detect-trends
Detect trending topics across multiple articles by analyzing entity co-occurrence and cross-source mentions. Uses memory search to find recent articles and LLM analysis to identify emerging trends. '
npx skills add majiayu000/claude-skill-registry --skill detect-trends --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Detect Trends Detect trending topics across multiple analyzed articles. ## When to Use Use this skill when you need to: - Identify topics mentioned across multiple sources - Detect emerging trends in AI news - Track topic momentum over time - Prioritize topics for digest composition ## Instructions ### Step 1: Search for Recent Analyses Use `memory/search` to find recent article analyses: - namespace: "news/analyses" - query: "recent AI news analysis" - limit: 100 (or appropriate window) This returns articles with their extracted entities and categories. ### Step 2: Extract Entity Mentions From the search results, collect all entities and track: - Which articles mention each entity - How many times each entity appears - Which sources mention each entity **Entity normalization:** - Lowercase and strip whitespace - Handle variations (e.g., "GPT-4" = "GPT4" = "gpt-4") ### Step 3: Calculate Trend Scores For each entity, calculate a trend score: **Score formula:** ``` score = mention_count * source_diversity_bonus source_diversity_bonus = 1.0 + (unique_sources - 1) * 0.2 ``` **Thresholds for trend qualification:** - Minimum 2 mentions - Minimum 2 different articles ### Step 4: Analyze
- When to Use
- Instructions
- Step 1: Search for Recent Analyses
- Step 2: Extract Entity Mentions
- Step 3: Calculate Trend Scores
- Step 4: Analyze with LLM
- Step 5: Store Trends in Memory
- Step 6: Link Trends to Articles
- Step 7: Return Results
- Tool Usage Guidance
- memory/search
- usellm
- memory/add
- memory/link
What does the detect-trends skill do?
Detect trending topics across multiple articles by analyzing entity co-occurrence and cross-source mentions. Uses memory search to find recent articles and LLM analysis to identify emerging trends. '
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill detect-trends --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.