Skill

linkedin-post-writer

Drafts viral LinkedIn posts using 2026 hook formulas like platform-risk anaphora, R.I.P. obituary, and year-over-year pivot. Humanizes drafts, shows approval, and schedules via Publora. Use for new posts, hooks, or formats.

automation

npx claudepluginhub sergebulaev/linkedin-skills --plugin linkedin-skills

Tool Access

This skill uses the workspace's default tool permissions.

Preview

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).

Supporting Assets

references/algorithm-heuristics.mdreferences/hook-formulas.mdreferences/humanizer-checklist.md

SKILL.md

Similar Skills

linkedin-content

401

Generates high-engagement LinkedIn posts and content strategies using proven hooks, formats, algorithm signals, and writing rules.

openclaudia-openclaudia-skills

linkedin-writer

Generates two viral LinkedIn posts in proven formats with voice matching from templates. Use for creating engaging, high-performing LinkedIn content.

2 files

founder-skills

linkedin-content

Generates algorithm-optimized LinkedIn content with hooks, posting strategies, templates for text posts, carousels, videos, polls, and content pillars for personal branding and engagement.

1 file1 tool

majestic-marketing

Stats

Stars33

Forks3

Last CommitApr 29, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

LinkedIn Post Writer

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

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