Evals
Define expectations, criteria, and recorded results for prompts, agents, tools, skills, and workflows.
- License 许可
- MIT
- 所属仓库
- benmcnulty/orgos
- 最近更新
- 2026-10-25
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- Evals
- tools
- [ "evals.list", "evals.write" ]
- context
- 4096
- version
- 1.0.0
- description
- Define expectations, criteria, and recorded results for prompts, agents, tools, skills, and workflows.
03 SKILL.md 正文
Evals Skill
Use this skill to store evaluation criteria and results for quality assurance and prompt/process refinement.
Persistent File
.data/organizations/{{ORG_ID}}/evals.json
04 同仓库更多 Skills
Web Browsing
Search the web via DuckDuckGo, fetch and extract content from URLs, and look up reference material. Use for real-time information, external documentation, and validating facts against public sources.
Vision
Capture screenshots of the application UI and analyze image content. Use for visual verification, UI inspection, accessibility review, and generating image-grounded descriptions.
Staff
Shape the organization structure, assign agent templates to roles, and manage staffed identities in the active organization.
Projects
Define delivery-oriented projects, participants, outputs, and current execution state for the active organization.
organizations
暂无简介
notifications
暂无简介