Leaderboard / api.aiskills402.com / endpoint
GET https://api.aiskills402.com/v1/skills/prompt-caching-review/file
Scores measure reliability and honesty, not output quality.
- Listed only 2 days ago; new listings earn trust over 30 days.
- Answered all 10 probes in the last 7 days.
- Category
- Inference by llm, confidence 50%
- Latest quote
- $0.01 on Base to 0xbc0d…2e68
- Uptime
- 100% / 7d, 100% / 30d
- Delivery
- none not yet paid-tested
- Observed
- none reported yet (opt-in wrapper telemetry)
- HTTPS
- yes
- First listed
- 2026-11-16
- Last probe
- 6h ago
- Next probe
- 2026-11-18 18:25 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Base | 0x8335…2913 | $0.01 | 0xbc0d…2e68 | default | yes | 18m ago |
Paid probes
No paid probes yet. Paid probing is off by default and runs weekly per host under a strict spend cap; each paid probe links to its on-chain transaction here.
Delivery checks
Inside each paid probe we ask for something whose correct answer we know, then compare. A pass means the seller delivered what it was paid for; a fail means it charged and returned something wrong; inconclusive means we could not judge (no reference, unknown input shape, or a non-2xx response). Every row carries the request, the response hash and the reference so the verdict can be reproduced. Judged results feed the "Delivery after payment" component (pass 1, error after payment 0.25, fail 0); inconclusive rows are excluded; a fail in the last 14 days caps the verdict at caution. Methodology.
No delivery checks yet. They run inside the weekly paid probe.
Classification history
Every classification is kept; the newest row is the current category. Rules match the listing text; the model is consulted only when the rules are unsure.
| When | Category | Confidence | Method | Version | Evidence |
|---|---|---|---|---|---|
| 34h ago | Inference | 50% | llm | v1 | claude-haiku-5-5: The endpoint reviews a Claude API request and returns findings about prompt caching, which is LLM-related analysis of model requests. It is not a chat completion itself, but it is closest to inference-adjacent model output. Confidence is moderate because the category is a judgment call between inference and other or web_audit-like code review. |
| 44h ago | Inference | 60% | rules | v1 | rule inference matched "claude" in description |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 6h ago | free | 402 | 210 ms | v2 | yes | $0.01 | 0xbc0d…2e68 | — |
| 12h ago | free | 402 | 223 ms | v2 | yes | $0.01 | 0xbc0d…2e68 | — |
| 18h ago | free | 402 | 218 ms | v2 | yes | $0.01 | 0xbc0d…2e68 | — |
| 24h ago | free | 402 | 222 ms | v2 | yes | $0.01 | 0xbc0d…2e68 | — |
| 31h ago | free | 402 | 544 ms | v2 | yes | $0.01 | 0xbc0d…2e68 | — |
| 37h ago | free | 402 | 634 ms | v2 | yes | $0.01 | 0xbc0d…2e68 | — |
| 43h ago | free | 402 | 225 ms | v2 | yes | $0.01 | 0xbc0d…2e68 | — |
| 2d ago | free | 402 | 186 ms | v2 | yes | $0.01 | 0xbc0d…2e68 | — |
| 2d ago | free | 402 | 208 ms | v2 | yes | $0.01 | 0xbc0d…2e68 | — |
| 3d ago | free | 402 | 191 ms | v2 | yes | $0.01 | 0xbc0d…2e68 | — |