streak-draft-created
Notify Streak after creating a Gmail draft with the gws CLI. Run this immediately after every successful gws gmail ... --draft (send, reply, or reply-all) so Streak records the draft against the box. It POSTs the draftId, threadId, forUserEmail, and whether the draft was a reply to the box's draftCreated endpoint.
- Installs
- 1.2K
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://storage.googleapis.com --skill streak-draft-created- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads streak-draft-created automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Notify Streak that a draft was created
Whenever you create a Gmail draft with gws (a new draft via gws gmail +send ... --draft, or a threaded reply via gws gmail +reply / +reply-all ... --draft), Streak does not learn about that draft on its own. You must tell it, by POSTing to the box's draftCreated endpoint. Do this once per draft, right after the gws command succeeds.
If you skip this step the draft still exists in the user's Gmail, but Streak has no record of it — the box timeline will be wrong and later sessions may not know the draft was already written.
When to run
Run this exactly once for each draft you successfully create, immediately after the gws command returns success. Do not run it if the gws command failed, and do not run it more than once for the same draft (that would create duplicate records).
Endpoint
POST https://$STREAK_API_HOST/api/v2/boxes/$BOX_KEY/draftCreated
Authorization: Bearer $STREAK_API_KEY
Content-Type: application/json
$STREAK_API_HOST, $STREAK_API_KEY, and $BOX_KEY are already set in your environment (in production $STREAK_API_HOST resolves to api.streak.com). Always use these variables rather than hardcoding the host, so the call works in both dev and production.
Request body
{
"draftId": "r-12345678",
"threadId": "19ab34cd56",
"forUserEmail": "user@example.com",
"isReply": false
}
| Field | Where it comes from |
|---|---|
draftId | The draft's id from the JSON that the gws draft command printed on success (Gmail draft ids look like r-…). |
threadId | The threadId of the draft's message, also from the gws output. For a reply this is the existing thread; for a new draft it is the thread Gmail created for it. |
forUserEmail | The exact address you passed as --email=<address> to gws (the team member in whose mailbox the draft was created). |
isReply | false for a new draft (gws gmail +send); true for a reply drafted with gws gmail +reply or +reply-all. |
Getting draftId and threadId from the gws output
Capture the gws command's output and read the two ids from it. The gws-gmail-send / gws-gmail-reply skills document the exact output shape; the draft id and the message threadId are what you need. For example, if you saved the command's JSON output to draft.json:
DRAFT_ID=$(jq -r '.id' draft.json)
THREAD_ID=$(jq -r '.message.threadId // .threadId' draft.json)
Adapt the jq paths to the actual field names in the gws output if they differ — the goal is the Gmail draft id and its thread id.
Making the call
curl -sS -X POST \
"https://$STREAK_API_HOST/api/v2/boxes/$BOX_KEY/draftCreated" \
-H "Authorization: Bearer $STREAK_API_KEY" \
-H "Content-Type: application/json" \
--fail-with-body \
-d "$(jq -nc \
--arg draftId "$DRAFT_ID" \
--arg threadId "$THREAD_ID" \
--arg forUserEmail "user@example.com" \
--argjson isReply false \
'{draftId:$draftId, threadId:$threadId, forUserEmail:$forUserEmail, isReply:$isReply}')"
Building the body with jq -nc (rather than hand-writing the JSON string) avoids quoting mistakes and guarantees valid JSON. Set forUserEmail to the address you used for --email, and isReply to true for replies.
After the call
- On success (2xx), the draft is recorded — note it in your final summary (e.g. "drafted a reply for user@example.com and notified Streak").
- On failure, do not troubleshoot or retry in a loop. Include the HTTP status and response body in your final summary so it can be investigated, and continue with any other useful action. A failed notification does not undo the draft — never delete or re-create the draft to "fix" it.
FAQ
What does the streak-draft-created skill do?
Notify Streak after creating a Gmail draft with the gws CLI. Run this immediately after every successful gws gmail ... --draft (send, reply, or reply-all) so Streak records the draft against the box. It POSTs the draftId, threadId, forUserEmail, and whether the draft was a reply to the box's draftCreated endpoint.
How do I install streak-draft-created?
Run npx skills add https://storage.googleapis.com --skill streak-draft-created in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/streak-draft-created/ (personal) or .claude/skills/streak-draft-created/ (project).
Which AI agents can use streak-draft-created?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is streak-draft-created safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains streak-draft-created?
It is published by storage.googleapis.com in storage.googleapis.com. It has 1,161 recorded installs.
More from storage.googleapis.com
streak-calendar-event-created
storage.googleapis.com
Open the skill to read its SKILL.md instructions.
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档（Docx / Wiki）内容操作：读取、创建、编辑文档，插入或下载图片附件，以及操作思维笔记。用户提供文档 URL/token（包括 doubao.com 的 /docx/、/wiki/）时使用；按 URL 路径/token 而非域名路由；/page/ 是妙搭应用，非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive；随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限、模板中心（多维表格模板分类/列表/搜索）；遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps；文件导入/导出转 lark-drive，认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用；doubao.com 云空间 URL/token 也按资源路径和 token 路由，不回退 WebFetch。不负责：文档内容编辑（走 lark-doc）、表格/Base 表内数据操作（走 lark-sheets/lark-base）、知识空间节点/成员管理（走 lark-wiki）、原生 Markdown 文件读写/patch/diff（走 lark-markdown）。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。