← Back to list
alphaear-reporter Checked
Plan, write, and edit professional financial reports; generate finance chart configurations. Use …
6.5Overall rating
Installation
🤖 Install via AI
Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.
Install the "alphaear-reporter" skill by following the instructions at https://skill123.me/install/alphaear-reporter.
⌨️ Command line install
Run in your terminal — downloads and installs to ~/.claude/skills/.
curl -fsSL https://skill123.me/install/alphaear-reporter.sh | bash
📦 Download ZIP
Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.
⬇ Download v1.0.0 · 105 KBAbout this skill
Overview
Plan, write, and edit professional financial reports; generate finance chart configurations. Use when condensing finance analysis into a structured output.
Source
- Repo: https://github.com/RKiding/Awesome-finance-skills
- Path: skills/alphaear-reporter
Score breakdown
Trigger
5.0
What plus When clause ('when condensing finance analysis into a structured output'); no When-Not; no trigger variants; English-only.
Structure
6.7
Same monolithic application tree as alphaear-signal-tracker; single useful reference (PROMPTS.md); duplicated '## Capabilities' heading; minimal progressive disclosure over a large code mass.
Workflow
6.4
Three-prompt planner/writer/editor pipeline is a well-chosen generator pattern with concrete output contracts (JSON clusters, [@CITE_KEY] citations, json-chart blocks); ReportUtils provides deterministic bibliography building; visualizer renders K-line/forecast HTML charts; verification broken (test imports missing ReportAgent, second test is a no-op).
Content
7.0
Prompts are concrete and actionable; SKILL.md terse; no runnable example; mixed Chinese/English.
Engineering
6.0
Frontmatter valid; dependency list (sqlite3 only) wildly under-declares actual needs (pyecharts, pandas, loguru, plus the whole bundle); tests/test_reporter.py imports non-existent ReportAgent -> ImportError; visualizer.py and PROMPTS.md paths exist.
Security
8.0
Manifest: bundled code has network egress to newsnow.busiyi.world, s/r.jina.ai, gamma-api.polymarket.com, DashScope/z.ai/OpenRouter/DeepSeek, EastMoney/Yahoo, and HuggingFace model downloads (Kronos) — none declared by a description about report writing; env API keys used as auth to own providers; writes local sqlite db and HTML chart files. No injection, no hardcoded secrets, no persistence. Substantive promise-capability gap -> major deduction; no exfiltration of local data.
Good agentic report pipeline (Cluster->Write Section->Final Assembly prompts) with bibliography/cite-key utilities and pyecharts visualization. But it re-bundles the entire 7,400-line FinAgent codebase (news APIs, search, LLM routing, Kronos predictor) far beyond the report-generation description; duplicated '## Capabilities' heading; declared deps only sqlite3; test imports a non-existent ReportAgent class (only ReportUtils exists).