alphaear-search — Claude Code skill: finance search and local RAG
A skill that runs finance searches on the web through Jina, DDG or Baidu, and pulls results from a local news store. Useful when the agent needs fresh data or your own documents.
npx skills add RKiding/Awesome-finance-skills --skill alphaear-search -a claude-codeWhat alphaear-search does
The skill gives an agent two ways to gather finance information. Web search lives in scripts/search_tools.py: search(query, engine, max_results) works with Jina, DuckDuckGo, Baidu and a local engine, while aggregate_search(query) merges hits from several engines at once. Local RAG runs through scripts/hybrid_search.py or the same SearchTools with engine='local', and it queries the daily_news database.
To avoid repeating the same request, references/PROMPTS.md ships a Search Cache Relevance Prompt. The agent reads the cache first and decides whether the stored result still fits. Both the cache and the local news store are handled by scripts/database_manager.py.
You need duckduckgo-search and requests installed. Jina and Baidu calls require an API key you supply yourself, so check that access before pointing the skill at them.
What it helps with
- pull fresh finance news for a query
- merge results from several search engines
- query a local news database instead of the web
- reuse earlier search results through the cache
- get finance facts without browsing sites by hand
Example prompts for the agent
- search the web for the latest Fed rate news with alphaear-search
- look through the local daily_news database for this company
- aggregate jina and ddg results for the earnings query
How to install alphaear-search
1Skills CLI (Vercel)
npx skills add RKiding/Awesome-finance-skills --skill alphaear-search -a claude-code2Manually: put the files in place
~/.claude/skills/alphaear-search/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/alphaear-search/
1Skills CLI (Vercel)
npx skills add RKiding/Awesome-finance-skills --skill alphaear-search -a codex2Manually: put the files in place
.agents/skills/alphaear-search/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add RKiding/Awesome-finance-skills --skill alphaear-search -a cursor2Manually: put the files in place
.cursor/skills/alphaear-search/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install RKiding/Awesome-finance-skills alphaear-search2Manually: put the files in place
.github/skills/alphaear-search/SKILL.md1Skills CLI (Vercel)
npx skills add RKiding/Awesome-finance-skills --skill alphaear-search -a gemini-cli2Platform CLI
gemini skills install https://github.com/RKiding/Awesome-finance-skills --path skills/alphaear-searchManually: put the files in place
.devin/skills/alphaear-search/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add RKiding/Awesome-finance-skills --skill alphaear-search -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about alphaear-search
How do I install alphaear-search in Claude?
Run npx skills add RKiding/Awesome-finance-skills --skill alphaear-search -a claude-code. The skill lands in ~/.claude/skills/alphaear-search/SKILL.md.
What does alphaear-search do?
It searches the web for finance information via Jina, DuckDuckGo or Baidu and can retrieve data from a local daily_news store. It also caches queries so the same search is not repeated.
What dependencies does the skill need?
The duckduckgo-search and requests packages, plus scripts/database_manager.py for the cache and local news. Jina and Baidu engines need an API key.
Source text
SKILL.md · Apache-2.0
---
name: alphaear-search
description: 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).
---
# AlphaEar Search Skill
## Overview
Unified search capabilities: web search (Jina/DDG/Baidu) and local RAG search.
## Capabilities
### 1. Web Search
Use `scripts/search_tools.py` via `SearchTools`.
- **Search**: `search(query, engine, max_results)`
- Engines: `jina`, `ddg`, `baidu`, `local`.
- Returns: JSON string (summary) or List[Dict] (via `search_list`).
- **Smart Cache (Agentic)**: If you want to avoid redundant searches, use the **Search Cache Relevance Prompt** in `references/PROMPTS.md`. Read the cache first and decide if it's usable.
- **Aggregate**: `aggregate_search(query)`
- Combines results from multiple engines.
### 2. Local RAG
Use `scripts/hybrid_search.py` or `SearchTools` with `engine='local'`.
- **Search**: Searches local `daily_news` database.
## Dependencies
- `duckduckgo-search`, `requests`
- `scripts/database_manager.py` (search cache & local news)
© RKiding · Apache-2.0 · RKiding/Awesome-finance-skills
