メニュー
Recommends what to write next. Analyzes the author's Topic Backlog, cluster balance, trends, and the algorithm. Prioritizes topics from Inbox into Prioritized. Helps avoid sameness and ride a trend.
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 | suggest-next-post |
| description | Recommends what to write next. Analyzes the author's Topic Backlog, cluster balance, trends, and the algorithm. Prioritizes topics from Inbox into Prioritized. Helps avoid sameness and ride a trend. |
| disable-model-invocation | true |
| argument-hint | ["Author"] |
| allowed-tools | Read, Grep, Glob |
What to write next? Prioritize topics from the Topic Backlog with cluster balance, trends, and the algorithm in mind.
$0 — author name (Seva, Kirill)Author DIP:
Knowledge-Base/01-Identity-Profiles/[Author]-DIP.md
→ Expertise Clusters, cluster distribution, Viral Angles
Topic Backlog:
Posted/[Author]/Topic-Backlog.md
→ Inbox topics, Prioritized, Done
Posted (recent posts):
Posted/[Author]/
→ Last 10–15 posts for cluster and format analysis
Algorithm-Intelligence:
Knowledge-Base/02-LinkedIn-Algorithm/Algorithm-Intelligence.md
→ Timing, formats, engagement rules
Current-Trends:
Knowledge-Base/03-Viral-Trends/Current-Trends.md
→ What's trending now
Format-Performance-Data:
Knowledge-Base/02-LinkedIn-Algorithm/Format-Performance-Data.md
→ Which formats perform better
Read the author's last 10–15 posts. Extract cluster: from each frontmatter.
Compare actual distribution against the DIP target:
Example:
| Cluster | Target % | Actual % | Status |
|---|---|---|---|
| AI-Native Teams | 30% | 45% | OVER — reduce |
| Perf Marketing + Product | 30% | 20% | UNDER — add |
| Founder Journey | 20% | 25% | OK |
| Industry Insights | 20% | 10% | UNDER — add |
Last 5 posts → which formats were used? If 3+ in a row in the same format → recommend a different one.
When was the last post? If >3 days ago — urgent. Optimal frequency: 3–5 posts per week.
Read the author's Topic-Backlog.md:
For each Inbox topic, score:
| Criterion | Weight | How to score |
|---|---|---|
| Cluster fit | 30% | Needed cluster per balance → +3, over → −2 |
| Trend match | 25% | Matches Current-Trends → +3 |
| Unique angle | 20% | Has contrarian / fresh perspective → +2 |
| Source readiness | 15% | Raw source available (transcript, Telegram) → +2 |
| Urgency | 10% | Timely topic (event, news) → +3 |
## What to write next — [Author]
### Date: [today]
### Last post: [date, topic]
### Cluster balance: [OK / skew toward X]
---
### Top 3 recommendations
#### 1. [Topic] ⭐ PRIORITY
**Cluster:** [cluster] — [why this cluster is needed now]
**Format:** [recommended format]
**Angle:** [from DIP Viral Angles]
**Source:** [which raw source to use]
**Trend match:** [match with Current-Trends]
**Score:** [N]/10
#### 2. [Topic]
[same fields]
#### 3. [Topic]
[same fields]
---
### Topics for Inbox → Prioritized
| Topic | Score | Cluster | Recommendation |
|-------|-------|---------|----------------|
| ... | N/10 | ... | Prioritized / Keep in Inbox / Remove |
### Cluster gap
**Need more posts on:** [cluster] — [specific topics from the DIP]
**Can wait:** [cluster] — [already well covered]
Suggest topics from:
/scan-telegram)