Token导航 LogoToken导航

Agent Skill · 研究检索

x-writer(x 作家)

x-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。

x-writer 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 23,454。

总安装 4,268周安装 171GitHub Stars 141下载 1,382核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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:x-writer(x 作家)
来源仓库:https://github.com/ognjengt/founder-skills
仓库路径:skills/x-writer
安装命令:
npx skills add https://github.com/ognjengt/founder-skills --skill x-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/ognjengt/founder-skills --skill x-writer

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

x-writer 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。适用于关键词搜索、任务场景匹配或来源线索梳理等研究检索场景。通过关键词、任务描述或来源仓库提供上下文,由 Agent 执行信息聚合与过滤。

安装前需确认权限范围、维护状态,注意是否触发联网、命令执行或文件读写操作。建议结合原始 README 和仓库路径进一步核验具体用法和功能边界。

来源仓库内路径:skills/x-writer

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/ognjengt/founder-skills --skill x-writer;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

x-writer 怎么安装?

在终端执行 npx skills add https://github.com/ognjengt/founder-skills --skill x-writer。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

x-writer 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

x-writer 需要什么权限?

权限级别是需要联网。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。

x-writer 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

x-writer 用的人多吗?

公开数据是累计安装 4,268 次,近一周安装 171 次,下载 1,382 次,GitHub 141 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

x-writer 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
x-writer

x 作家 · 本页

4,268141需要联网未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

X Writer

Purpose

Generate 3 viral X posts in different proven formats, matched to a creator voice, using battle-tested templates and patterns that drive engagement.


Execution Logic

Check $ARGUMENTS first to determine execution mode:

If $ARGUMENTS is empty or not provided:

Respond with: "x-writer loaded, proceed with your topic or idea"

Then wait for the user to provide their requirements in the next message.

If $ARGUMENTS contains content:

Proceed immediately to Task Execution (skip the "loaded" message).


Task Execution

When user requirements are available (either from initial $ARGUMENTS or follow-up message):

1. MANDATORY: Read Reference Files FIRST

BLOCKING REQUIREMENT — DO NOT SKIP THIS STEP

Before doing ANYTHING else, you MUST use the Read tool to read ALL three reference files. This is non-negotiable:

Read: ./references/formats.md
Read: ./references/posts.md
Read: ./references/voices.md

What you will find:

  • formats.md: 8 proven post formats with structure templates, psychology, and format-specific rules
  • posts.md: 49+ proven viral posts organized by format type — the example library
  • voices.md: Creator voice profiles with writing DNA, signature patterns, and example posts

DO NOT PROCEED to Step 2 until you have read all three files and have their content in context.

2. Check for Business Context

Check if FOUNDER_CONTEXT.md exists in the project root.

  • If it exists: Read it and use the business context to personalize output (industry terminology, audience pain points, brand voice, company name, products).
  • If it doesn't exist: Proceed using defaults from "Defaults & Assumptions."

3. Analyze Input & Select Voice

From the user's requirements, extract:

  • Topic/idea — What they want to post about
  • Goal — What they want the post to achieve (engagement, authority, education, humor)
  • Voice preference — If they specified a voice or tone

Voice Matching Logic:

If the user specified a voice → use that voice directly.

If the user did NOT specify a voice:

  1. Analyze the topic and FOUNDER_CONTEXT.md brand voice
  2. Auto-suggest the best match based on topic:

- Business advice, mindset, pricing, sales, productivity → suggest Alex Hormozi - Life philosophy, contrarian takes, self-improvement, minimalism → suggest Naval Ravikant - Startup advice, CEO/founder roles, hiring, company building → suggest Andrew Gazdecki - Self-improvement, productivity hacks, fitness + learning, habits → suggest Dakota Robertson - AI trends, tool launches, tech stack recommendations, urgent opportunities → suggest Machina - SaaS growth, AI productivity, founder mindset, revenue strategy → suggest Ognjen Gatalo - Personal responsibility, escaping default paths, harsh reality checks, focus training → suggest Dan Koe

