geekbot

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Geekbot — AI-Powered Standup & Poll Management

Geekbot — AI驱动的站会与投票管理

Overview

This skill wraps the

geekbot

CLI to let users manage async team rituals conversationally. It handles two broad workflows:

Manager workflows — create standups/polls from templates, edit configs, manage members and schedules, analyse team engagement from report data
Reporter workflows — draft standup reports with AI assistance, carry over unresolved blockers, calibrate tone from history, post reports

The CLI produces structured JSON output with machine-readable error codes, making it reliable for agent-driven automation.

本Skill封装了

geekbot

CLI，支持用户通过对话方式管理异步团队仪式。它覆盖两大类工作流：

管理者工作流 —— 基于模板创建站会/投票、编辑配置、管理成员与日程、基于报告数据分析团队参与度
提交者工作流 —— 借助AI辅助草拟站会报告、同步未解决的阻塞问题、根据历史记录调整语气、发布报告

CLI会生成带机器可读错误码的结构化JSON输出，非常适合Agent驱动的自动化场景。

Prerequisites

前置要求

Before any operation, verify the CLI is available and authenticated.

Run

check-cli.sh

on first invocation. If it fails:

CLI not found: Install via
```
npm install -g geekbot-cli
```
(requires Bun >= 1.3.5 runtime). Note:
```
npx geekbot-cli
```
also requires Bun on PATH — it is not a Node.js fallback.
Auth not configured: Guide the user to run
```
geekbot auth setup
```
which stores the API key in the OS keychain. Alternatively they can set
```
GEEKBOT_API_KEY
```
as an environment variable.

Do not attempt any Geekbot operation until both checks pass.

执行任何操作前，请先验证CLI可用且已完成身份认证。

首次调用时运行

check-cli.sh

，如果运行失败：

未找到CLI：通过
```
npm install -g geekbot-cli
```
安装（需要Bun >= 1.3.5运行环境）。注意：
```
npx geekbot-cli
```
同样要求PATH中存在Bun，不能作为Node.js的替代方案。
未配置身份认证：引导用户运行
```
geekbot auth setup
```
，该命令会将API密钥存储到系统钥匙串中。用户也可以将
```
GEEKBOT_API_KEY
```
设置为环境变量。

两项检查都通过后再执行任何Geekbot操作。

How the CLI Works

CLI工作原理

The CLI follows a noun-verb pattern:

geekbot <resource> <action> [options]

Every command returns a JSON envelope on stdout:

Success: { "ok": true,  "data": <T>,  "error": null,  "metadata": {...} }
Error:   { "ok": false, "data": null,  "error": { "code", "message", "retryable", "suggestion" }, "metadata": {...} }

Always check the

ok

field first. On errors, the

error.suggestion

field often contains the exact fix — including listing valid IDs when a resource isn't found. Use this to self-correct without bothering the user.

For the full command reference with flags, defaults, and examples, read

cli-commands.md

CLI遵循名词-动词的使用模式：

geekbot <资源> <操作> [选项]

。

所有命令都会在标准输出返回JSON封装结果：

Success: { "ok": true,  "data": <T>,  "error": null,  "metadata": {...} }
Error:   { "ok": false, "data": null,  "error": { "code", "message", "retryable", "suggestion" }, "metadata": {...} }

始终优先检查

ok

字段。出现错误时，

error.suggestion

字段通常会给出明确的修复方案——包括资源未找到时列出有效的ID。可以直接使用该字段自行修正，无需打扰用户。

完整的命令参考（包含参数、默认值、示例）请查看

cli-commands.md

。

Quick Reference

快速参考

Most common operations at a glance:

Task	Command
List my standups	`geekbot standup list` (add `--brief` for compact output, `--name` / `--channel` to filter, `--mine` for member-only, `--member <id>` for a specific user, `--limit <n>` to cap results)
Get standup details + question IDs	`geekbot standup get <id>`
Create a standup	`geekbot standup create --name "..." --channel "..." --questions '[...]'`
Update a standup (PATCH)	`geekbot standup update <id> --time "09:30"`
Delete a standup	`geekbot standup delete <id> --yes`
List reports	`geekbot report list --standup-id <id> --limit 10`
Submit a report	`geekbot report create --standup-id <id> --answers '{"<qid>":"..."}'`
My profile + user ID	`geekbot me show`
Create a poll (Slack only)	`geekbot poll create --name "..." --channel "..." --question "..." --choices '[...]'`
Search team members	`geekbot team search <query>` (matches username, realname, email)
Check auth	`geekbot auth status`

