← Back to list
alphaear-logic-visualizer Checked
Create visualize finance logic diagrams (e.g., Draw.io XML) to explain complex finance transmissi…
6.7Overall 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-logic-visualizer" skill by following the instructions at https://skill123.me/install/alphaear-logic-visualizer.
⌨️ Command line install
Run in your terminal — downloads and installs to ~/.claude/skills/.
curl -fsSL https://skill123.me/install/alphaear-logic-visualizer.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 · 10 KBAbout this skill
Overview
Create visualize finance logic diagrams (e.g., Draw.io XML) to explain complex finance transmission chains or finance logic flows.
Source
- Repo: https://github.com/RKiding/Awesome-finance-skills
- Path: skills/alphaear-logic-visualizer
Score breakdown
Trigger
3.5
What-only description (with awkward grammar 'Create visualize'); no When/When-Not; no trigger variants.
Structure
7.3
Small SKILL.md with one reference; but visualizer.py bundles mostly unrelated stock-chart code for a logic-diagram skill, and the Draw.io prompt is duplicated between references/PROMPTS.md and scripts/visualizer_prompt.py; duplicated heading.
Workflow
6.0
Generator pattern is appropriate: rules+template prompt for the agent, deterministic render_drawio_to_html helper to persist output; no validation that generated XML is well-formed before render; init-only test.
Content
7.0
Prompt is concrete and actionable; SKILL.md example is conceptual; mixed languages.
Engineering
7.0
Frontmatter valid; dependency declaration ('None, standard library') contradicts actual imports (pandas, pyecharts, loguru) — render path breaks on a clean environment; referenced paths exist.
Security
10.0
Manifest: no script network egress; generated HTML references the official viewer.diagrams.net CDN (benign); writes only user-facing HTML output files; no env/credential access, no persistence. Capabilities match declared scope despite code bloat. No injection, no secrets.
Agentic Draw.io XML generation with a solid prompt (auto-layout rules, color semantics for positive/negative/neutral) plus an HTML render helper. Problems: dependency claim 'None (Standard Library)' is false — visualizer.py imports pandas/pyecharts/loguru at module level, so even the declared Draw.io path fails without them; visualizer.py is mostly unrelated K-line chart code; prompt duplicated verbatim in references/ and scripts/; duplicated heading.