Supabase Agent Skills Model Card

这是可索引项目报告证据页：它保留 Supabase Agent Skills 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。

Supabase Agent Skills Model Card

1. Role in Self Evolve

supabase/agent-skills publishes composable skill packs for coding and product-support agent workflows with reusable prompt structures. It matters because self-evolving agents need repeatable harness control, measurable feedback loops, and reusable skill procedures before claiming stable improvement.

2. Working Principle

encode domain-specific playbooks as compact skill assets -> inject them into agent context only when needed -> preserve high-value workflow constraints and SQL/product knowledge -> stabilize assistant output quality through reusable prompt primitives

3. Evidence Path

web-observed GitHub page showed 2.2k stars, 146 forks, 79 commits, MIT license, and markdown-first skill package design. 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 Agent Skill Packs and Prompt Compression Patterns: 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.