Rohit Ghumare
da94da82e8
feat: add multi-tier eval engine (skillkit eval)
6-tier evaluation system for comprehensive skill assessment:
- Tier 1: LLM quality scoring (G-Eval pattern, 6 dimensions)
- Tier 2: Contradiction detection (formal rules + LLM semantic)
- Tier 3: Behavioral security (code analysis + taint tracking + LLM)
- Tier 4: Sandbox execution testing (Docker, graceful skip)
- Tier 5: Dynamic marketplace benchmarks (percentile ranking)
- Tier 6: Community signals (freshness, metadata, content health)
Works without API keys (heuristic fallback for Tier 1, Tiers 5-6).
Full LLM evaluation with --provider flag.
2026-03-10 21:47:50 +05:30
..
2026-01-25 14:09:47 +00:00
2026-02-09 20:21:54 +00:00
2026-02-10 09:05:49 +00:00
2026-02-05 15:40:14 +00:00
2026-01-24 11:54:47 +00:00
2026-02-04 00:27:25 +00:00
2026-01-23 18:12:15 +00:00
2026-02-09 20:21:54 +00:00
2026-02-02 16:18:13 +00:00
2026-01-25 14:09:47 +00:00
2026-03-10 21:47:50 +05:30
2026-02-02 16:18:13 +00:00
2026-02-22 21:39:47 +05:30
2026-01-30 17:48:10 +00:00
2026-01-24 11:54:47 +00:00
2026-01-30 17:48:10 +00:00
2026-01-28 10:47:02 +00:00
2026-01-27 00:02:40 +00:00
2026-02-11 20:26:51 +00:00
2026-03-06 08:53:32 +00:00
2026-03-10 15:09:31 +00:00
2026-02-04 00:27:25 +00:00
2026-02-22 21:39:47 +05:30
2026-01-23 22:32:29 +00:00
2026-01-29 19:09:03 +00:00
2026-01-30 17:48:10 +00:00
2026-02-22 21:39:50 +05:30
2026-02-10 09:05:49 +00:00
2026-02-04 00:27:25 +00:00
2026-02-02 16:18:13 +00:00
2026-02-22 21:39:47 +05:30
2026-02-22 21:39:50 +05:30
2026-02-04 00:27:25 +00:00
2026-02-10 09:05:49 +00:00
2026-02-14 10:24:08 +00:00
2026-02-02 23:28:08 +00:00
2026-02-14 07:11:44 +00:00
2026-01-23 22:32:29 +00:00
2026-01-23 18:12:15 +00:00
2026-02-09 20:21:54 +00:00
2026-02-02 16:18:13 +00:00
2026-02-22 21:39:47 +05:30
2026-02-10 09:05:49 +00:00
2026-01-30 17:48:10 +00:00
2026-02-09 20:21:54 +00:00
2026-01-23 22:32:29 +00:00
2026-03-10 21:47:50 +05:30
2026-02-09 20:21:54 +00:00
2026-02-03 13:48:35 +00:00
2026-02-22 21:39:50 +05:30