メニュー
Golden window workflow — the first 90 minutes after publishing a LinkedIn post. Checklist of actions to maximize reach: replying to comments, engagement routine, sharing strategy. Critical for the algorithm.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Checks whether an author's LinkedIn Article(s) are cited by LLM engines (ChatGPT, Perplexity, Google AI Overview, Claude.ai web). Runs a list of ICP queries, records citations, and computes share-of-voice. Run 4+ weeks after publishing an Article.
Builds a Voice Vocabulary for an author — a dictionary of their characteristic phrases, turns of speech, fillers, metaphors, and contrarian formulas. Used as a humanization layer on top of the DIP. Collected ONLY from raw sources (transcripts, voice input, personally written Telegram posts), NEVER from the author's LinkedIn posts.
Checks a LinkedIn post for factual accuracy. Finds statements compiled from multiple sources and verifies logical integrity. Use after creating a post or whenever facts need to be verified.
Checks content for generic / abstract phrasing, AI language, and repetition from the author's previous posts. Supports two-pass mode — the first pass catches original issues, the second (--second-pass) verifies that the humanizer didn't introduce new generic phrases.
Transparently shows where each key idea in a LinkedIn post comes from. Builds a source map. Lets you exclude specific sources.
Writes a LinkedIn comment on SOMEONE ELSE's post on behalf of an author. Loads the author's DIP, analyzes the post, picks a formula, and checks source grounding. Use when you need to comment on another person's post.
| name | post-publication |
| description | Golden window workflow — the first 90 minutes after publishing a LinkedIn post. Checklist of actions to maximize reach: replying to comments, engagement routine, sharing strategy. Critical for the algorithm. |
Workflow for the first 90 minutes after publishing a LinkedIn post. Maximizing reach through strategic engagement.
$0 — author name (Seva, Kirill)Author DIP:
Knowledge-Base/01-Identity-Profiles/[Author]-DIP.md
Comments-Engine:
Knowledge-Base/06-Comments-Engine/Comments-Engine.md
Algorithm-Intelligence:
Knowledge-Base/02-LinkedIn-Algorithm/Algorithm-Intelligence.md
| Fact | Source |
|---|---|
| The first 60–90 minutes determine the post's reach | Algorithm-Intelligence (360Brew model) |
| Author reply within the first 30 min → +64% total comments, 2.3× views | Richard van der Blom |
| Commenting on 5–10 posts after publication → +55% profile views | Algorithm-Intelligence |
| Dwell time in the first hour → quality signal for the algorithm | 360Brew |
| Author's first comment in the first 5 min → steers the discussion | Comments-Engine |
Publish the pre-prepared first comment (from /create-post output):
Rules:
Teammates leave their own comments:
| Who | Angle | Timing |
|---|---|---|
| Teammate 1 | Their own unique angle (doesn't repeat the author) | T+5–10 min |
| Teammate 2 | Different angle | T+10–15 min |
Rules:
The author comments on 5–10 posts in their niche:
Why: the algorithm sees profile activity → more reach for the post you just published.
Use /reply-to-comments [Author] to generate replies.
| Channel | Action | Timing |
|---|---|---|
| Team (Slack/Telegram) | Share the link + ask for engagement | T+0 |
| Partners | DM with the link (if relevant) | T+30 min |
| Channel | Action | Timing |
|---|---|---|
| Author's Telegram channel | Cross-post with adaptation | T+60 min |
| Email newsletter (if any) | Include in the next issue | Next issue |
## Post-Publication Checklist — [Author]
### Post: [title / slug]
### Published: [date, time]
### Ready materials
**Author's first comment:**
[text]
**Teammate 1 comment ([name]):**
[text]
**Teammate 2 comment ([name]):**
[text]
### Timeline
- [ ] T+0: Post published
- [ ] T+0–5: Author's first comment
- [ ] T+5–15: Teammate comments
- [ ] T+15–30: Engagement routine (5–10 posts)
- [ ] T+30–60: Replies to comments
- [ ] T+60–90: Second engagement round
- [ ] T+90+: Monitor every 2–3 hours
### Engagement targets for commenting
1. [post type / topic] — [angle]
2. [post type / topic] — [angle]
3. [post type / topic] — [angle]
### Distribution
- [ ] Team notified
- [ ] Telegram cross-post (T+60)
- [ ] Partners (if relevant)
/create-post → generates post + first comment + cross-team comments/reply-to-comments → generates comment replies in batch mode/find-comment-targets → recommends posts for the engagement routine/comment-on-post → writes individual comments on identified posts