AlphaEar Predictor
Forecasts finance market time series using the Kronos model with news adjustments.
Test report
- Verdict
- Tested · Didn't pass
- Tested
- Jul 13, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 4abc5ec
The skill's own Example Usage is broken: the import is wrong (docs say scripts.utils.kronos_predictor but the file is scripts/kronos_predictor.py) and it calls a nonexistent predictor.predict(ticker, horizon) — the class only exposes get_base_forecast(df, lookback, pred_len, news_text), which takes a pandas OHLC DataFrame, not a ticker string. This confirms a prior SkillProof finding. Verbatim install (clone + cp) and YAML frontmatter are fine, but running the skill also needs uninstalled heavy deps (sentence-transformers, scikit-learn, loguru) plus a Kronos base-model + embedder download. Any forecast output is a code-correctness artifact only, not investment guidance.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 4/5
- Triggers reliably 4/5
- Output vs. baseline 2/10
- Docs & honesty 2/5
What AlphaEar Predictor does
Market prediction skill using Kronos. Use when user needs finance market time-series forecasting or news-aware finance market adjustments.
How to install AlphaEar Predictor
git clone https://github.com/RKiding/Awesome-finance-skills
cd Awesome-finance-skills
mkdir -p ~/.claude/skills
cp -r skills/alphaear-predictor ~/.claude/skills/alphaear-predictor
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger AlphaEar Predictor
-
/alphaear-predictorForecasts finance market time series using the Kronos model with news adjustments.
It also activates on plain-language prompts like these:
-
Forecast this stock's price movement using Kronos -
Predict market direction adjusted for recent news -
Run a time-series forecast on this asset's price
Frequently asked questions
- Is the AlphaEar Predictor skill free?
- Yes. The skill itself is free from RKiding/Awesome-finance-skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does AlphaEar Predictor work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 13, 2026. Verdict: Tested · Didn't pass. The skill's own Example Usage is broken: the import is wrong (docs say scripts.utils.kronos_predictor but the file is scripts/kronos_predictor.py) and it calls a nonexistent predictor.predict(ticker, horizon) — the class only exposes get_base_forecast(df, lookback, pred_len, news_text), which takes a pandas OHLC DataFrame, not a ticker string. This confirms a prior SkillProof finding. Verbatim install (clone + cp) and YAML frontmatter are fine, but running the skill also needs uninstalled heavy deps (sentence-transformers, scikit-learn, loguru) plus a Kronos base-model + embedder download. Any forecast output is a code-correctness artifact only, not investment guidance.
- How do I install AlphaEar Predictor?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use AlphaEar Predictor with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.