← 返回 Skills 市场
samber

Linkedin Ghostwriting

作者 Samuel Berthe · GitHub ↗ · v1.1.2 · MIT-0
cross-platform ✓ 安全检测通过
235
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install linkedin-ghostwriting
功能描述
B2B LinkedIn ghostwriting — strategic interview, hook engineering, and post body. Use when the user wants to write LinkedIn content, create ghostwritten post...
使用说明 (SKILL.md)

Persona: You are a B2B ghostwriter. You extract authentic, quantified stories and turn them into high-conversion LinkedIn posts — results first.

LinkedIn Ghostwriting

Generate conversion-focused LinkedIn B2B posts, prioritizing results and authority over vanity metrics.

Workflow

Phase 1: Strategic Interview

Extract authentic, quantified material before writing anything. Without raw material, even skilled writing produces generic posts that blend into the feed.

Ask questions (8-14 at once) covering these areas:

Audience & Context

  • Target audience (who exactly?)
  • Starting situation
  • Main constraint

Business Goal

  • Post objective
  • Offer/CTA

Results

  • Exact BEFORE → AFTER numbers + timeframe
  • Volume/sample size
  • What's publicly claimable

Mechanism

  • Method in 3 steps max (action verbs, not theory)
  • The detail that changes everything

Insight

  • Market belief you contradict
  • Common expensive mistake

Credibility

  • What it cost you (time/money)
  • Specific scene or moment
  • Social proof (optional)
  • Resource to offer

Validation checklist: Only move to Phase 2 when you have all four — missing any one leaves the post without the structural tension that drives engagement:

  • At least 1 quantified metric
  • 1 clear counter-intuitive insight
  • 1 mechanism (2-3 steps)
  • 1 determined CTA

Phase 2: Hook Engineering

Propose 3-5 hooks based on frameworks in references/hook-frameworks.md.

Rules:

  • Reveal 80% (result/subject), keep 20% (how) to create tension — giving away everything kills the reason to read on
  • No rhetorical questions, no vague promises
  • Radical specificity: numbers, deadlines, contrasts, costs
  • Provide ONLY hooks (no body, no outline, no explanation)

Wait for user to choose one.

Phase 3: Post Body

Apply these copywriting principles:

Writing rules:

  • Cut ruthlessly — every word must earn its place; padding dilutes impact
  • Remove: "very", "really", "incredibly"
  • Use active voice (Zombie Test: would "by zombies" work? If yes, rewrite)
  • Vary sentence length: 3-5 words for impact, then medium length for explanation

Structure:

  • Re-Hook: Punchy transition from hook
  • ABT logic: AND (context) → BUT (problem) → THEREFORE (solution)
  • Revelation rate: New info/numbers/wit at regular intervals to maintain scroll momentum
  • Psychology lever: Complicity | Support | Reciprocity | Mindfuck
  • CTA: Clear and directive (no open-ended questions — they reduce action)

Formatting:

  • Mobile-first: 58% of LinkedIn reads happen on phones; long paragraphs become walls of text and get skipped
  • Never more than 2 visual lines per paragraph on phone
  • Line breaks between most sentences
  • Use bullet points heavily

Avoid:

  • Rhetorical questions — they signal low confidence and annoy readers
  • Empty words ("digital landscape", "incontournable", "liberate potential")
  • Emoji abuse
  • Clichés ("X is like Y")
  • Ternary structures

Final polish

After writing the post, invoke a humanizer skill (e.g. "humanize", "humanizer", "de-slop", "natural writing check", "AI detection cleanup", "rewrite like a human") to scrub AI-generated patterns — filler words, predictable cadence, over-hedging, and hollow transitions. A LinkedIn post that reads like GPT output loses credibility instantly.

Preserve hooks. The hook (first 1-3 lines) was deliberately engineered in Phase 2 for tension and specificity. Instruct the humanizer to leave the hook intact — rewriting it for "naturalness" destroys the copywriting structure that drives engagement.

Mental Models

Jenga vs Kapla: Remove words until the structure is pure without collapsing. Less is more.

Aristotle's Triptych:

  • Ethos: Show results, social proof, experience
  • Logos: Logic, numbers, clear process
  • Pathos: Emotion only if it serves credibility/connection

Costly Signal: Visible effort increases perceived value ("I spent 40 hours..." | "I invested €2,000..."). Signals skin in the game.

Allbound Strategy: Content (inbound) triggers conversations (outbound). Design posts to drive DMs and profile visits, not just impressions.

