跳到主要内容
知仓学习社ZHICANG

rewards-optimizer

Figure out the best card or payment route for a purchase (or your everyday spending) to maximize cashback/points — without overspending or drowning …

不碰外部(只输出文字)无严重或高危命中mohitagw15856/pm-claude-skills

它会碰到什么

扫了多少1 个文本文件,4 KB
它会碰到什么不碰外部(只输出文字)
命中总数0 处
命中统计严重 0 · 高 0 · 中 0 · 低 0

这一栏是扫描器报的事实,不是结论。命中多不等于有毒(安全工具、规则库、示例脚本本来就会包含危险写法),命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系,需要你自己看。

技能内容

Rewards Optimizer

Reward programs are designed to be confusing so most value goes unclaimed. This cuts through it: given the cards and programs you actually have, it tells you the best one to use for a specific purchase or builds a simple by-category cheat-sheet for everyday spending — while keeping the golden rule front and center: rewards are only worth it if you pay in full and don't spend more to earn them.

What This Skill Produces

  • The best route for this spend — which of your cards/programs earns most for the specific purchase or category
  • An everyday cheat-sheet — a simple "use card X for groceries, Y for dining, Z for everything else" map
  • Redemption tips — how to get the most value when cashing in (transfer partners, statement credit vs travel, avoiding devaluation)
  • Guardrails — pay-in-full always, don't chase sign-ups into debt, keep it simple enough to actually follow
  • A "worth it?" check — when an annual fee or a new card does or doesn't pay off for your spending

Required Inputs

Ask for these if not provided:

  • Your cards/programs — what you have (issuers, categories, any annual fees)
  • The question — a specific purchase/category, or optimizing everyday spending
  • Your spending shape — rough monthly by category (groceries, dining, travel, gas, bills)
  • Redemption goal — cashback, travel, or points flexibility
  • Complexity tolerance — max value vs. keep-it-simple

Framework: Value First, Never Into Debt

  1. Match the card to the category. Use whichever card earns the highest rate for that specific spend — bonus categories are where the value is.
  2. Keep the everyday map simple. A two-or-three-card routine most people can actually remember beats a 10-card optimization nobody follows.
  3. Redeem smartly. Points aren't all worth the same — flag high-value redemptions and watch for devaluation; sometimes plain cashback wins.
  4. Judge fees honestly. An annual fee only pays off if your spending in its categories clears the fee in rewards — do that math.
  5. Guardrail hard. Rewards are worthless if you carry a balance or overspend to earn them — pay in full, don't chase. Say this plainly.

Output Format

Rewards: [specific spend / everyday] · cards: [yours]

For this purchase: use [card] — earns [rate/value] because [category bonus].

Everyday cheat-sheet

| Category | Best card | Why |

|---|---|---|

| Groceries | [card] | [rate] |

| Dining | [card] | [rate] |

| Everything else | [card] | [base rate] |

Redeem for max value: [best redemption path + watch-outs].

Fee check: [card] fee pays off if you spend ~[x] in [category].

> Not financial advice. Only worth it if you pay the balance in full every month and don't spend more to earn rewards.

Quality Checks

  • [ ] Recommends the highest-earning card for the actual category
  • [ ] Everyday cheat-sheet is simple enough to follow
  • [ ] Includes redemption-value guidance, not just earning
  • [ ] Does honest annual-fee math
  • [ ] Leads with pay-in-full / don't-overspend guardrails
  • [ ] Uses only the cards/programs the person has

Anti-Patterns

  • Optimizing into complexity nobody will follow.
  • Ignoring the pay-in-full rule — interest erases all rewards.
  • Encouraging spend to hit bonuses.
  • Treating all points as equal value.
  • Recommending a fee card without the break-even math.

Example Trigger Phrases

  • "Which card should I use for booking a flight?"
  • "Help me maximize my cashback across my cards."
  • "Best card for groceries and dining from what I have?"
  • "Is this card's annual fee worth it for my spending?"
  • "Set me up a simple system for which card to use where."

想直接用这个技能?

本站把开放许可(MIT / Apache 等)的技能按仓库打包整理到网盘,点一下转存到你自己的网盘,不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接,不打包。

同名技能的其他版本

有 3 个不同仓库或目录里都有叫 rewards-optimizer 的技能。它们内容并不相同,别混用: