Use your own card files to compare which card fits a purchase, review unused or expiring credits, and plan travel redemptions with points or miles. Recommendations include values and next steps, while stale or unverified information is flagged.
Tracks the principal's credit cards, their perks and annual credits, and points and miles balances across bank, airline and hotel programs, then turns them into which-card answers, unused-credit sweeps and points redemptions through transfer partners, all from the principal's own card data files. USE WHEN credit card benefits, card perks, which card should I use, annual credits, unused credits, expiring credits, my points, my miles, airline miles, hotel points, update my points balance, redeem points, transfer partners, plan a trip with points, refresh card perks. NOT FOR spending totals, expense tracking or bookkeeping, revenue or payments data, or moving money.
Run score Not tested
See how to installCardBenefits uses your card data files to compare card perks, annual fees, credits, and points or miles balances. It can help choose a card for a purchase or airfare, identify unused or soon-to-expire credits, and plan trips around available points and transfer partners. Recommendations include estimated dollar or points values and next steps. Information that is more than 90 days old or marked unverified is flagged.
Use it when you have multiple cards and want to compare benefits for a particular purchase, check credits you may have left unused, or consider travel options based on your points balance. It does not handle spending totals, expense tracking, bookkeeping, or payments.
The skill reads your own card data files. Points balances are updated from your report or a statement, and card benefits need web verification. It plans transfers, benefit activations, and bookings, but does not move money, activate benefits, or make reservations.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI checked the SKILL.md for operations that need care and for setup requirements. The score comes only from actually running the skill (hands-on test).
Not counted in the score. Rated by AI (OpenAI Codex) as of Oct 28, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Single source of truth for the principal's credit cards, their perks and points balances, and the planning layer that turns points into trips.
| Intent | Trigger | File |
|---|---|---|
| ShowBenefits | "what perks do I have", "card benefits", "which card for X" | Intents/ShowBenefits.md |
| UpdatePoints | "I have N points", "update my points", "new balance" | Intents/UpdatePoints.md |
| PlanRedemption | "plan a trip with points", "use my points for", "what can N points get" | Intents/PlanRedemption.md |
| RefreshPerks | "refresh perks", "did the benefits change", "verify card benefits" | Intents/RefreshPerks.md |
| CreditSweep | "unused credits", "credits on the table", "expiring credits", "monthly credit check" | Intents/CreditSweep.md |
| File | Read when |
|---|---|
Setup.md | first-time setup of the four data files, with an invented worked example of each and a proof command |
This skill is procedure only. All personal financial data (card inventory, balances, credits, cross-card strategy, standing travel preferences) lives in the USER tree at <configRoot>/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/CardBenefits/ and is read by path on every invocation (configRoot is $CLAUDE_CONFIG_DIR when set, else ~/.claude). First-time setup, a worked example of each file and a proof command: Setup.md. When Cards.md is missing, stop and point the principal at Setup.md; never answer perks from model memory.
Data files:
Cards.md — card inventory (issuer, product variant, annual fee, points program) plus the full perk and credit list per card, each with a last-verified datePoints.md — current points balances, redemption valuations, transfer partners, standing travel preferences (including the default travel party)Playbook.md — cross-card strategy: category→card matrix, stacking plays, lounge and status map, combined transfer matrix, sweet spots tied to current balancesCredits.md — unified credit ledger and deadline calendar across all cardsAccount numbers never go in these files. Reference an account by its label in LIFEOS/USER/FINANCES/ACCOUNTS.md when you keep one.
last-verified in Cards.md is stale (>90 days) or marked UNVERIFIED gets RefreshPerks first or an inline flag.Points.md is old, say so and ask; a stale number is never presented as current.Cards.md records which product each card is, resolved from the issuer's dashboard or the product named on a statement; quote the perk set Cards.md names, never one inferred from a label.Example 1: Vacation planning
User: "We have 120K bank points — what could a trip to Lisbon look like?"
→ UpdatePoints (record the 120K balance on its program), then PlanRedemption
→ Reads Points.md valuations + transfer partners (airline and hotel partners reachable from that program)
→ Returns 2-3 concrete routings with points cost, cash equivalent, and next steps
Example 2: Which card
User: "Which card should I use for this flight?"
→ ShowBenefits
→ Compares the airfare earn rate and travel protections of each card in Cards.md (for example the Acme Sky Card earning more on airfare but carrying no trip insurance, against the Example Travel Card that includes it)
→ One-line answer with why
Example 3: Credit sweep
User: "What credits am I leaving on the table this year?"
→ CreditSweep
→ Reads `Credits.md`, flags unused/expiring/unregistered credits against today's date, dollars-at-risk up top
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Find and fetch vendor cybersecurity reports, then compare their findings on topics such as ransomware, breaches, cloud security, and AI. Analyses identify the reports consulted and cite each figure by vendor, year, and report, including where sources disagree.
Compare a component's own design needs with the goals of the larger system through three structured passes. The result identifies conflicts, recommends an appropriate scope, and assesses whether the proposed design fits the whole.
Find quotes that fit a text’s themes, with attribution and a short reason for each suggestion. Add sourced quotes, research thinkers, and organize a quote collection by theme and usage history to avoid repetition.
Create blog illustrations, technical diagrams, comparisons, comics, and icons through workflows tailored to each format. The skill guides composition, color, and model selection, then stages generated images for review before they are used in a project.
Assess the visual quality of images, films, slides, and site captures against a brief and craft criteria. Two vision judges score the work and rank defects, guiding bounded revision; delivery is gated on a passing critique, with human calibration labels recorded separately.
Find arXiv papers by topic, research category, or paper ID. Retrieve titles, authors, abstracts, and links, check new submissions, and add AlphaXiv's AI-generated overviews when available to help decide which papers to read.