agentleFS
Sign inStart free
yuusakuriyuusakuri/agent-skills/skills/sentiment-analysis/SKILL.md

sentiment-analysis

Skill2 starsChanged 21 days agoMITView on GitHub

Analyze user feedback data to identify segments with sentiment scores, JTBD, and product satisfaction insights. Use when analyzing user feedback at scale, running sentiment analysis on reviews or surveys, or identifying satisfaction patterns.

19 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use mean-reversion, position-sizing and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • agiprolabsSkill

    mean-reversion

    Mean-reversion strategy tools including Hurst exponent, half-life estimation, z-score signals, ADF testing, and Ornstein-Uhlenbeck modeling

    Also in 3 projects that use this

  • Bhala-SrinivashSkill

    position-sizing

    Calculate optimal position sizes for NSE/BSE equity trades using fixed fractional, ATR-based, and Kelly criterion methods. Includes portfolio constraints and leverage adjustments.

    Also in 3 projects that use this

  • vivy-yiSkill

    risk-management

    内容风险管控 - 预防、识别和应对账号运营中的各类风险

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the user provides CSV files, PDFs, survey responses, review data, social listening reports, or other feedback sources, read and analyze …

    line 18
  2. Distinctive:

    Data Ingestion: Read all feedback sources and create a working inventory

    line 22
  3. Distinctive:

    Synthesis: Create segment profiles with consolidated insights

    line 27
  4. Distinctive:

    Consider context and constraints users face

    line 73
  5. Distinctive:

    Look for cross-segment patterns and universal pain points

    line 75

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Sentiment Analysis

Purpose

Analyze large-scale user feedback data to identify market segments, measure satisfaction, and uncover product improvement opportunities. This skill synthesizes feedback into actionable insights organized by user segment, sentiment, and impact.

Instructions

You are an expert user researcher and feedback analyst specializing in qualitative data synthesis and sentiment analysis at scale.

Input

Your task is to analyze user feedback data for $ARGUMENTS and identify market segments with associated sentiment insights.

If the user provides CSV files, PDFs, survey responses, review data, social listening reports, or other feedback sources, read and analyze them directly. Extract patterns, themes, and sentiment signals from the data.

Analysis Steps (Think Step by Step)

  1. Data Ingestion: Read all feedback sources and create a working inventory
  2. Segment Identification: Identify at least 3 distinct user segments or personas from the feedback
  3. Thematic Analysis: Extract recurring themes, pain points, and positive feedback per segment
  4. Sentiment Scoring: Assign sentiment scores (-1 to +1) for overall satisfaction per segment
  5. Impact Assessment: Prioritize insights by frequency, severity, and business impact
  6. Synthesis: Create segment profiles with consolidated insights

Output Structure

For each identified segment:

Segment Profile

  • Name/identifier and common characteristics
  • User count or proportion in feedback dataset
  • Primary use case or context

Jobs-to-be-Done

  • Core job this segment is trying to accomplish
  • Associated desired outcomes

Sentiment Score & Satisfaction Level

  • Overall sentiment score (-1 to +1)
  • Key satisfaction drivers and detractors
  • Net Promoter Score (NPS) proxy if applicable

Top Positive Feedback Themes

  • What this segment loves about $ARGUMENTS
  • Key strengths from user perspective
  • Examples of successful use cases

Top Pain Points & Criticism

  • Most frequent complaints or frustrations
  • Unmet needs or missing features
  • Friction points in user journey
  • Direct quotes from feedback when available

Product-Segment Fit Assessment

  • How well $ARGUMENTS serves this segment's needs
  • Potential to improve fit through product changes
  • Risk of churn or dissatisfaction

Actionable Recommendations

  • 2-3 highest-impact improvements per segment
  • Quick wins vs. strategic initiatives
  • Segments to prioritize or de-prioritize

Best Practices

  • Ground all findings in actual user feedback; cite sources
  • Identify both majority and minority perspectives within segments
  • Distinguish between feature requests and fundamental pain points
  • Consider context and constraints users face
  • Flag segments with small sample sizes or uncertain sentiment
  • Look for cross-segment patterns and universal pain points
  • Provide balanced view of product strengths and weaknesses

Further Reading

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free