For full flag details, see

cli-commands.md

最常用操作一览：

任务	命令
列出我参与的站会	`geekbot standup list` （添加 `--brief` 获取精简输出， `--name` / `--channel` 筛选， `--mine` 仅展示成员权限的站会， `--member <id>` 查看特定用户的站会， `--limit <n>` 限制返回结果数量）
获取站会详情 + 问题ID	`geekbot standup get <id>`
创建站会	`geekbot standup create --name "..." --channel "..." --questions '[...]'`
更新站会（PATCH）	`geekbot standup update <id> --time "09:30"`
删除站会	`geekbot standup delete <id> --yes`
列出报告	`geekbot report list --standup-id <id> --limit 10`
提交报告	`geekbot report create --standup-id <id> --answers '{"<qid>":"..."}'`
我的个人资料 + 用户ID	`geekbot me show`
创建投票（仅支持Slack）	`geekbot poll create --name "..." --channel "..." --question "..." --choices '[...]'`
搜索团队成员	`geekbot team search <query>` （匹配用户名、真实姓名、邮箱）
检查认证状态	`geekbot auth status`

完整参数说明请查看

cli-commands.md

。

External Context Enrichment

外部上下文增强

The skill becomes dramatically more useful when it can pull data from where work actually happens. This is opportunistic — check what MCP servers are connected in the current session and use whatever is available. Never fail or complain if nothing is connected; just fall back to asking the user.

For report drafting: Pull the user's recent activity from connected MCP servers (GitHub, Jira, Calendar, Slack) and use it to pre-populate a draft. The user reviews and approves instead of writing from scratch.

For analytics: Cross-reference standup report data with delivery data to give richer insights — not just "who posted" but "what was actually shipped."

For entity mapping tables and deduplication strategy, see

reporter-workflows.md

Important boundaries:

Always show the user what data you pulled and from where
Never post a report containing enrichment data without user review
If an MCP server query fails, skip it silently and move on
Enrichment provides specifics (PR numbers, ticket IDs); the user's voice still drives the narrative

当Skill能从实际工作场景中拉取数据时，实用性会大幅提升。这是可选功能——检查当前会话中连接了哪些MCP服务器，使用所有可用资源即可。如果没有连接任何服务也不要报错或提示，直接回退到询问用户即可。

报告草拟场景：从已连接的MCP服务器（GitHub、Jira、日历、Slack）拉取用户近期活动，用这些数据预填充草稿。用户只需审核确认即可，无需从零开始编写。

分析场景：将站会报告数据与交付数据交叉对比，提供更丰富的洞察——不只是“谁提交了报告”，还包括“实际交付了哪些内容”。

实体映射表与去重策略请查看

reporter-workflows.md

。

重要边界规则：

始终向用户展示拉取的数据内容和来源
未经用户审核，绝对不要发布包含增强数据的报告
如果MCP服务器查询失败，静默跳过继续执行
增强数据仅提供具体信息（PR编号、工单ID），报告的整体叙述仍以用户的表达为主

Intent Routing

意图路由

Pattern-match on the user's request to pick the right workflow. Don't ask "are you a manager or a reporter?" — the request itself makes intent clear. The same person can manage standups and submit reports in one conversation.

Route to Manager Workflows (§ below) when you see:

Creation/config language: "create", "set up", "configure", "schedule", "add members", "change the questions", "duplicate", "delete"
Analytics language: "how is my team doing", "engagement", "response rate", "who hasn't posted", "participation", "trends"
Member summary language: "what has X been up to", "X's reports", "1-1 prep for X", "summarize X's work", "what did X report", "catch me up on X", "X's recent standups"
Poll language: "create a poll", "voting results", "survey"

Route to Reporter Workflows (§ below) when you see:

Drafting language: "help me write", "draft my report", "what should I say", "fill in my standup"
Posting language: "post my answers", "submit my report"
Context language: "what did I say last time", "carry over blockers", "my recent reports"
Identity queries: "what standups am I in", "show my profile"

When ambiguous, ask one clarifying question — never more than one.

