← 返回 Skills 市场

LinkedIn Post Writer

Name: LinkedIn Post Writer
Author: sergebulaev

作者 Sergey Bulaev · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

总下载

当前安装

版本数

在 OpenClaw 中安装

/install linkedin-post-writer

功能描述

Draft a LinkedIn post using proven 2026 hook formulas, tailored voice, and scheduling options for founders, marketers, and thought leaders.

使用说明 (SKILL.md)

LinkedIn Post Writer

Ship long-form LinkedIn posts using hook formulas that actually performed in 2025-2026 (verified engagement multipliers from Jake Ward, Lara Acosta, Cam Trew, Noam Nisand, Alex Vacca, Richard Illingworth, Naïlé Titah).

When to use

User says "write me a LinkedIn post about X"
User has a topic + a rough angle and needs a hook + structure
User wants to pick from known-winning formats and fill in their voice
User wants to audit + schedule in one flow

Formulas this skill can use

Code	Formula	Reference eng	Best for
F1	Platform Risk Anaphora (Jake Ward)	4,240	Category/platform posts, product-as-fix
F2	R.I.P. Obituary (Alex Vacca)	3,822	Era-ending claims, industry pivots
F3	Year-over-Year Pivot (Cam Trew)	494, 3.74x	Identity shifts, founder reflection
F4	Time-Anchor Confession (Lara Acosta)	1,519+	Vulnerability, voice reset, ICP re-targeting
F5	Self-Proving Meta (Noam Nisand)	1,082 / 435 comments	Commitment-based posts, tests in public
F6	Comment-Gate Lead Magnet (Illingworth)	717-3,008	List building (use sparingly, capped reach)
F7	Odd-Precision Money Ledger (Jake Ward)	1,755, 9.4x	Founder build-log, cost breakdowns
F8	Paid-vs-Free Reversal (Illingworth)	550, 19.64x	Free framework give-away
F9	Curiosity-Gap Teaser (Naïlé Titah)	306, 4.25x	Emergent behavior, behind-the-scenes
F10	Contrarian + Historical Receipts (Jake Ward)	3,083	Sacred-cow takes, AI/tech cycles

Full skeletons in references/hook-formulas.md.

Steps

Gather inputs. Topic, angle, draft ideas if the user has them, target audience (founders / operators / marketers), desired length (short 300-500 / medium 900-1300 / long 1500-1900 chars).
Pick the formula. If the user didn't specify, suggest 2-3 formulas that fit the topic and let them pick. Show the reference engagement number next to each.
Draft the post. Fill the formula skeleton with user voice. Respect the 2026 algorithm rules:
- Hook in first 210 chars (before "… see more")
- 900-1,300 char sweet spot for text posts
- Double line-breaks between ideas, not single
- 0-2 hashtags, placed at end
- No external links in body (move to first comment)
Humanizer pass. Strip em dashes, AI vocab, rule-of-three, generic openers. Add at least 1 specific number, 1 named entity, 1 first-person concrete detail per 100 words.
Run audit. Optionally invoke linkedin-post-audit for algorithm + voice checks before showing to user.
Approval card. Show: formula used, full draft, char count, suggested posting window (Tue/Wed/Thu 7:30-9:00 AM local), reaction targets from likely commenters.
On approval — adapt to the active backend. Call lib.active_backend():
- publora (PUBLORA_API_KEY set) → schedule via lib.PubloraClient.create_post with LinkedIn platformId. If scheduledTime omitted, Publora posts ~90s in the future.
- manual (no backend configured — the default) → output the approved post via lib.manual_mode_message(draft_text, target_url="https://www.linkedin.com/post/new/", kind="post"). User pastes directly into LinkedIn's post composer. Do NOT attempt to publish programmatically.
- diy (LINKEDIN_SKILLS_CUSTOM_POSTER set) → invoke the custom poster with the post content + optional media URLs.

Hard rules (from user feedback)

No em dashes. Ever. Period.
Capitalize all names, companies, products.
Never frame LinkedIn as inferior in a LinkedIn post (algo penalty).
Don't name-drop the user's product in a way that reads as self-promo. One mention max, and only when it's the natural conclusion, not the pitch.
Include at least one moment of real vulnerability or concrete stakes — pure insight posts don't land in 2026.
Vary sentence length aggressively. Mix 3-word sentences and 25-word sentences.

