Leaderboard / agent.connskill.com / endpoint
POST https://agent.connskill.com/v1/keywords-for-site
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
- Web audit by llm, confidence 60%
- Latest quote
- $0.05 on Base to 0x43B8…63dE
- 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
- 5h ago
- Next probe
- 2026-11-18 18:55 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Base | 0x8335…2913 | $0.05 | 0x43B8…63dE | default | yes | 6h ago |
Listing changes
| When | Event | From | To |
|---|---|---|---|
| 6h ago | reappeared | false | true |
| 41h ago | disappeared | — | — |
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 |
|---|---|---|---|---|---|
| 6h ago | Web audit | 60% | llm | v1 | claude-haiku-5-5: Derives keywords from a supplied site's content, which is SEO analysis of a URL the caller provides; some ambiguity with search data. |
| 6h ago | Other | 40% | rules | v1 | rule none matched "" in none |
| 27h ago | Other | 20% | llm | v1 | claude-haiku-5-5: The listing has no name, description, tags, or example fields. The resource path suggests keyword extraction for a site, which might fall under web_audit or web_scrape, but the listing alone is too thin to classify confidently. |
| 41h ago | Other | 20% | rules | v1 | rule none matched "" in none |
| 44h ago | Other | 40% | rules | v1 | rule none matched "" in none |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 5h ago | free | 402 | 536 ms | v2 | yes | $0.05 | 0x43B8…63dE | — |
| 11h ago | free | 402 | 190 ms | v2 | yes | $0.05 | 0x43B8…63dE | — |
| 17h ago | free | 402 | 194 ms | v2 | yes | $0.05 | 0x43B8…63dE | — |
| 23h ago | free | 402 | 202 ms | v2 | yes | $0.05 | 0x43B8…63dE | — |
| 30h ago | free | 402 | 524 ms | v2 | yes | $0.05 | 0x43B8…63dE | — |
| 36h ago | free | 402 | 242 ms | v2 | yes | $0.05 | 0x43B8…63dE | — |
| 42h ago | free | 402 | 530 ms | v2 | yes | $0.05 | 0x43B8…63dE | — |
| 2d ago | free | 402 | 196 ms | v2 | yes | $0.05 | 0x43B8…63dE | — |
| 2d ago | free | 402 | 534 ms | v2 | yes | $0.05 | 0x43B8…63dE | — |
| 3d ago | free | 402 | 194 ms | v2 | yes | $0.05 | 0x43B8…63dE | — |