Index of every page on this site: llms.txt
All skills
sergebulaev avatar

/linkedin-post-writer

@32083c0
Run it yourself

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).

Use this Skill: https://skilld.dev/gh/sergebulaev/linkedin-skills/linkedin-post-writer

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈128 tokens for metadata: the name and description. ≈3k when used: this file. ≈2.2k more on demand in 4 files.

Description uses 6.4% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈514 characters, or 6.4%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

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

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alertstoday3 checks · Risk SAFE
  • Gen Agent Trust Hubtoday

    The skill is a LinkedIn content generation tool that drafts and schedules posts using specific engagement-driven formulas. It includes built-in quality checks and humanization passes to reduce AI detectable patterns before publishing. No security risks or malicious behaviors were detected.

  • Sockettoday

    No alerts

  • Snyktoday

    Risk: LOW · No issues

Signed by skilld at 32083c0. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 weeks ago
metadata
{
  "author": "Sergey Bulaev"
}

README badge

README badge for sergebulaev/linkedin-skills/linkedin-post-writer