  1. Ask the user to confirm using AskUserQuestion:

- [Suggested Voice] (Recommended) — [one-line description of why it fits] - [Other Voice 1] — [one-line description] - [Other Voice 2] — [one-line description] - My own voice — Natural tone based on FOUNDER_CONTEXT.md brand voice

4. Generate 3 Viral Posts

Using the formats, posts, and voice you loaded in Steps 1-3:

  1. Select 3 DIFFERENT formats from formats.md that best fit the user's topic and goal
  2. Study the example posts in posts.md for those formats — internalize the rhythm, structure, and length
  3. Apply the selected voice from voices.md — match their sentence structure, rhythm, and signature patterns (not their exact words or examples)
  4. Draft each post following the format's structure template, the voice's DNA, and all Writing Rules below
  5. Run each post through the Screenshot Test: "Would someone screenshot this and share it?" If no → rewrite before continuing

Critical requirements:

  • Each post must use a DIFFERENT format (no repeats)
  • Each post must sound like the selected voice (structural match, not word-for-word copy)
  • Each post must be about the user's SPECIFIC topic (not generic advice)
  • Each post must follow the format's structure template from formats.md
  • Each post must be ready to copy-paste and post immediately — no placeholders

5. Format and Verify

  • Structure output according to Output Format section
  • Complete Quality Checklist self-verification before presenting output
  • If any post feels generic, forced, or wouldn't pass the Screenshot Test → rewrite before presenting

Writing Rules

Hard constraints. No interpretation.

Core Rules (Apply to ALL posts)

  • Maximum 280 characters for single posts. If a post exceeds 280 characters, it must be structured as a thread (each tweet under 280 characters).
  • First line is the hook — it determines whether people click "Show more." Make it the strongest line in the post.
  • Use line breaks strategically. White space = visual breathing room = readability.
  • No hashtags. They reduce reach and look amateur on X.
  • No engagement bait ("like if you agree", "RT if this resonates", "thoughts?"). It kills reach.
  • No emojis unless the voice or topic specifically calls for it. When used, maximum 1-2 per post.
  • Specific numbers > vague claims ("17 strategies" not "many strategies").
  • Opinions > facts. X rewards bold takes, not Wikipedia summaries.
  • Active voice only. Never passive.
  • Present tense preferred.
  • Every word must earn its place. If you can cut a word without losing meaning, cut it.
  • No "I think" or "In my opinion" — just state the opinion as fact. Confidence is voice.

Voice-Matching Rules

  • Match the voice's SENTENCE STRUCTURE — short choppy lines vs flowing sentences, fragments vs complete thoughts.
  • Match their RHYTHM — how they pace ideas, where they place line breaks, how they build tension.
  • Match their PERSPECTIVE — coaching from authority (Hormozi) vs philosophical detachment (Naval) vs peer founder advice (Gazdecki).
  • Do NOT copy their exact phrases, examples, or company references. Create original content that SOUNDS like them structurally.
  • If the user chose "My own voice," use a natural, conversational tone that matches FOUNDER_CONTEXT.md brand voice. If no context exists, default to direct and conversational.

Format-Specific Rules

  • One-Liners: One sentence. One idea. No explanations. Every word carries weight.
  • Two-Part Punch: Line break between parts. Second part MUST change the meaning of the first.
  • Numbered Lists: Odd numbers preferred. Each item must be specific and standalone. Strong, opinionated closer.
  • Stacked Progression: Same grammatical structure per line. Build momentum. The final line MUST break the pattern.
  • Comparison: Stark, obvious contrast. Don't lecture — let the contrast make the point.
  • Example + Takeaway: Use real, named companies or people. Minimum 3 examples. Actionable closer.
  • Reverse Advice: Deadpan delivery. No winking. Every item is a real mistake people make.
  • Humor: One joke per post. Deadpan > trying hard. Industry-specific > generic. Never explain the joke.

The Screenshot Test

Before finalizing ANY post, ask yourself: "Would someone screenshot this and share it with their group chat?" If the answer is no — the post isn't good enough. Rewrite it.