根据用户请求的模式匹配选择合适的工作流。不要问“你是管理者还是提交者？”——请求本身已经能明确意图。同一个用户可以在一次对话中既管理站会也提交报告。

满足以下特征时路由到管理者工作流（见下文章节）：

创建/配置相关表述："create"、"set up"、"configure"、"schedule"、"add members"、"change the questions"、"duplicate"、"delete"
分析相关表述："how is my team doing"、"engagement"、"response rate"、"who hasn't posted"、"participation"、"trends"
成员总结相关表述："what has X been up to"、"X's reports"、"1-1 prep for X"、"summarize X's work"、"what did X report"、"catch me up on X"、"X's recent standups"
投票相关表述："create a poll"、"voting results"、"survey"

满足以下特征时路由到提交者工作流（见下文章节）：

草拟相关表述："help me write"、"draft my report"、"what should I say"、"fill in my standup"
发布相关表述："post my answers"、"submit my report"
上下文相关表述："what did I say last time"、"carry over blockers"、"my recent reports"
身份查询相关表述："what standups am I in"、"show my profile"

意图不明确时，最多问一个澄清问题，不要多次询问。

Manager Workflows

管理者工作流

For detailed multi-step guides, read

manager-workflows.md

详细的多步骤指南请查看

manager-workflows.md

。

Creating a Standup

创建站会

This is the most common and most complex manager operation.

If the request is vague ("set up a standup for my team"), offer templates. Load

standup-templates.json

and present the 3–4 most relevant options based on context. Templates provide pre-built questions and sensible schedule defaults — the user just needs to supply a name and Slack/Teams channel.

Gathering required fields:

```
--name
```
— the standup name (required)
```
--channel
```
— Slack/Teams channel to post in (required)
```
--questions
```
— JSON array of question objects (required; from template or custom)
```
--time
```
— defaults to 10:00 if not specified
```
--timezone
```
— infer from
```
geekbot me show
```
→
```
data.timezone
```
if not given
```
--days
```
— defaults to Mon–Fri
```
--users
```
— comma-separated user IDs (can add later via
```
update
```
)

Always confirm the full configuration with the user before executing. Show: name, channel, questions, schedule, timezone.

Note: The CLI sets which days of the week to run but cannot set frequency (bi-weekly, monthly). For non-weekly schedules, create the standup via CLI and tell the user to adjust the frequency in the Geekbot web dashboard.

这是最常见也最复杂的管理者操作。

如果请求比较模糊（比如"set up a standup for my team"），提供模板选项。加载

standup-templates.json

，根据上下文展示3-4个最相关的选项。模板提供预设的问题和合理的日程默认值，用户只需提供站会名称和Slack/Teams频道即可。

收集必填字段：

```
--name
```
—— 站会名称（必填）
```
--channel
```
—— 发布站会的Slack/Teams频道（必填）
```
--questions
```
—— 问题对象的JSON数组（必填，可以来自模板或自定义）
```
--time
```
—— 未指定时默认10:00
```
--timezone
```
—— 未指定时从
```
geekbot me show
```
返回的
```
data.timezone
```
推断
```
--days
```
—— 默认周一到周五
```
--users
```
—— 逗号分隔的用户ID（可以后续通过
```
update
```
添加）

执行前务必向用户确认完整配置，展示内容包括：名称、频道、问题、日程、时区。

注意：CLI可以设置每周运行的天数，但无法设置频率（双周、月度）。对于非每周的日程，通过CLI创建站会后，告知用户可以在Geekbot网页控制面板中调整频率。

Editing / Deleting / Other Operations

编辑/删除/其他操作

Edit: Fetch current state with
```
standup get
```
, show the user, confirm changes, use
```
standup update
```
(PATCH). Use
```
standup replace
```
only for full config replacement.
Delete: Always fetch and show what will be deleted first. Get explicit confirmation. Execute with
```
--yes
```
.

Duplicate:

geekbot standup duplicate <id> --name "New Name"

Trigger now:
```
geekbot standup start <id>
```
— confirm before executing.
Polls (Slack only): See
```
cli-commands.md
```
for poll commands.

编辑：通过
```
standup get
```
获取当前配置，展示给用户，确认修改后使用
```
standup update
```
（PATCH）。仅在需要全量替换配置时使用
```
standup replace
```
。
删除：始终先拉取并展示即将删除的内容，获取用户明确确认后执行，执行时添加
```
--yes
```
参数。

复制：

geekbot standup duplicate <id> --name "New Name"

立即触发：
```
geekbot standup start <id>
```
—— 执行前确认。
投票（仅支持Slack）：投票命令请查看
```
cli-commands.md
```
。

Analytics

分析

Analytics come from report data fetched via the CLI. The skill computes metrics; the CLI provides raw data. For the full analytics playbook with 6 named analysis patterns (response rate, participation gaps, blocker frequency, trends, answer quality, cross-referencing), read

manager-workflows.md

Quick start: Identify the standup with

standup list

, get member count with

standup get <id>

, fetch reports with

report list --standup-id <id> --after <date> --limit 100

, then compute.

