Together AI Skills Model Card
这是可索引项目报告证据页：它保留 Together AI 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。
Together AI Skills Model Card
| Field | Value |
|---|---|
| Repository | togethercomputer/skills |
| Category | Provider API Agent Skills Pack |
| Stars / forks snapshot | 28 / 5 |
| Language | Python/TypeScript |
| License | MIT |
| Raw capture | raw-github/togethercomputer_skills.md |
| Updated by | hourly public metadata update, 2026-05-25 13:21 +0800 |
1. Role in Self Evolve
Together AI Skills packages provider-specific API and SDK knowledge into 12 agent skills covering inference, training, embeddings, audio, video, images, function calling and infrastructure.
2. Working Principle
provider API references -> runnable scripts -> agent skill routing for SDK usage
3. Evidence Path
web GitHub page observed 137 commits, MIT license, 28 stars and 5 forks; README says the skills are compatible with Claude Code, Cursor, Codex and Gemini CLI and include SKILL.md routing, references, scripts and OpenAI/Codex UI metadata.. Shell GitHub API access remained DNS-blocked and the local gh token was invalid in this run, so this card treats the current snapshot as web-observed rather than API-verified.
4. Teaching Use
Use this card to explain how Together AI Skills fits the raw -> classification -> project card -> site/report pipeline. It is useful for comparing whether self-evolution is implemented as skill supply, memory substrate, planning persistence, harness governance, multi-agent orchestration, provider API packaging, or benchmark/evaluation infrastructure.
5. Limits
当前未克隆源码，未运行 benchmark、skill install flows、memory experiments、MCP servers、agent evolution loops、security scanners 或 production deployments；star/fork/commit/release 快照来自公开 GitHub 页面文本或可见页面片段。