← Back to list
alphaear-search Checked
Perform finance web searches and local context searches. Use when the user needs general finance …
7.2Overall 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-search" skill by following the instructions at https://skill123.me/install/alphaear-search.
⌨️ Command line install
Run in your terminal — downloads and installs to ~/.claude/skills/.
curl -fsSL https://skill123.me/install/alphaear-search.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 · 23 KBAbout this skill
Overview
Perform finance web searches and local context searches. Use when the user needs general finance info from the web (Jina/DDG/Baidu) or needs to retrieve finance information from a local document store (RAG).
Source
- Repo: https://github.com/RKiding/Awesome-finance-skills
- Path: skills/alphaear-search
Score breakdown
Trigger
5.5
What + explicit When clause naming the engines (Jina/DDG/Baidu) and local RAG; no When-Not; no trigger variants; English-only description.
Structure
8.0
Small SKILL.md with one prompt reference; scripts/ again bundles shared database_manager plus out-of-scope sentiment_tools and llm/ factory; no progressive disclosure beyond PROMPTS.md.
Workflow
6.8
Tool wrapper with engine abstraction, aggregate search, TTL search cache plus an agentic cache-relevance prompt (good design); thread-safe rate limiting and 429 backoff for Jina; undermined by the logger NameError bug on the main search path; shallow init-only tests.
Content
7.0
Concise capability docs; API-level usage only, no runnable example command; mixed Chinese/English.
Engineering
7.0
Valid frontmatter; declared deps miss agno/loguru/jieba; search_tools.py references logger without importing loguru (runtime NameError); referenced paths exist.
Security
9.0
Manifest: web search GETs to s.jina.ai, r.jina.ai, DuckDuckGo and Baidu (via agno tools) — all declared in the description; env reads JINA_API_KEY/SEARCH_CACHE_TTL; writes local sqlite search cache/news store; bundled llm/ factory (DashScope/z.ai) is dead code not reachable from documented entry points. Capabilities match declared scope. No injection, no hardcoded secrets, no persistence.
Unified web search (Jina/DDG/Baidu) + local RAG with smart cache-relevance prompt. Network destinations are declared in the description (rare among this family). Real bug: scripts/search_tools.py uses logger throughout but never imports loguru — NameError on the search path. Bundles unused sentiment_tools and llm/ factory beyond skill scope; deps under-declared (agno, loguru, jieba).