Last30Days Skill Benchmark Harness Model Card
这是可索引项目报告证据页：它保留 Last30Days Skill Benchmark Harness Model Card 的源材料入口、机制线索和限制提醒；正文仍需 reader/editor 与 academic public-copy review 后才能当作最终结论引用。
Last30Days Skill Benchmark Harness Model Card
| Field | Value |
|---|---|
| Repository | mvanhorn/last30days-skill |
| Category | Reproducible Agent Skill Benchmark and Evaluation Harness |
| Stars / forks snapshot | 1300 / 147 |
| Language | Python |
| License | MIT |
| Raw capture | raw-github/mvanhorn_last30days-skill.md |
| Updated by | hourly public metadata update, 2026-06-01 01:50 +0800 |
1. Role in Self Evolve
mvanhorn/last30days-skill provides a mature Python benchmark harness for evaluating agent skill performance over time. It matters because self-evolving agents need repeatable harness control, measurable feedback loops, and reusable skill procedures before claiming stable improvement.
2. Working Principle
define benchmark tasks and scoring protocol for skill-driven agent runs -> execute task trajectories under controlled harness settings -> compare variants over reproducible metrics and historical windows -> retain high-performing skill behaviors while flagging regressions
3. Evidence Path
web-observed GitHub page showed 1.3k stars, 147 forks, 620 commits, MIT license, and Python-dominant benchmark implementation. Shell GitHub API access remained blocked by DNS and local gh auth was invalid, so this card treats the snapshot as web-observed rather than API-verified.
4. Teaching Use
Use this card to explain Reproducible Agent Skill Benchmark and Evaluation Harness: it shows how harness/runtime/benchmark layers convert agent behavior into reproducible and auditable engineering workflows.
5. Limits
The repository was not cloned in this iteration; no benchmark run, plugin install, workflow execution, or agent loop experiment was executed. Counts and claims are visible public-page/search signals unless independently revalidated later.