Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Manage Sub2API admin APIs for accounts, redeem codes, groups, proxies, error passthrough rules, TLS fingerprint profiles, imports, exports, batch updates, and raw administrator API calls. Use when the user mentions Sub2API, admin API keys, account management, redeem code management, recharge codes, invitation codes, bulk account import/export, keeping or deleting accounts, refreshing accounts, clearing errors, CRS sync, or managing Sub2API backend settings through the admin API.
.claude/skills/bilal140202-sub2api-admin/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 96% | 22 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -33% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 4% | 0% |
Use the bundled CLI instead of ad hoc curl. Run examples from this skill directory.
bashexport SUB2API_BASE_URL='https://your-sub2api-host' export SUB2API_ADMIN_API_KEY='<admin api key>' node scripts/sub2api-admin.js accounts list
For all commands and payload examples, read references/admin-cli.md.
SUB2API_BASE_URL and SUB2API_ADMIN_API_KEY from the environment.accounts list, accounts get <id>, groups all, or proxies all.bashnode scripts/sub2api-admin.js accounts list --page-size 20 node scripts/sub2api-admin.js accounts get 40 node scripts/sub2api-admin.js accounts usage 40 node scripts/sub2api-admin.js accounts set-schedulable 40 true node scripts/sub2api-admin.js accounts bulk-update --ids 40,39 --json '{"concurrency":10}' node scripts/sub2api-admin.js redeem-codes list --page-size 20 node scripts/sub2api-admin.js redeem-codes generate --json '{"count":1,"type":"balance","value":10}' --idempotency-key redeem-$(date +%s) node scripts/sub2api-admin.js redeem-codes create-and-redeem --json '{"code":"order_123","type":"balance","value":10,"user_id":123}' --idempotency-key order-123 node scripts/sub2api-admin.js error-rules list node scripts/sub2api-admin.js tls-profiles list
x-api-key.INVALID_ADMIN_KEY, ask the user to regenerate the admin API key.accounts export includes credentials and tokens. Prefer --file and avoid printing exports in chat.--idempotency-key for payment or recharge workflows.api <METHOD> <admin-path> after a read-only check.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-08 | fail→fail | 5,565 | 4,049 | -27% | 1 | 1 | 0% | 1,019 | 824 | -19% | 0 | 0 | — |
case-02 | fail→fail | 8,182 | 3,157 | -61% | 1 | 1 | 0% | 1,653 | 1,067 | -35% | 0 | 0 | — |
case-01 | fail→fail | 4,938 | 2,978 | -40% | 1 | 1 | 0% | 281 | 957 | +241% | 0 | 0 | — |
case-03 | fail→fail | 11,611 | 8,708 | -25% | 1 | 1 | 0% | 2,253 | 1,012 | -55% | 0 | 0 | — |
case-04 | fail→pass | 13,496 | 5,049 | -63% | 1 | 1 | 0% | 2,460 | 1,640 | -33% | 0 | 0 | — |
case-05 | fail→pass | 4,279 | 3,169 | -26% | 1 | 1 | 0% | 826 | 836 | +1% | 0 | 0 | — |
case-06 | fail→pass | 7,359 | 2,237 | -70% | 1 | 1 | 0% | 1,184 | 993 | -16% | 0 | 0 | — |
case-07 | fail→pass | 6,842 | 2,363 | -65% | 1 | 1 | 0% | 1,125 | 978 | -13% | 0 | 0 | — |
case-09 | fail→pass | 17,104 | 5,319 | -69% | 1 | 1 | 0% | 1,448 | 1,512 | +4% | 0 | 0 | — |
case-10 | fail→pass | 9,679 | 2,887 | -70% | 1 | 1 | 0% | 1,778 | 1,222 | -31% | 0 | 0 | — |
case-11 | fail→fail | 6,999 | 3,995 | -43% | 1 | 1 | 0% | 1,137 | 797 | -30% | 0 | 0 | — |
case-12 | fail→pass | 9,767 | 3,977 | -59% | 1 | 1 | 0% | 1,792 | 1,199 | -33% | 0 | 0 | — |
case-13 | pass→pass | 7,861 | 2,712 | -66% | 1 | 1 | 0% | 1,580 | 1,093 | -31% | 0 | 0 | — |
case-14 | fail→pass | 9,615 | 2,201 | -77% | 1 | 1 | 0% | 1,765 | 1,063 | -40% | 0 | 0 | — |
case-15 | pass→pass | 4,364 | 2,191 | -50% | 1 | 1 | 0% | 756 | 762 | +1% | 0 | 0 | — |
case-16 | pass→pass | 8,724 | 3,273 | -62% | 1 | 1 | 0% | 1,691 | 1,169 | -31% | 0 | 0 | — |
case-17 | fail→pass | 3,064 | 2,572 | -16% | 1 | 1 | 0% | 538 | 1,128 | +110% | 0 | 0 | — |
case-18 | fail→pass | 7,704 | 1,815 | -76% | 1 | 1 | 0% | 1,311 | 907 | -31% | 0 | 0 | — |
case-19 | fail→pass | 4,877 | 3,175 | -35% | 1 | 1 | 0% | 985 | 1,306 | +33% | 0 | 0 | — |
case-20 | pass→pass | 10,044 | 5,564 | -45% | 1 | 1 | 0% | 2,169 | 1,794 | -17% | 0 | 0 | — |
case-21 | pass→pass | 6,397 | 3,994 | -38% | 1 | 1 | 0% | 1,403 | 1,418 | +1% | 0 | 0 | — |
case-22 | pass→pass | 7,791 | 5,271 | -32% | 1 | 1 | 0% | 1,588 | 1,649 | +4% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 19 counted toward the lift figure. The other 3 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +50 percentage points is the difference between those two pass rates over the 19 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.