luca-assistant

Credit card rewards optimizer — query 150+ cards, compare benefits, track portfolio, check 5/24 status, and get the best sign-up bonuses (撸卡助手)

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "luca-assistant" with this command: npx skills add troyt-666/luca-assistant

Luca Assistant (撸卡助手)

A credit card rewards optimization tool. Query 150+ US credit cards, compare benefits, track your portfolio, and find the best sign-up bonuses.

When to use this skill

Trigger this skill when the user asks about:

  • Credit card recommendations or comparisons
  • Sign-up bonuses (SUBs) or welcome offers
  • Chase 5/24 status or bank application rules
  • Adding/removing cards in their portfolio
  • Card benefits, category multipliers, or annual credits

Setup

Check if already installed

Before running setup, check whether Luca is already available:

export PATH="$HOME/.local/bin:$PATH"
command -v luca-mcp && luca-mcp --help

If luca-mcp responds, skip to How to use. Otherwise run setup below.

First-run setup

export PATH="$HOME/.local/bin:$PATH"
bash {baseDir}/scripts/setup.sh

This installs luca-assistant from PyPI via uv and seeds the database (~150 cards from Offer Optimist).

PATH note: uv tool install places binaries in ~/.local/bin. If luca-mcp is not found after setup, ensure ~/.local/bin is on PATH (export PATH="$HOME/.local/bin:$PATH").

Verify setup

luca-mcp --help        # should print MCP server usage
luca cards | head -5   # should list cards from the database

How to use

Luca is an MCP tool server. The database lives at ~/.local/share/luca/luca.db.

If Luca is already configured as an MCP server in the agent's environment, call luca_* tools directly. Otherwise, call tools via the bundled script:

export PATH="$HOME/.local/bin:$PATH"
bash {baseDir}/scripts/mcp_call.sh <tool_name> '<json_args>'

Available MCP tools

Card queries:

  • luca_query_card_details(card_name, bank?) — look up a card's benefits, current offers, and fees
  • luca_find_highest_offers(bank?, min_bonus_usd?, is_business?, limit?) — best current sign-up bonuses
  • luca_compare_card_benefits(card_names) — side-by-side benefit comparison
  • luca_get_bank_rules(bank) — issuer application rules (Chase 5/24, Amex lifetime language, Citi 8/65, etc.)

Card enrichment:

  • luca_update_card_benefit(card_name, category, multiplier, points_type, notes?, bank?, annual_credit?, credit_category?) — add or update a card's category multiplier or credit
  • luca_import_cards(source?, force?) — refresh data from 'offer-optimist' (cards + SUBs) or 'cfpb' (APRs + fees)

Portfolio tracking:

  • luca_get_user_portfolio() — user's open and closed cards
  • luca_check_chase_524_status() — 5/24 count and remaining slots
  • luca_add_user_card(card_name, opened_date, bank?, credit_limit?, bonus_earned?, bonus_met_date?, notes?) — add a card to portfolio
  • luca_close_user_card(card_name, closed_date, bank?) — mark a card as closed

Examples

# Look up Chase Sapphire Preferred
bash {baseDir}/scripts/mcp_call.sh luca_query_card_details '{"card_name":"Chase Sapphire Preferred"}'

# Find top 5 offers worth at least $500
bash {baseDir}/scripts/mcp_call.sh luca_find_highest_offers '{"min_bonus_usd":500,"limit":5}'

# Compare two cards
bash {baseDir}/scripts/mcp_call.sh luca_compare_card_benefits '{"card_names":["Amex Gold","Chase Sapphire Preferred"]}'

# Check Chase 5/24 status
bash {baseDir}/scripts/mcp_call.sh luca_check_chase_524_status '{}'

Enrichment workflow

When luca_query_card_details returns a multiplier_hint, the card has missing category multiplier data. To fill the gap:

  1. Web search for the card on site:doctorofcredit.com OR site:thepointsguy.com
  2. Find the earning rates (e.g., "3x on dining, 2x on travel")
  3. Call luca_update_card_benefit for each category to persist the data

Optional: USCardForum integration

For community data points from USCardForum (美卡论坛), install the companion nitan skill. It provides discourse_search, discourse_read_topic, discourse_list_hot_topics, and more.

Guidelines

  • All card data comes from the database — never fabricate card details
  • If a card isn't found, tell the user rather than guessing
  • Respond in the user's language (Chinese or English)
  • Use luca_import_cards to refresh data if it seems stale

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

Huo15 Openclaw Enhance

火一五·克劳德·龙虾增强插件 v5.7.8 — 全面适配 openclaw 2026.4.24:peerDep ^4.24 + build/compat 同步到 4.24 + 14 处 api.on 全部去掉 as any 改成 typed hook(hookName 联合类型 + handler 自动推断 Pl...

Registry SourceRecently Updated
General

Content Trend Analyzer

Aggregates and analyzes content trends across platforms to identify hot topics, user intent, content gaps, and generates data-driven article outlines.

Registry SourceRecently Updated
General

Prompt Debugger

Debug prompts that produce unexpected AI outputs — diagnose failure modes, identify ambiguity and conflicting instructions, test variations, compare model re...

Registry SourceRecently Updated
General

Indie Maker News

独行者 Daily - 变现雷达。读对一条新闻,少走一年弯路。每天5分钟,给创业者装上商业雷达。聚焦一人公司、副业、创业变现资讯,智能分类,行动导向。用户下载即能用,无需本地部署!

Registry SourceRecently Updated