К основному содержанию
скилл CX Codex

linkedin-post-writer · sergebulaev — скилл для Claude Code

Скилл linkedin-post-writer для Claude Code создаёт посты для LinkedIn по формулам хуков и целям охвата. Запускается при запросе на черновик поста с нуля.

MIT 192 установок ★ 6 103 обновлён 2026-11-18

Установить в Claude Code · Через Skills CLI (Vercel) Все способы и платформы ↓
npx skills add sergebulaev/linkedin-skills --skill linkedin-post-writer -a claude-code
Открыть на GitHub

Что делает linkedin-post-writer

Скилл генерирует посты для LinkedIn, подбирая одну из 20 формул хуков под конкретную метрику: комментарии, репосты, лайки или сохранения. Для фаундеров предусмотрена библиотека из 10 ракурсов (A1–A10), которая делает упор на доверие инвесторов и партнёров, а не на случайный вирусный охват. Доступны форматы от коротких заметок на 300–500 знаков до подробных постов на 1500–1900 знаков.

Инструмент считывает стиль автора из voice-profile.md и конкретные факты из story-bank.md, а также принимает пятистрочную структуру после linkedin-interviewer. Для проверки готовых черновиков скилл не подходит — для этого предназначен linkedin-humanizer --mode audit. Согласованную публикацию инструмент передаёт в Publora.

Какие задачи решает

  • написание постов в LinkedIn
  • подобрать формулу открывающего хука под комментарии, репосты или лайки
  • оформить фаундерский пост по готовым ракурсам без выдуманных цифр
  • запланировать публикацию через Publora после одобрения текста

Примеры запросов агенту

  • Напиши пост в LinkedIn о переходе с микросервисов на монолит с целью собрать комментарии
  • Подбери фаундерский хук для истории о первом платном клиенте
  • Сделай черновик поста для LinkedIn на 1000 знаков на основе story-bank.md

Как установить linkedin-post-writer

1Через Skills CLI (Vercel)

npx skills add sergebulaev/linkedin-skills --skill linkedin-post-writer -a claude-code

2Вручную: положить файлы

~/.claude/skills/linkedin-post-writer/SKILL.md

Папка скилла целиком; для одного проекта — .claude/skills/linkedin-post-writer/

По шагам, с командами для каждой платформы: Как установить скилл в Claude Code: пять способов

Вопросы о linkedin-post-writer

Как установить linkedin-post-writer в Claude Code?

Выполните команду npx skills add sergebulaev/linkedin-skills --skill linkedin-post-writer -a claude-code.

Что делает linkedin-post-writer?

Скилл пишет черновики постов для LinkedIn с нуля, выбирая одну из 20 формул хуков под выбранную метрику вовлечения.

Подходит ли linkedin-post-writer для вычитки существующих черновиков?

Нет, аудит готовых текстов скилл не выполняет: для этого в наборе предусмотрен linkedin-humanizer --mode audit.

Исходный текст

SKILL.md · MIT
---
name: linkedin-post-writer
description: "Draft a new LinkedIn post from scratch using one of 20 2026 hook formulas (anaphora, R.I.P., time-anchor, curiosity-gap, contrarian, controlled A/B, false-binary, and more) plus a founders-edition angle library, picked by engagement goal (comments, reposts, likes, saves). Runs the humanizer pass and schedules via Publora on approval. Use to write a post, find a hook or proven format, or get founder-specific angles. Not for reviewing existing drafts (use linkedin-humanizer --mode audit)."
license: MIT
metadata:
  author: Sergey Bulaev
---

# LinkedIn Post Writer

Ship long-form LinkedIn posts using hook formulas that actually performed in 2025-2026 (verified engagement multipliers).

