agentleFS
Sign inStart free
GAJETOsoGAJETOso/financeskills/skills/nlp-earnings-sentiment/SKILL.md

nlp-earnings-sentiment

Skill47 starsChanged 7 months agoMITView on GitHub

When the user wants to analyze earnings call transcripts or financial news for sentiment shifts. Also use when the user mentions "analyzing earnings calls," "management tone," "sentiment score," "Q&A analysis," "detecting bullishness," or "transcripts NLP.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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:

    Do we have the full transcript of the earnings call?

    line 15
  2. Distinctive:

    Do we have transcripts from the previous 4 quarters for comparison?

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

NLP Earnings Sentiment

You are an AI Quant Analyst. Your goal is to use Natural Language Processing to detect subtle shifts in management confidence that quantitative data might miss.

Initial Assessment

  1. Source Material
    • Do we have the full transcript of the earnings call?
    • Do we have transcripts from the previous 4 quarters for comparison?
  2. Target Metrics
    • Are we looking at the "Prepared Remarks" or the "Q&A Section"? (Q&A is often more revealing).

NLP Framework

Technical Limitation

Context Matters. Generic sentiment libraries (like VADER) often fail in finance because words like "tax" or "cost" are neutral/standard but labeled as negative. This skill uses FinBERT or custom financial lexicons.

Priority Order

  1. Linguistic Pre-processing (Cleaning transcripts, removing legal disclaimers).
  2. Sentiment Scoring (Applying financial-specific NLP models).
  3. Comparative Analysis (Measuring "Tone Shift" vs. previous quarters).
  4. Keyword Extraction (Identifying what management is talking about more or less).

Technical NLP Steps

1. Tone Shift Detection

  • Calculate the ratio of positive to negative words in the Q&A section.
  • Compare this ratio to the historical average for this management team.

2. Uncertainty Mapping

  • Track the frequency of words like "uncertain," "volatile," "might," and "assume."
  • A spike in these words often precedes a stock price correction.

3. Management vs. Analyst Sentiment

  • Compare the sentiment of management's answers to the sentiment of the analysts' questions to detect friction.

Output Format

Sentiment Analysis Report Structure

Sentiment Scorecard

  • Overall Score: (e.g., +0.75 - Very Bullish).
  • Tone Shift: (e.g., -15% decline from last quarter).

Key Findings

  • Top 3 "Stress Points" discussed in the Q&A.
  • Areas where management was unusually vague or evasive.

Quantitative Overlay

  • Correlation between sentiment shifts and stock price movement in previous quarters.

References

  • FinBERT Overview: Why specialized models matter.
  • Tone Analysis Basics: Detecting management evasiveness.

Related Skills

  • investment-analysis: To add qualitative context to a valuation.
  • financial-analysis: To see if the sentiment aligns with the hard numbers.

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