write-agent-card

仓库创建 2026年7月26日最近提交 19 小时前SkillHot 收录 15 小时前

这个 Skill 做什么

编写和审计符合 A2A 规范的 agent-card.json，让其他 agents 能发现并调用你的技能。用于新建 agent、更新或校验 agent-card.json 时，会检查字段完备性、技能触发说明、能力标志和安全方案。关键优势是保证卡片里的声明和运行时的 SKILL.md 一致，避免发现与实际能力不匹配。

▸ 展开 SKILL.md 英文原文

Writes and audits A2A-compliant agent-card.json files: the machine-readable discovery metadata that lets other agents find, route to, and invoke an agent's skills. Covers all required and optional JSON fields, skill declaration quality (description, examples, tags), capability flags, security schemes, and alignment between the card and the agent's runtime SKILL.md. Use when creating a new agent, auditing an existing agent-card.json, or adding/modifying skills declared in a card.

Stars

Forks

仓库内 Skill

积累中

7 日增星

安装 / 使用

给你的 Agent 一句话（通用）

帮我安装这个 skill：https://raw.githubusercontent.com/fagerbergj/dotagents/main/skills/write-agent-card/SKILL.md

或 curl 直取 SKILL.md

curl -fsSL "https://raw.githubusercontent.com/fagerbergj/dotagents/main/skills/write-agent-card/SKILL.md"

SKILL.MD 节选查看完整文件 ↗

# Write Agent Card - A2A Agent Discovery Metadata

## Checklist (validate before shipping)

- [ ] `name` is the product name, not a technical identifier (`SupportBot Pro`, not `support_agent_v2`)
- [ ] `description` covers: what it does, task categories, integrations, output formats
- [ ] Every `skills[].description` states what the skill does **and** what requests trigger it
- [ ] Every `skills[].examples` has ≥2 diverse, realistic natural-language prompts
- [ ] Every `skills[].tags` has ≥2 descriptive category tags
- [ ] `capabilities.streaming` is only `true` if SSE is actually implemented
- [ ] `securitySchemes` matches what the endpoint actually enforces
- [ ] `supportedInterfaces[].url

via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有