## 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 | 4,240 | Category/platform posts, product-as-fix |
| F2 | R.I.P. Obituary | 3,822 | Era-ending claims, industry pivots |
| F3 | Year-over-Year Pivot | 494, 3.74x | Identity shifts, founder reflection |
| F4 | Time-Anchor Confession | 1,519+ | Vulnerability, voice reset, ICP re-targeting (2026: use with care, see caveats) |
| F5 | Self-Proving Meta | 1,082 / 435 comments | Commitment-based posts, tests in public |
| F6 | Comment-Gate Lead Magnet | 717-3,008 | List building (2026: use with care, real deliverable only, see caveats) |
| F7 | Odd-Precision Money Ledger | 1,755, 9.4x | Founder build-log, cost breakdowns (2026: strongest opener, number-first) |
| F8 | Paid-vs-Free Reversal | 550, 19.64x | Free framework give-away |
| F9 | Curiosity-Gap Teaser | 306, 4.25x | Emergent behavior, behind-the-scenes (2026: use with care, pay off in 2 lines) |
| F10 | Contrarian + Historical Receipts | 3,083 | Sacred-cow takes, AI/tech cycles |
| F11 | Emotional Cold-Open | high-reach* | Real story with emotional stakes (likes) |
| F12 | Permission Slip | comment-heavy* | Encouragement, reassurance (comments; 2026: use with care, needs a dated fact) |
| F13 | Bait-and-Switch Reversal | high-reach* | Policy/process change that's an upgrade (likes) |
| F14 | Named Gratitude / Tribute | repost-heavy* | Thanking mentors / team / departing colleague (reposts) |
| F15 | Explain-to-Kids | save-heavy* | Demystifying jargon (saves) |
| F16 | Status-Strip Humility | like-heavy* | Senior voice wanting warmth not distance (likes) |
| F17 | Controlled A/B Anecdote | structural† | One-variable comparison, delegation/AI takes (comments) |
| F18 | False-Binary Dissolve | structural† | "Both obvious answers fail" governance/strategy (comments/reposts; 2026: it is the post's one contrast) |
| F19 | Anecdote-Meets-Evidence Bridge | structural† | Personal noticing + a data stack (comments/saves) |
| F20 | Diverging-Curves Close | structural† | Two trajectories that diverge, quotable maxim (reposts) |

\* F11-F16 reach is absolute 2026-corpus reach (often source-driven: a reshare or a famous author), NOT a baseline multiplier like the F1-F10 numbers. The two columns measure different things and are not comparable: F11's "256k" is raw reach, F8's "550, 19.64x" is a format multiplier. Do not rank formulas by putting these side by side. See `../../references/hook-formulas.md` for each formula's real reference and caveats.

† F17-F20 are **structural formulas**: they shape the logic of a post (a controlled comparison, a false binary, an evidence bridge, two diverging curves) rather than its topic. They carry no reference number and are chosen by primary goal. They were built for the founders edition and several founder angles pin them by name.

Full skeletons in `../../references/hook-formulas.md`. F1-F10 are the long-form thought-leadership set; F11-F16 (validated against a 2026 corpus of above-average performers) skew shorter and emotional and each carries a primary engagement goal.

### 2026 reach caveats (Sep 2026 audit)

Read `references/reach-caveats-2026.md` before choosing a formula: it lists which formulas need care in 2026 (F4, F6, F9, F12, F18), the number-first and no-question-opener rules, and the density rule.

### Pick by goal first

If the user knows what they want the post to earn, start here, then narrow by topic. Canonical mapping: `../../references/hook-formulas.md` → Engagement-goal split.

| Goal | Reach for |
|---|---|
| Comments | F17, F10, F4, F12, F9 (F4/F12/F9 with their 2026 caveats) |
| Reposts | F14, F2, F8 |
| Likes | F11, F13, F16 |
| Saves | F15, F7, F8 |

## Steps

**Voice profile first (all drafts).** If `../../references/voice-profile.md` has `filled: yes`, load it and match the user's voice fingerprint, hard rules, and CTA/link style throughout. If it is not filled, mention once that `linkedin-humanizer --mode profile` can learn their voice from a few posts, then proceed with the generic voice rules. If `../../references/story-bank.md` has `filled: yes`, load it too and take concrete details (numbers, dates, named projects) from there instead of asking mid-draft. Never invent a figure that is not in it; if the bank has nothing that fits, ask the user or offer `linkedin-interviewer`.

**Founder mode (when the writer is a founder).** Before picking a formula, open `../../references/founder-topics.md` and offer a founder **angle** (A1-A10) that fits their goal. The angle picks the *territory* (reprice the category, the scarce-shots math, the delegation line, and so on); several angles pin the formula for you (A9 uses F17, A10 uses F18+F20). Founder angles compound trust with a narrow audience of investors, hires, and design partners rather than chasing broad reach. Fill the angle's bracketed slots with the founder's real numbers, then continue from step 3.

**Spine from an interview (skip the asking).** If `linkedin-interviewer --mode post` handed over a five-line spine (Moment, Number, Correction, Opposition, Ask), that spine is the skeleton: Moment opens the post, Number is the proof, Correction is the turn, Opposition fixes the audience, Ask is the close. Do not re-ask for anything the spine already carries, and do not fill a line the interview left labelled empty. Pick the formula that fits the spine rather than bending the spine to a formula; if none fits, say which line is the obstacle.