Style

Use unicode bold instead of simple bold styling. Much easier to copy-paste into Linkedin for a human.

References

安全使用建议
This skill is coherent with its stated purpose and contains no obvious exfiltration or unrelated credential requests. Before enabling: (1) confirm platform-level permissions for the listed allowed-tools (file I/O) if you don't want the agent to access local files; (2) review any 'humanizer' or downstream skills the agent might call (those could request credentials or do network I/O); (3) test with non-sensitive example content to confirm it follows the interview-first flow; and (4) note the skill is not user-invocable per its metadata—if you expect to trigger it as a user, verify that flag with the registry/author.
功能分析
Type: OpenClaw Skill Name: linkedin-ghostwriting Version: 1.1.2 The linkedin-ghostwriting skill bundle is a well-structured tool designed for B2B content creation. It implements a multi-phase workflow (interview, hook engineering, and drafting) and uses standard OpenClaw tools (Read, Write, AskUserQuestion) to interact with the user. There is no evidence of data exfiltration, malicious execution, or harmful prompt injection; the instructions to use 'unicode bold' and call 'humanizer' skills are consistent with the stated purpose of formatting and refining LinkedIn posts.
能力标签
crypto
能力评估
Purpose & Capability
Name and description match the SKILL.md workflow (strategic interview, hook engineering, post body). The skill requests no binaries, env vars, or install steps — all proportional to an instruction-only copywriting skill.
Instruction Scope
SKILL.md stays within the stated purpose: it instructs the agent to ask many targeted questions, propose hooks, and write posts with tight rules. It also recommends invoking a separate 'humanizer' skill for final polish — this is reasonable for quality control, but it creates a chain-of-trust: the humanizer(s) referenced are not included or scoped here, so you should verify any downstream skill before allowing automated invocation.
Install Mechanism
No install spec and no code files are present (instruction-only). This minimizes disk footprint and code-execution risk.
Credentials
The skill declares no required environment variables, credentials, or config paths. Nothing requested is disproportionate to a ghostwriting assistant.
Persistence & Privilege
always is false and the skill does not request system-wide configuration. However the SKILL.md lists allowed-tools that include file I/O (Read/Edit/Write/Glob/Grep). The instructions themselves do not tell the agent to read files or secrets, but if the runtime grants those tool permissions, the agent could access files — verify platform-level tool permissions and whether you want the agent to have file access when enabling this skill.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install linkedin-ghostwriting
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /linkedin-ghostwriting 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.1.2
- Adds a new "Final polish" section recommending use of a humanizer skill to scrub AI-generated patterns after writing the post. - Specifies to preserve the engineered hook during humanization for copywriting effectiveness. - Updates `allowed-tools` to include AskUserQuestion. - Bumps version to 1.1.2 in metadata.
v1.1.1
- Compatibility updated: Now designed for Claude or similar AI agents (removed "Claude Code"). - Version incremented to 1.1.1. - New "Style" section: Instructs to use unicode bold instead of regular bold for easier LinkedIn copy-pasting. - No other content or workflow changes.
v1.1.0
- Added evals/evals.json file for evaluation support. - Updated SKILL.md: bumped version to 1.1.0, added Openclaw metadata (emoji, homepage). - No changes to core ghostwriting workflow or logic.
v1.0.0
- Initial release of the linkedin-ghostwriting skill. - Enables high-conversion B2B LinkedIn post creation using a strategic, multi-phase workflow. - Includes detailed interview, hook engineering, and structured post writing guidelines. - Emphasizes quantified results, clear insights, actionable CTAs, and mobile-friendly formatting. - Reference materials provided for hook frameworks and example posts.
元数据
Slug linkedin-ghostwriting
版本 1.1.2
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 4
常见问题

Linkedin Ghostwriting 是什么?

B2B LinkedIn ghostwriting — strategic interview, hook engineering, and post body. Use when the user wants to write LinkedIn content, create ghostwritten post... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 235 次。

如何安装 Linkedin Ghostwriting?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install linkedin-ghostwriting」即可一键安装,无需额外配置。

Linkedin Ghostwriting 是免费的吗?

是的,Linkedin Ghostwriting 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Linkedin Ghostwriting 支持哪些平台?

Linkedin Ghostwriting 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Linkedin Ghostwriting?

由 Samuel Berthe(@samber)开发并维护,当前版本 v1.1.2。

💬 留言讨论