Skip to content
SkillModel-led638 tokens in use

Sentiment Analysis

Turn reviews, surveys and CSV feedback into user segments with sentiment scores, themes, jobs to be done and recommended fixes.

28,201 stars on the repository MIT Licensephuryn/pm-skills · pm-market-research/skills/sentiment-analysis
claude plugin marketplace add phuryn/pm-skills claude plugin install pm-market-research@pm-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Sentiment Analysis costs

45tokens idle
638tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure22/25
  • Examples3/15
  • Output5/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity80
  • Maintenance76
  • Community60
  • Maturity32
  • Momentum40

Sentiment Analysis has an agent act as a user researcher and feedback analyst. It reads feedback you provide, such as CSV files, PDFs, survey responses, review data or social listening reports, and groups it into at least three user segments.

For each segment it scores sentiment from -1 to +1, extracts positive themes and pain points, and recommends the highest-impact improvements.

What You Get

  • Segment profiles with size and primary use case
  • A sentiment score from -1 to +1 per segment, with drivers and detractors
  • Top positive themes and top pain points, with direct quotes where available
  • A product-segment fit assessment including churn risk
  • Two to three recommended improvements per segment

Common Use Cases

  • Analyzing app store or product reviews at scale
  • Finding satisfaction patterns in survey open answers
  • Deciding which user segments to prioritize based on feedback

What Makes It Unique

It groups feedback by segment and scores each segment separately, and it asks for sources, small-sample flags and minority views. The survey design skill in the same plugin points to this one for coding open-text answers.

Under The Hood

The skill is a single instruction file with no scripts. It tells the agent to read the feedback files you provide, such as CSV and PDF, and analyze them in the conversation. It does not fetch web pages, call APIs, run commands or write files on its own.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers