Earnings forecast

Skill kuntal-r-d/my-skills/skills/earnings-forecast

Install

npx -y skills add kuntal-r-d/my-skills --skill earnings-forecast

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Projects future earnings for a DSE stock from historical EPS/revenue trends, seasonality and growth drivers, with an earnings-quality check and an explicit confidence band. Use when the user asks to forecast/project earnings or EPS, next-quarter or next-year estimate, earnings growth outlook, earnings quality, or "what will GP earn" on the Dhaka Stock Exchange.

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.7 KB, as published. Nobody here has run it

Earnings Forecast

Prompt-first, pure-prompt skill. No script — project from the supplied earnings history. Always state assumptions and a confidence band; never present a point estimate as certain.

Role & objective

Project near-term earnings (next quarter / next year) with a growth rate, an earnings-quality read, and an explicit uncertainty band. Output a normalised score for the earnings outlook.

When to use

"Forecast GP's EPS", "next-year earnings estimate", "earnings growth outlook", "is the earnings quality good?". Feed the growth view into fundamental-analysis.

Inputs you need

fundamentals — eps_history[] (≥12 quarters ideal), revenue_history[], eps_ttm, margins, and optional analyst estimates/earnings_surprise history.

Method (follow in order)

Historical trend — growth rate from EPS history; detect seasonality and cyclicality.
Projection — simple trend/exponential-smoothing projection of next quarter & year; widen the band when history is short or volatile.
Earnings quality — accruals vs cash earnings, one-time items, core vs reported EPS.
Growth drivers — revenue growth, margin trend, operating leverage.
Estimate context — consensus, revision trend, surprise/beat history if supplied.

Scoring rubric

score = clamp(projected growth / 0.15, −1, 1) (≈15% growth → full positive), adjusted down for poor earnings quality. Rating: ≥0.5 strong_growth · ≥0.15 growth · −0.15..0.15 flat · ≤−0.15 declining. Confidence is low by default (forecasting is uncertain): higher with ≥12 quarters, stable margins, and consistent beats; lower with short/volatile history (state the band).

Output (emit this Thinking Card)

{ "skill": "earnings-forecast", "ticker": "..", "mode": "investment", "as_of": "..",
  "score": 0.0, "confidence": 0.0, "rating": "strong_growth|growth|flat|declining",
  "key_metrics": { "ttm_eps": 0, "next_year_eps": 0, "growth_rate": 0.0,
    "band_low": 0, "band_high": 0, "earnings_quality": 0.0 },
  "reasoning": ["assumptions + drivers"], "flags": ["short_history?", "low_earnings_quality?"],
  "disclaimer": "Educational analysis only. Not financial advice. Forecasts are uncertain." }

DSE pitfalls

DSE disclosure is often annual/semi-annual and lumpy — short history → wide band, low confidence.
One-off gains (asset sales, revaluations) inflate reported EPS — strip them for core earnings.
Don't extrapolate a single strong quarter; weight the trend and seasonality.

Optional precision helper

No bundled script — pure-prompt skill. Use fundamental-analysis for the valuation that consumes this growth estimate.

Worked example

8 quarters, EPS CAGR ~16%, stable margins, 2 recent beats, clean accruals → next-year EPS +16% (band ±5%) → score ≈ +1.0 capped → strong_growth, confidence ≈ 0.6 (state the band).

References

See fundamental-analysis/references/VALUATION.md for how growth feeds fair value. Output is educational analysis only, never financial advice.