Skill

trend-analysis

Identify temporal trends across a text corpus — rising/falling topics, entities, or keywords over time. Use after topic-analysis or ner-extraction when the user wants "what am I talking about more / less than before" or "when did X first show up".

npx claudepluginhub danielrosehill/claude-code-plugins --plugin text-corpus-analysis

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Temporal shape of topics, entities, and keywords.

SKILL.md

Similar Skills

ui-ux-pro-max

72.7k

Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.

ui-ux-pro-max

context7-mcp

51.8k

Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.

context7-plugin

seo-cannibalization-detector

36.5k

Analyzes multiple pages for keyword overlap, SEO cannibalization risks, and content duplication. Suggests differentiation, consolidation, and resolution strategies when reviewing similar content.

antigravity-bundle-seo-specialist

Stats

Stars0

Forks0

Last CommitApr 23, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Trend Analysis

Temporal shape of topics, entities, and keywords.

Prereqs

Documents must have timestamps (creation date, captured-at, published-at).

Feed comes from topic-analysis, ner-extraction, or word-frequency.

Procedure

Choose a bucket: day / week / month / quarter / year. Rule of thumb: aim for ≥30 documents per bucket. If the corpus is sparse, go wider.

Count per bucket: mentions, topic-shares, or document-counts per bucket.

Normalize: raw counts mislead when corpus volume varies over time. Use share of bucket (percent) rather than absolute count.

Detect movement:

Rising: terms whose share in the latest 25% of buckets exceeds their share in the first 75% by ≥2x and passes a minimum-count floor.
Falling: inverse.
New: first appears in the latest N buckets.
Dormant: not seen in the latest N buckets.

Smoothing: apply a 3-bucket rolling mean before plotting. Raw weekly/monthly counts are noisy.

Output:

trends.csv: term, bucket, count, share, smoothed_share
trends-summary.md: top 10 rising, top 10 falling, top 10 new.
Optional line plot.

Pitfalls

Corpus bias: if voice-note volume tripled last quarter, everything "rose". Always normalize.

Small numbers: a term going from 1 mention to 3 is not a trend. Set a minimum bucket-count floor (e.g. ≥5).

Seasonality: if the data spans years, separate seasonal (yearly) effects from secular trends before claiming a movement.

No LLM needed

This is a pure classical-NLP / stats task. Do not propose a cloud LLM.

Trend Analysis

Temporal shape of topics, entities, and keywords.

Prereqs

Documents must have timestamps (creation date, captured-at, published-at).
Feed comes from topic-analysis, ner-extraction, or word-frequency.

Procedure

Choose a bucket: day / week / month / quarter / year. Rule of thumb: aim for ≥30 documents per bucket. If the corpus is sparse, go wider.
Count per bucket: mentions, topic-shares, or document-counts per bucket.
Normalize: raw counts mislead when corpus volume varies over time. Use share of bucket (percent) rather than absolute count.
Detect movement:
- Rising: terms whose share in the latest 25% of buckets exceeds their share in the first 75% by ≥2x and passes a minimum-count floor.
- Falling: inverse.
- New: first appears in the latest N buckets.
- Dormant: not seen in the latest N buckets.
Smoothing: apply a 3-bucket rolling mean before plotting. Raw weekly/monthly counts are noisy.
Output:
- trends.csv: term, bucket, count, share, smoothed_share
- trends-summary.md: top 10 rising, top 10 falling, top 10 new.
- Optional line plot.

Pitfalls

Corpus bias: if voice-note volume tripled last quarter, everything "rose". Always normalize.
Small numbers: a term going from 1 mention to 3 is not a trend. Set a minimum bucket-count floor (e.g. ≥5).
Seasonality: if the data spans years, separate seasonal (yearly) effects from secular trends before claiming a movement.

No LLM needed

This is a pure classical-NLP / stats task. Do not propose a cloud LLM.