分析数据来自CLI拉取的报告原始数据，由Skill计算指标。完整的分析指南包含6种命名分析模式（回复率、参与缺口、阻塞问题频率、趋势、回答质量、交叉对比），请查看

manager-workflows.md

。

快速入门：通过

standup list

确定目标站会，通过

standup get <id>

获取成员数量，通过

report list --standup-id <id> --after <date> --limit 100

拉取报告，再计算相关指标。

Team Member Summary

团队成员总结

Summarize what a specific person has been working on — ideal for 1-1 prep. For the full step-by-step workflow, read

manager-workflows.md

§Team Member Summary.

Quick start:

geekbot team search <name>

→ get user ID →

geekbot standup list --member <id> --brief

to find their standups →

geekbot report list --standup-id <sid> --user-id <id> --after <3 weeks ago> --limit 20

→ synthesize by work stream, not chronologically.

总结特定成员的工作内容——非常适合1对1沟通准备。完整的分步工作流请查看

manager-workflows.md

的§团队成员总结章节。

快速入门：

geekbot team search <name>

→ 获取用户ID →

geekbot standup list --member <id> --brief

查找该用户参与的站会 →

geekbot report list --standup-id <sid> --user-id <id> --after <3 weeks ago> --limit 20

→ 按工作流合成总结，而非按时间顺序排列。

Reporter Workflows

提交者工作流

For the full drafting pipeline, tone calibration, blocker carry-over logic, and edge cases, read

reporter-workflows.md

完整的草拟流程、语气校准、阻塞问题同步逻辑、边缘场景处理请查看

reporter-workflows.md

。

Report Drafting Pipeline (Summary)

报告草拟流程（摘要）

Identify the standup —
```
standup list
```
, auto-select if only one
Fetch questions —
```
standup get <id>
```
→ extract question IDs and text
Gather context — from MCP servers (if connected), previous reports (for style calibration), and the user's direct input
Draft answers — match their historical tone/length, weave in specifics from MCP data, run blocker carry-over check on last 3–5 reports
Review and post — present draft, get explicit approval, then
```
report create --standup-id <id> --answers '{...}'
```

Never post a report without explicit user approval.

确定目标站会 —— 调用
```
standup list
```
，如果只有一个则自动选择
拉取问题列表 —— 调用
```
standup get <id>
```
→ 提取问题ID和内容
收集上下文 —— 从MCP服务器（如果已连接）、历史报告（用于风格校准）、用户直接输入中获取信息
草拟回答 —— 匹配用户历史的语气/篇幅，整合MCP数据中的具体信息，检查过往3-5份报告同步未解决的阻塞问题
审核与发布 —— 展示草稿，获取用户明确批准后，执行
```
report create --standup-id <id> --answers '{...}'
```

未经用户明确批准，绝对不要发布报告。

Quick Actions

快捷操作

One-shot commands that don't need the full pipeline:

"What standups am I in?" →
```
geekbot standup list
```

"Show my recent reports" →

geekbot report list --user-id <uid> --limit 5

"Show my profile" →
```
geekbot me show
```
"What teams am I in?" →
```
geekbot me teams
```
"Trigger my standup now" → confirm first, then
```
geekbot standup start <id>
```

不需要完整流程的一次性命令：

"What standups am I in?" →
```
geekbot standup list
```

"Show my recent reports" →

geekbot report list --user-id <uid> --limit 5

"Show my profile" →
```
geekbot me show
```
"What teams am I in?" →
```
geekbot me teams
```
"Trigger my standup now" → 先确认，再执行
```
geekbot standup start <id>
```

Confirmation Policy

确认规则

Operation	Confirmation required?	What to show
CREATE standup/poll	Yes	Full config: name, channel, questions, schedule
UPDATE standup	Yes	Current vs proposed (diff)
DELETE standup	Yes, always	What will be deleted (name, channel, members)
POST report	Yes, always	Complete draft with all answers
TRIGGER standup	Yes	Which standup, who it targets
List / Get / Analytics	No	Just execute and present results
Error recovery retries	No	Transparent to user

操作	是否需要确认？	需要展示的内容
创建站会/投票	是	完整配置：名称、频道、问题、日程
更新站会	是	当前配置与修改内容的对比
删除站会	始终需要	即将删除的内容（名称、频道、成员）
发布报告	始终需要	包含所有回答的完整草稿
触发站会	是	目标站会、通知对象
查询/获取/分析	否	直接执行并展示结果
错误恢复重试	否	对用户透明

Error Handling

错误处理

For the complete recovery guide, read

error-recovery.md

Core pattern: always parse the JSON envelope, check

ok

, branch on exit code.