Anti-patterns (skill will refuse)

All-caps first line ("THIS CHANGED EVERYTHING.")
Em dashes anywhere
"In today's fast-paced world" openers
Rule-of-three lists without receipts
"Game-changer", "deep dive", "leverage", "fundamentally"
External links in the body
Reused engagement-bait closers ("tag someone who needs this")

Resources

references/hook-formulas.md — all 10 formula skeletons with worked examples
references/algorithm-heuristics.md — 2026 posting rules (timing, format, length)
references/humanizer-checklist.md — the full scrub list
Upstream: ../../corporate-knowledge/personal/knowledge/linkedin/serge/2026-04-13-viral-drafts/ — canonical reference drafts

Related skills

linkedin-post-audit — run this on any draft before publishing
linkedin-humanizer — aggressive AI-tell scrubber
linkedin-hook-extractor — reverse-engineer a hook from a viral post you admire

安全使用建议

This skill appears to do what it claims (draft and optionally schedule LinkedIn posts) but there are two practical red flags to resolve before installing: (1) SKILL.md expects external backends and environment variables (PUBLORA_API_KEY, LINKEDIN_SKILLS_CUSTOM_POSTER) but the manifest lists no required env vars — ask the publisher to declare any credentials, explain precisely when the skill will call external APIs, and provide the vendor/domain for any scheduler (Publora). (2) SKILL.md references an upstream local path to private corporate knowledge — verify whether the skill will attempt to read any local files or private repos. Before enabling automatic scheduling, require explicit user confirmation in the UI and verify the third-party scheduler's privacy/security practices. If you cannot get clear answers about the undeclared env vars and the upstream path, treat the skill as untrusted and use manual mode only.

功能分析

Type: OpenClaw Skill Name: linkedin-post-writer Version: 1.0.0 The 'linkedin-post-writer' skill is a specialized tool for generating and scheduling LinkedIn content based on specific marketing frameworks. It contains detailed instructions for an AI agent to follow formatting rules, 'humanize' text by removing AI-typical vocabulary, and handle publishing through various backends (Publora API, manual, or custom). There is no evidence of malicious intent, data exfiltration, or unauthorized execution; the use of API keys and external library calls (e.g., lib.PubloraClient) is consistent with its stated purpose of social media management.

能力标签

cryptocan-make-purchasesrequires-sensitive-credentials

能力评估

ℹ Purpose & Capability

The name/description (draft LinkedIn posts, apply hook formulas, optionally schedule) aligns with the instructions: drafting, a humanizer pass, an approval card, and optional scheduling via a backend. However, the SKILL.md references concrete backends and variables (PUBLORA_API_KEY, LINKEDIN_SKILLS_CUSTOM_POSTER) and an upstream local path that are not declared in the skill metadata — this is inconsistent and should be justified or fixed.

⚠ Instruction Scope

Runtime instructions instruct the agent to: run a humanizer pass, optionally invoke other skills (linkedin-post-audit, linkedin-humanizer), call lib.active_backend(), and—if a Publora backend is active—call lib.PubloraClient.create_post. Those instructions may cause the agent to transmit drafted content (and potentially scheduling metadata) to external services. The SKILL.md also points to an absolute upstream path (../../corporate-knowledge/...) which implies reliance on local private files not declared or included. The instructions reference environment variables and backends that the skill manifest does not declare, giving the agent broad runtime choices without clear, declared permissions.

✓ Install Mechanism

This is an instruction-only skill with no install spec and no code files — lowest install risk. Nothing is downloaded or written to disk by the skill package itself.

⚠ Credentials

The skill metadata declares no required environment variables, yet SKILL.md explicitly expects PUBLORA_API_KEY and LINKEDIN_SKILLS_CUSTOM_POSTER to enable scheduling/backends. That mismatch is problematic: if those variables are present in the environment, the skill will use them (possibly posting content); if not, it defaults to manual mode. The skill should declare any credentials it can use and explain what data it will send to third-party scheduling APIs. The upstream local path reference also suggests hidden dependencies on private data.

✓ Persistence & Privilege

always:false and no install-time persistence are set — the skill does not request permanent inclusion or elevated agent privileges. The skill can be invoked autonomously (platform default), which is expected for a productivity skill; this is not in itself flagged, but it does increase the importance of resolving the environment/endpoint inconsistencies above.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install linkedin-post-writer
安装完成后，直接呼叫该 Skill 的名称或使用 /linkedin-post-writer 触发
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

v1.0.0

Initial release: 10 viral 2026 hook formulas with verified engagement multipliers, 360Brew algorithm heuristics, humanizer checklist.

元数据

Slug linkedin-post-writer

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题