1. **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).
2. **Pick the formula.** First ask (or infer) the goal: comments, reposts, likes, or saves. Use the "Pick by goal first" table to shortlist, then suggest 2-3 formulas that also fit the topic and let the user pick. Show the reference engagement number next to each, plus the formula's 2026 caveat if it has one. Two hook rules apply regardless of formula: **never open with a question** (-34% median likes; the question goes at the close, +3%) and **prefer a number-first line** (+34% median likes; both MagicPost vendor data, proprietary AI-score). If the best hook you have is a question, invert it into the number that answers it.
3. **Draft the post.** Fill the formula skeleton with user voice. Respect the 2026 algorithm rules:
   - Hook in first 210 chars (before "… see more"); line 1 is a statement or a number, never a question, never "Here's what/how", never "Stop X, start Y"
   - Length: **the target the user picked in step 1 wins.** 900-1,300 chars is the default when they express no preference, not a ceiling over their choice. If they asked for long (1,500-1,900), write long and do not trim toward the sweet spot: 1,000+ chars and 20+ sentences carry a 1.18x / 1.14x reach lift (AuthoredUp, 3M posts), so the evidence runs with them, not against them. The one hard limit is LinkedIn's 3,000 characters.
   - Double line-breaks between ideas, not single; 1-2 sentence paragraphs are the recommended layout
   - One contrast and one triple per post maximum; no "The result?" / "Plot twist:" reveal bridges (Density rule in `../../references/hook-formulas.md`)
   - Close with a specific question, and add a one-line P.S. when there is a real follow-up (+7.5%)
   - 0-2 hashtags, placed at end
   - No external links in body (move to first comment)
4. **Humanizer pass.** Scrub 2026 AI vocab by density, cap em dashes (about one per 100 words), break stacked triads, generic openers and reveal bridges. Add at least 1 specific number, 1 named entity, 1 first-person concrete detail per 100 words.
5. **Run audit.** Optionally invoke `linkedin-humanizer --mode audit` for algorithm + voice checks before showing to user.
6. **Optional illustration.** If the post would land better with a visual (or the user asks), offer one: draft an image and generate it with `lib.illustrate(prompt, kind="wide")`, pulling brand handle/color from Voice & Brand Profile §6 for the overlay. Show the returned `url` + `cost` in the approval card and attach it via `media_urls` on publish. For a **multi-image grid** (2-10 images in one post) use `lib.illustrate_set([p1, p2, ...], kind="wide", overlay=brand)` and pass every `url` in `media_urls=[...]`. For a **quote-card of the hook**, skip the model and typeset it: `lib.quote_card("<hook line>", handle="@handle", style="brand")` — crisp text, same `url` flow. Full workflow: `../linkedin-humanizer/sub-skills/illustration.md`. No Pixfaro key -> it drafts the prompt for the user to generate manually.
7. **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, and the illustration (if any).
8. **On approval.** Call `lib.publish(kind="post", draft_text=<approved>, target_url="https://www.linkedin.com/post/new/", platforms=[{"platform":"linkedin","platformId":<id>}], scheduled_time=<iso_or_None>, media_urls=<list_or_None>)`. The wrapper handles Publora / manual / diy routing. If the user reconsiders after approving, call `lib.unpublish(post_group_id=<postGroupId from the response>)` to cancel it before it goes out. On the publora tier the post is already queued, so the dashboard is otherwise the only way back.

## Hard rules (from user feedback)

Global voice rules: see root `SKILL.md` §Voice rules. Additional skill-specific rules:

- 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.
- Natural rhythm, not manufactured variance: one genuinely long sentence next to a short one per paragraph is fine; never alternate long/short across the post and never stack fragments (at most 2 standalone fragments per post). Touch a paragraph only if every sentence reads the same flat length.