Exit code	Meaning	Agent action
0	Success	Proceed normally
3	Not found	Parse `error.suggestion` — it lists valid IDs. Offer them to the user.
4	Auth failed	Guide user through `geekbot auth setup` . Do not retry.
5	Forbidden	Explain permission issue. The user may need admin access.
6	Validation	Show `error.message` , help the user fix the input.
7	Network	If `error.retryable` is true, retry once after 2s silently. If it fails again, report.
8	Conflict	Explain the conflict (e.g., duplicate name). Suggest resolution.
9	Schema validation ( `schema_validation_error` )	API response didn't match expected format. Don't ask user to fix input — suggest updating CLI or reporting a bug.
1, 2, 9	General / usage / API	Report `error.message` to the user clearly.

Never retry errors where

retryable

is false.

完整的恢复指南请查看

error-recovery.md

。

核心模式：始终解析JSON封装结果，检查

ok

字段，根据退出码分支处理。

退出码	含义	Agent操作
0	成功	正常继续
3	资源未找到	解析 `error.suggestion` ，其中会列出有效ID，提供给用户选择
4	认证失败	引导用户执行 `geekbot auth setup` ，不要重试
5	无权限	说明权限问题，用户可能需要管理员权限
6	校验失败	展示 `error.message` ，帮助用户修正输入
7	网络错误	如果 `error.retryable` 为true，静默等待2秒后重试一次，如果再次失败则上报
8	冲突	说明冲突原因（比如名称重复），给出解决方案建议
9	结构校验失败（ `schema_validation_error` ）	API返回格式不符合预期，不要让用户修正输入，建议升级CLI或提交bug反馈
1、2、9	通用/使用/API错误	清晰地向用户上报 `error.message`

retryable

为false的错误绝对不要重试。

Common Mistakes

常见错误

Inventing report answers — if the user didn't provide enough context for a question, ask. Never guess or fabricate.
Retrying auth errors — exit code 4 is never transient. Guide the user to
```
geekbot auth setup
```
instead.
Skipping confirmation for deletes — always show what will be deleted and get explicit approval, even if it feels obvious.
Dumping raw JSON — format output as tables, summaries, or narratives. The user should never see a raw JSON envelope.
Ignoring
error.suggestion
— when a resource isn't found (exit 3), the CLI already lists valid alternatives. Use them.
Asking "are you a manager or reporter?" — the request itself reveals intent. Pattern-match, don't interrogate.

编造报告回答 —— 如果用户没有提供足够的问题上下文，直接询问，永远不要猜测或编造内容。
重试认证错误 —— 退出码4永远不是临时错误，直接引导用户执行
```
geekbot auth setup
```
即可。
删除操作跳过确认 —— 始终展示即将删除的内容并获取明确批准，哪怕看起来是很明显的操作。
输出原始JSON —— 将输出格式化为表格、摘要或叙述内容，永远不要让用户看到原始的JSON封装结果。
忽略
error.suggestion
—— 当资源未找到（退出码3）时，CLI已经列出了有效的替代选项，直接使用即可。
询问“你是管理者还是提交者？” —— 请求本身已经透露了意图，做模式匹配即可，不要询问用户。

Output Patterns

输出模式

CRUD confirmations — brief, factual, include key identifiers:

Created "Sprint Retro" standup (ID 789) in #engineering — Fridays at 15:00 Chicago time with 3 questions.

Lists — concise table: ID, name, channel, schedule. Don't dump raw JSON.

Analytics — narrative summary first, data table for details. Use visualisation (chart/graph) when showing trends over time.

Report drafts — one question per block, clearly labelled with question text and proposed answer. Easy to scan and approve.

Errors — plain language: what happened, why, what to do next. Always use

error.suggestion

when available.

CRUD操作确认 —— 简洁、 factual，包含关键标识：

已创建"Sprint Retro"站会（ID 789），位于#engineering频道 —— 芝加哥时间每周五15:00，包含3个问题。

列表 —— 精简表格：ID、名称、频道、日程，不要输出原始JSON。

分析结果 —— 先给出叙述性摘要，再附上数据表展示细节。展示时间趋势时使用可视化（图表/图形）。

报告草稿 —— 每个问题单独成块，清晰标注问题内容和建议回答，方便用户浏览和批准。

错误 —— 通俗易懂的语言：发生了什么、原因、下一步操作。可用时始终使用

error.suggestion

的内容。