Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →internet-court/altllm-portal-billing
Use this skill when the user asks to inspect AltLLM Portal balance, redeem a promo code, review billing transactions, or view usage analytics by period, model, or API key using the local altllm CLI.
Passed 22 of 22 test cases with the skill, and 6 of 22 without it.
and 17 more in the full report
16 fixed6 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 16 test cases the skill fixed. Same model, same prompt, with and without the skill.
If I execute `altllm usage-by-model` without providing any date arguments, what period does it report on by default?
| Checked | Without skill | With skill |
|---|---|---|
| States that it defaults to the current UTC month | Missed | Passed |
The instructions your model reads when the skill loads.
Balance, promo, transaction history, and usage analytics for the local altllm CLI.
Before the first
altllmcommand in a fresh checkout, read and follow:
../_shared/preflight.md../_shared/session-and-target.md
| Command | Purpose |
|---|---|
credit | Current Portal balance, expiry, and allowed models |
redeem-promo | Redeem a promo code |
transactions | Billing transaction history with pagination and type filters |
usage-summary | Current calendar-month summary |
usage-timeline | Daily usage history |
usage-by-model | Usage grouped by model |
usage-by-key | Usage grouped by API key |
credit is the current CLI inspection path for plan/model-access metadata returned by Portal, including Business/Flex fields such as subscription_tier: "flex" when present.transactions supports --page, --limit, and --type.usage-summary currently reflects the current calendar month only.usage-timeline, usage-by-model, and usage-by-key default to the current UTC month when no date flags are passed.--month or a complete explicit date range.balance is an alias for credit.See references/cli-reference.md for filters, examples, and representative outputs.
test cases passed, vs 6 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.