Draft a platform-native LinkedIn post in your voice. Reads platform-voice.md + brand-brief.md + business-brain.md. Generates 3 hook candidates, plan-then-approves, writes to outputs/, optionally schedules via Blotato. Follows the 12-step shared draft-skill spec.
Draft a platform-native Facebook post in your voice. Reads platform-voice.md + brand-brief.md + business-brain.md. 40-80 word sweet spot. Link previews supported. Plan-then-approves, writes to outputs/, optionally schedules via Blotato. Reads pageId from state-social.md.
Draft a platform-native Instagram caption with required image attachment. Reads platform-voice.md + brand-brief.md + business-brain.md + asset-index.md. Image MANDATORY. 125-2200 char caption, 5-10 hashtags. Plan-then-approves, writes to outputs/, schedules via Blotato.
Draft a platform-native Meta Threads post or reply chain in your voice. Reads platform-voice.md + brand-brief.md + business-brain.md. Up to 500 chars per post, reply chain up to 10. Conversational tone (Instagram-but-text). Plan-then-approves, writes to outputs/, schedules via Blotato.
Draft a TikTok video script + caption + hashtags. Reads platform-voice.md + brand-brief.md + business-brain.md + asset-index.md. Video MANDATORY. Hook under 3s -> context -> payoff -> CTA. Caption under 150 chars, 3-5 hashtags. Plan-then-approves, outputs/, schedules via Blotato.
Draft a platform-native Twitter/X post or thread in your voice. Reads platform-voice.md + brand-brief.md + business-brain.md. 280-char enforcement per tweet, thread support up to 12 tweets. Plan-then-approves, writes to outputs/, optionally schedules via Blotato.
Saturday 8am scheduled task. Reads trend-sources.md + brand-brief + recent calendar-log entries; produces 10 ranked post ideas to ideas/YYYY-MM-DD-ideas.md. Headless: NEXT MOVE block embedded in the file footer.
| name | draft-linkedin |
| description | Draft a platform-native LinkedIn post in your voice. Reads platform-voice.md + brand-brief.md + business-brain.md. Generates 3 hook candidates, plan-then-approves, writes to outputs/, optionally schedules via Blotato. Follows the 12-step shared draft-skill spec. |
| when_to_use | ["/draft-linkedin","draft linkedin post","linkedin post about","write a linkedin post","linkedin draft"] |
Draft a LinkedIn post (hook + body + CTA) tuned to LinkedIn's algorithm and voice. Long-form, comment-driving, no image required.
Read these files on every run. If any is missing, halt and tell the user which /onboard-social phase to re-run.
| File | Purpose |
|---|---|
about-me/writing-rules.md | Universal writing rules |
about-me/business-brain.md | ICP, audience, recent stories, wedge |
projects/social-media-content/brand-brief.md | what_you_sell, primary_cta, recent_proof_story, contrarian_belief, voice_signature |
projects/social-media-content/platform-voice.md | LinkedIn section only — length_range, signature_openings, signature_closings, banned_phrases, voice_notes |
projects/social-media-content/state-social.md | blotato_status (connected / skipped / awaiting-oauth) |
_shared/hook-patterns.md | 11 hook patterns (Step 4) |
Foundation A — lazy-load: read ONLY the LinkedIn section of
platform-voice.md. Don't load the whole file.
Follow the 12-step spec in _shared/draft-skill-spec.md. Platform-specific deltas below.
| Field | LinkedIn value |
|---|---|
| Length | 1200-1900 chars sweet spot (3000 char max) |
| Hook window | First 140 chars (LinkedIn truncates at ~210 before "see more") |
| Image | Optional (text-only often outperforms) |
| Hashtags | 0-3 max, placed at end |
| Line breaks | Preserve aggressively — whitespace is a LinkedIn ranking signal |
| CTA bias | Drive comments (LinkedIn algorithm weights comments > likes) |
| Hook pattern bias | Reframe (#1), Receipts (#9), Stolen Lesson (#11) |
| First-3-words test | Must create curiosity within 3 words (see hook-patterns.md) |
outputs/social-media-content/YYYY-MM-DD-linkedin-<slug>.md
Frontmatter:
---
date: YYYY-MM-DD
platform: linkedin
slug: <kebab-case-3-5-words>
hook_pattern: <pattern-name>
length_chars: <count>
asset_used: null
status: drafted
---
Body = the actual post text, line breaks preserved, ready to copy-paste.
Branch on projects/social-media-content/state-social.md → blotato_status:
connected → Load scheduling-defaults.md, find LinkedIn row, get next-occurrence. Ask:
"Schedule this for [next Tuesday 8:30am ET]? (y / specific time / skip)" On
y, callmcp__claude_ai_Blotato__blotato_create_postwith:text(the draft),accountId(LinkedIn fromblotato_list_accounts), optionalmediaUrls,scheduledFor(ISO 8601).
skipped / awaiting-oauth → Save to outputs/ only. Tell user:
"Blotato isn't connected — copy/paste the draft into LinkedIn manually at [default time per scheduling-defaults.md]."
On Blotato success: update calendar-log row → scheduled, update post frontmatter → status: scheduled, return Blotato post ID.
/grade-post internal pass; don't show drafts under 80The LinkedIn post voice is defined in projects/social-media-content/platform-voice.md (LinkedIn section) + brand-brief.md (voice_signature). Don't reinvent it — load and follow.
See _shared/foundations.md → Foundation B. After delivering the main output + the ⚡ NEXT MOVE block, ask: "What would've made this 10% better?" Log the answer to projects/social-media-content/memory.md as:
<YYYY-MM-DD> | /draft-linkedin | <answer verbatim>
Run recurrence check. If 3+ matches surface, prompt to update the skill + draft a row in skill-improvements.md.
See _shared/foundations.md → Foundation C. Skill output ends with a ⚡ NEXT MOVE block matching the validation regex.
/grade-post after a 10-minute rest/draft-twitter on the same angle⚡ NEXT MOVE: Schedule the LinkedIn draft for Tuesday 8:30am ET.
Why: That's your highest-engagement LinkedIn window per scheduling-defaults + the hook is timely this week.
⚡ NEXT MOVE: Post the LinkedIn draft manually tomorrow at 8:30am ET.
Why: Blotato isn't connected yet + that's still your peak window for comments.
⚡ NEXT MOVE: Reply to every comment on this LinkedIn post within 2 hours of going live tomorrow.
Why: First-2-hours reply velocity is the LinkedIn algo's biggest amplifier signal.