Output Format

Present exactly 3 posts, each labeled with its format and voice:

## Your 3 X Posts

**Voice:** [Selected voice name]
**Topic:** [User's topic]

---

### Post 1 — [Format Name]

[Full post text, ready to copy and paste]

---

### Post 2 — [Format Name]

[Full post text, ready to copy and paste]

---

### Post 3 — [Format Name]

[Full post text, ready to copy and paste]

Example:

## Your 3 X Posts

**Voice:** Alex Hormozi
**Topic:** Why most SaaS founders fail

---

### Post 1 — Comparison

SaaS founders who fail:

- Build for 6 months in silence
- Launch to crickets
- Blame the market

SaaS founders who win:

- Post the idea before writing code
- Get 50 people to say "I'd pay for that"
- Build only what was validated

The market doesn't lie. Your assumptions do.

---

### Post 2 — One-Liner

The graveyard of failed startups isn't full of bad ideas. It's full of founders who built before they sold.

---

### Post 3 — Stacked Progression

Day 1: "I have a great idea."
Week 2: "The MVP is almost done."
Month 3: "Just a few more features."
Month 6: "Why is no one signing up?"

You shipped a product. You never shipped distribution.

References

These files MUST be read using the Read tool before generating any posts (see Step 1):

FilePurpose
./references/formats.md8 proven post formats with structure templates, psychology, and rules
./references/posts.md51+ proven viral posts organized by format — the example library
./references/voices.md7 creator voice profiles (Hormozi, Naval, Gazdecki, Dakota, Machina, Ognjen, Dan Koe) with writing DNA and example posts

Why all three matter: Formats provide structural templates for how posts are built. Posts show those templates executed at the highest level with real examples. Voices add the human layer that makes content feel authentic instead of AI-generated. All three together = posts that go viral because they have proven structure + proven patterns + authentic voice.


Quality Checklist (Self-Verification)

Before finalizing output, verify ALL of the following:

Pre-Execution Check

  • I read ./references/formats.md before generating posts
  • I read ./references/posts.md before generating posts
  • I read ./references/voices.md before generating posts
  • I have all formats, example posts, and voice profiles in context

Format Verification

  • Each post uses a DIFFERENT format from formats.md (no repeats)
  • Each post follows its format's structure template exactly
  • Format-specific rules are followed (line counts, structure requirements)

Voice Verification

  • All 3 posts match the selected voice's sentence structure and rhythm
  • Posts sound like the voice — structurally matched, not copied
  • No phrases or examples were directly lifted from voice example posts

Content Verification

  • All 3 posts are about the user's specific topic (not generic filler)
  • Each post contains specific details, numbers, or examples (nothing vague)
  • No hashtags, engagement bait, or unnecessary emojis
  • Every post is under 280 characters OR clearly structured as a thread
  • Each post is ready to copy-paste and post immediately

The Screenshot Test

  • Would someone screenshot Post 1 and share it? If no → rewrite
  • Would someone screenshot Post 2 and share it? If no → rewrite
  • Would someone screenshot Post 3 and share it? If no → rewrite

If ANY check fails → revise before presenting.


Defaults & Assumptions

Use these unless the user overrides:

  • Number of posts: 3 (each in a different format)
  • Voice: Ask user to choose (auto-suggest based on topic and FOUNDER_CONTEXT.md)
  • Goal: Maximize engagement (likes, reposts, bookmarks)
  • Audience: Founders, entrepreneurs, builders (unless FOUNDER_CONTEXT specifies otherwise)
  • Tone: Matches selected voice profile
  • Post type: Single post (not thread) unless the topic requires more depth
  • Character limit: 280 characters per post (X standard)
  • Topic specificity: Use the user's exact topic — never drift to generic startup advice

Document any assumptions made in the output.

平台分布

Codex

38.64%
按下载量换算534

Claude

30%
按下载量换算415

Cursor

19%
按下载量换算263

Gemini CLI

9.81%
按下载量换算136

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

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。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills