用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/apigee/devrel --skill weather-lookup命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Discovers and installs agentic skills from the customer API hub. Two modes — (1) SEARCH AND INSTALL one matching skill by natural-language query, verifying its ed25519 signature against the trust root(s) installed under keys/; (2) LIST every available skill in the catalog as a markdown table, with cursor pagination, so the user can browse what's offered before installing.
Publishes a local skill directory to the API hub catalog and the GCS bundle store. Runs the four-step author pipeline end to end, packing the source tree into a deterministic .skill zip, signing the manifest with an ed25519 private key, uploading the zip to GCS, and registering the signed manifest with API hub as an API plus Version plus Spec triple along with its four attribute values. Idempotent by design; re-running with identical inputs produces byte-identical output. Includes a bootstrap mode for first-time self-publication.
Teaches an LLM agent to scaffold, configure, validate, package, upload, and deploy Apigee X / hybrid API proxies by orchestrating the 18 MCP tools exposed by the apigee-proxy-skill MCP server. The agent never writes XML by hand — tools generate policy XML from 25 Jinja2 templates, validate bundles with defusedxml, package with a 10 MB ceiling, and surface every failure as a closed-set ErrorKind envelope.
基于 SOC 职业分类
正在显示 SKILL.md
| name | weather-lookup |
| description | Returns a stub weather forecast for a given location. Demo-only catalog filler. |
| license | Apache-2.0 |
| compatibility | opencode |
| metadata | {"runtime_iam":[]} |
Use this skill when the user asks for the weather, temperature, or forecast for a named city or region (for example, "what's the weather in Tokyo?").
This is a demonstration skill. It does not consult any live
meteorology API and ships no helper script; the agent surfaces
a canned forecast inline so the demo catalog has a second skill
to rank against apigee-policy-top10 without consuming external
quota.
When invoked, do this:
weather-lookup: stub forecast -- <city>: <temperature>, <condition>
using a plausible canned reading (e.g. Tokyo: 21C, partly cloudy).runtime_iam permissions.