to post about?",
    "header": "Topic",
    "multiSelect": false,
    "options": [
      {"label": "Paste a context dump", "description": "I have notes, transcripts, or raw ideas to turn into a post"},
      {"label": "I have a topic in mind", "description": "I will type the topic after this"},
      {"label": "Suggest topics for me", "description": "Based on my voice system, suggest 5 topics I should post about"}
    ]
  },
  {
    "question": "Do you have any reference posts you want me to use as structural inspiration?",
    "header": "References",
    "multiSelect": false,
    "options": [
      {"label": "No references", "description": "Write from scratch using my voice files only"},
      {"label": "I will paste examples", "description": "I have posts from other creators I want you to study first"},
      {"label": "Use my training posts", "description": "Reference the posts I used in the Voice Builder"}
    ]
  }
]

Based on the answers:

  • "Paste a context dump": wait for the user to paste, extract the core idea, then proceed to Step 2
  • "I have a topic in mind": wait for the user to type it, then proceed to Step 2
  • "Suggest topics for me": read about-me.md topic pillars and voice.md, suggest 5 specific topics with a one-line angle for each, then use AskUserQuestion to let them pick one
  • "I will paste examples": wait for reference posts, note the structural patterns, then proceed
  • "Use my training posts": reference whatever posts are already in the project

Step 2. Research and plan

Before writing, research the topic. Look for:

  • Data points or statistics that support the angle
  • Contrarian takes or surprising facts
  • Real examples or case studies
  • Common misconceptions to challenge

Then present a post plan. Call AskUserQuestion:

[
  {
    "question": "Which angle works best for this post?",
    "header": "Angle",
    "multiSelect": false,
    "options": [
      {"label": "[Angle 1 name]", "description": "[One sentence describing the angle and hook]"},
      {"label": "[Angle 2 name]", "description": "[One sentence describing the angle and hook]"},
      {"label": "[Angle 3 name]", "description": "[One sentence describing the angle and hook]"}
    ]
  },
  {
    "question": "Which framework do you want?",
    "header": "Framework",
    "multiSelect": false,
    "options": [
      {"label": "PAS", "description": "Problem, Agitate, Solution"},
      {"label": "How-to list", "description": "Numbered steps or tips"},
      {"label": "Story to lesson", "description": "Personal story with a takeaway"},
      {"label": "Contrarian take", "description": "Challenge a common belief"}
    ]
  }
]

Fill in the actual angle options based on the topic research. Do not use placeholder text for the angle descriptions.

Step 3. Write the draft

Write the post following these rules:

  • Read voice.md for tone, rhythm, hook style, CTA style, and the absence patterns section (what the voice never does)
  • Read about-me.md for audience and topic context
  • Match the sentence length and paragraph rhythm from voice.md
  • Avoid every banned word, structure, and pattern listed in voice.md's absence section
  • Use the hook pattern that fits the chosen angle
  • End with the CTA style from voice.md

Output the post inside a plain code block:

[The full post goes here with all line breaks and formatting exactly as it should appear on LinkedIn]

After the code block, add 2 to 3 sentences on why you chose this hook and structure, referencing specific patterns from voice.md.

Step 4. Iterate

Ask the user:

How does this feel? Tell me what to change, or say "ship it" and I will save the final version.

If the user gives feedback, revise and output a new code block. Maximum 3 revision rounds.

If the user says "ship it" or equivalent, save the final post as a markdown file in the project.

Then say:

Post saved. Say "design a graphic" to create a visual, or "score my post" to get feedback before publishing.

Rules

  • Always read about-me.md and voice.md before writing.
  • Always output posts in a plain code block.
  • Never use em dashes in any post.
  • British English unless voice.md says otherwise.
  • Do not add hashtags unless voice.md explicitly uses them.
  • Do not add engagement bait CTAs unless they appear in voice.md.
  • Keep posts between 150 and 300 words unless the user requests otherwise.
  • Plan before writing. Never skip Step 2.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

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

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

Codex

34.96%
按下载量换算22

Claude

28.34%
按下载量换算18

Cursor

19.23%
按下载量换算12

Gemini CLI

10.39%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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