Card credits

Skill jiahongc/credit-card-skills/.claude/skills/card-credits

Agent Skills suite for researching US credit cards — works with Claude Code, Codex, Cursor, Gemini CLI, and any Agent Skills-compatible tool

Install

npx -y skills add jiahongc/credit-card-skills --skill card-credits

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Return statement credits and cash-like credits for one major-US credit card, including trigger rules, cadence, enrollment requirements, restrictions, and practical usage notes. Use when the user wants the credits picture only.

SKILL.md

2.9 KB, 625 tokens by cl100k_base, as published. Nobody here has run it

Card Credits

Goal

Return the credits view of one exact card variant in compact format.

What Counts as a Credit

A "credit" is a statement credit, cash-back rebate, or complimentary subscription with a concrete dollar value that directly offsets cost. Examples: "$300 travel credit," "$50 hotel credit," "complimentary DashPass membership ($120 value)."

Not credits: enhanced earning rates (e.g., "5x on Lyft"), bonus point multipliers, anniversary point bonuses, or any benefit that only increases points earned per dollar. Those belong in card-rate, not card-credits.

Search Strategy: knowledge-first

Use training knowledge plus one issuer page fetch + one secondary source for credit trigger details. Do NOT spawn a subagent — answer directly.

Workflow

Resolve the card using ../card-identity/SKILL.md. If ambiguous, return a numbered choice list and stop.

Run one Brave Search API call (see search_method in ../card-shared/source-policy.yaml):

curl -sS "https://api.search.brave.com/res/v1/web/search?q=CARD+NAME+credits+benefits&count=10" -H "X-Subscription-Token: $BRAVE_API_KEY"

If $BRAVE_API_KEY is not set, fall back to WebSearch.

Fetch pages — pick the top issuer URL and top 1 secondary URL (prefer thepointsguy.com, then bankrate.com) from the search results. Fetch both in parallel:
```
curl -sS -L "URL" | sed 's/<[^>]*>//g' | tr -s '\n' | head -200
```
Search snippets are too shallow for credits — the full page has the complete credit list.
Combine the fetched page content + search snippets + training knowledge to fill all required sections.
Follow ../card-shared/confidence-rules.md. Flag any detail that may have changed since training data.
Return compact markdown using the card-credits contract in ../card-shared/command-contracts.yaml.
YAML is internal only — do not include it in user-facing output.
Do not show a "Why It Matters" section.

Required Sections

## 💳 Credits Overview
## 🏷️ Credit Details
## 📏 Usage Rules
## 📋 Confidence Notes
## 🔗 Sources — numbered list of URLs fetched, as markdown hyperlinks with short "Site - Topic" labels, e.g. [Chase - Sapphire Preferred](https://...)

Omit ## Card Identity when the match is confident. Use a numbered list for credits with amount, cadence, trigger, and restriction in one compact line per item.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.