agentleFS
uvwtuvwt/agentdock-skills/skills/poke-api/SKILL.md

poke-api

Skill6 starsChanged 2 months agoApache-2.0View on GitHub

Send context-rich instructions to Poke through the V2 inbound API using a securely injected API key.

  • Reads credentials

The file

Files
SKILL.md

Poke API Skill

通过 Poke V2 API 将消息或结构化上下文发送给你的 Poke 助手。

操作

status

检查 Skill 版本、固定端点以及 POKE_API_KEY 是否已从 ~/.agentdock/env/skill/poke-api.env 或当前命令显式环境加载。不会发起网络请求,也不会输出密钥。

send

向 https://poke.com/api/v1/inbound/api-message 发送 JSON。

输入:

  • message:推荐使用的自然语言指令。
  • context:可选 JSON 对象,其字段会与 message 合并到顶层请求体,便于附带 URL、文件路径、事件 ID 或其他结构化信息。
  • dry_run:只构造请求,不访问 Poke;无密钥时也可使用。
  • timeout_seconds:请求超时,范围 1–60 秒。

message 与 context 至少提供一个。若两者都提供,显式 message 会作为最终请求体的 message 字段。

配置

仅通过私有 Skill 环境文件或当前命令环境配置:

POKE_API_KEY

不要把 API Key 写进 Skill 源码、输入参数、日志、README 或 Git。该 Skill 只支持 Kitchen 创建的 V2 Key 和新端点;不调用已弃用的 /api/v1/inbound-sms/webhook。

安全边界

  • API 端点固定为 https://poke.com/api/v1/inbound/api-message,输入不能覆盖。
  • Authorization Header 和 API Key 不会出现在输出中。
  • HTTP 响应会递归脱敏常见凭据字段。
  • 请求体限制为 512 KiB,响应体限制为 1 MiB。
  • 使用 Python 标准库,无第三方依赖。

辅助脚本执行

Skill 本体是本说明文档。确需调用包内辅助脚本时,在 Skill 包根目录使用相对路径执行;运行宿主负责切换到包根目录并把所需变量注入当前子进程。

printf '%s' '{"skill_action":"<动作>"}' | python3 run.py

输入必须是 JSON 对象。写操作仍按本文档中的确认规则执行。

动作用途
statusCheck Poke API configuration without sending a request or revealing the API key.
sendSend a natural-language message and optional top-level structured context to Poke.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.