## Anti-patterns (skill will refuse)

- All-caps first line ("THIS CHANGED EVERYTHING."). This holds even for F11 Emotional Cold-Open: carry the intensity with word choice, never caps.
- Question as the first line ("Ever wondered why...?"). Invert to a number, move the question to the close.
- "Here's what / here's how" or "Stop X, start Y" as the opener; "The result?" / "Plot twist:" as a reveal bridge
- Announced candor ("Let me be honest", "Confession:") with no dated fact behind it
- "Comment X to get Y" comment-gate phrasing
- Em dashes above the cap (more than about one per 100 words)
- "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 20 formula skeletons with worked examples, per-formula 2026 reach notes, "What still lifts reach in 2026" and the Density rule
- `../../references/founder-topics.md` — founders-edition library of 10 founder angles (A1-A10) with fill-in templates
- `../../references/algorithm-heuristics.md` — 2026 posting rules (timing, format, length)
- `references/humanizer-checklist.md` — the full scrub list

## Related skills

- `linkedin-humanizer` — aggressive AI-tell scrubber, plus `--mode audit` for pre-publish review
- `linkedin-hook-extractor` — reverse-engineer a hook from a viral post you admire

© sergebulaev · MIT · sergebulaev/linkedin-skills

Похожие скиллы

Все скиллы по теме «Маркетинг и контент» →

Сначала — linkedin-post-writer от других авторов.

linkedin-post-writer social-media-skills Скилл linkedin-post-writer для Claude Code и Codex. Пишет посты для LinkedIn с цепляющей первой строкой, разметкой под долгое чтение и ссылками в первом комментарии. CX Codex +1 1 200установок linkedin-post publora Скилл linkedin-post для Claude Code и Codex публикует и планирует посты в LinkedIn через MCP-сервер Publora: текст, сетку картинок, видео или PDF. Создаёт публикации без веб-интерфейса. CX Codex +1 ★ 71звёзд репо LinkedIn Post Writer официальный github Субагент LinkedIn Post Writer превращает черновик, технический текст или идею в готовый пост для LinkedIn с Unicode-разметкой и структурой под алгоритм ленты. CX Codex +1 ★ 41 430звёзд репо linkedin-writer ognjengt Скилл linkedin-writer для Claude Code генерирует два поста для LinkedIn в разных форматах под голос автора, выбирая формат по теме. CX Codex +1 1 400установок linkedin-post-optimizer OneWave-AI Скилл linkedin-post-optimizer для ИИ-агента, который пишет посты в LinkedIn: хук в первых двух строках, разбивка на строки, стратегия хештегов. CX Codex +1 426установок linkedin-analytics publora Скилл linkedin-analytics для Claude Code собирает статистику публикаций LinkedIn и управляет реакциями через Publora. Анализирует охваты и отвечает на комментарии из чата. CX Codex +1 ★ 71звёзд репо linkedin manojbajaj95 Проверяет профиль LinkedIn и помогает писать посты. Оценивает видимость и SSI, составляет контент-план. CX Codex +1 145установок

Из того же набора13

Весь набор →
linkedin-marketing Скилл linkedin-marketing для Claude Code планирует, пишет, проверяет и публикует посты и комментарии в LinkedIn. Помогает составлять контент-план и работать с обсуждениями. CX Codex +1 2 100установок linkedin-profile-optimizer Скилл linkedin-profile-optimizer для Claude Code разбирает девять секций профиля LinkedIn и переписывает слабые блоки. Запускается при просьбах проверить резюме, переписать заголовок или био. CX Codex +1 195установок linkedin-humanizer Скилл linkedin-humanizer для Claude Code убирает маркеры ИИ-текста из постов и комментариев в LinkedIn. Запускается перед публикацией черновика или во время проверки стиля. CX Codex +1 182установок linkedin-content-planner Скилл linkedin-content-planner составляет план публикаций LinkedIn на 7 дней: темы, форматы, призывы к действию и цели по комментариям. CX Codex +1 182установок linkedin-hook-extractor Скилл linkedin-hook-extractor разбирает структуру вирусных постов в LinkedIn, определяет формулу зачина из 20 канонических шаблонов и собирает пустую заготовку под вашу тему. CX Codex +1 178установок linkedin-comment-drafter Скилл linkedin-comment-drafter готовит варианты комментариев к чужим публикациям в LinkedIn по ссылке или создаёт репост с заметкой. Помогает включиться в обсуждение и публикует результат через Publora после одобрения. CX Codex +1 173установок linkedin-reply-handler Скилл linkedin-reply-handler готовит ответы на отдельные комментарии LinkedIn или на целую ветку, а после вашего одобрения публикует их через Publora. Пригодится, чтобы продолжить разговор или разобрать комментарии под постом. CX Codex +1 168установок linkedin-engager-analytics Скилл linkedin-engager-analytics для Claude Code собирает профили тех, кто лайкал или комментировал посты LinkedIn, и делит их по соответствию ICP. Он формирует списки для дальнейших действий. CX Codex +1 161установок

Спонсоры проекта

Компании, которые помогают держать аналитику открытой