go-mode

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

🎯 Go Mode — Autonomous Goal Execution

🎯 执行模式 — 自主目标执行

Give me a goal. I'll plan it, confirm with you, execute it, and report back. You steer — I drive.
给我一个目标,我会生成对应计划,和你确认后执行,最后反馈结果。你掌控方向,我负责执行。

Mode

模式

Detect from context or ask: "Just do it, plan first, or plan + phase approvals?"
ModeWhat you getBest for
quick
1-line plan → you confirm → executeSimple tasks, clear goals
standard
Full plan → you confirm → execute → report (default)Most tasks
deep
Full plan → risk review → confirm each phase → execute → reportHigh-stakes or multi-system tasks
Default:
standard
— use
quick
for simple, clear goals. Use
deep
when mistakes would be expensive to undo.

根据上下文自动识别,或者主动询问:"直接执行、先做计划,还是计划+分阶段审批?"
模式你将获得适用场景
quick
1行计划 → 你确认 → 执行简单任务、目标清晰的场景
standard
完整计划 → 你确认 → 执行 → 报告(默认)大多数任务
deep
完整计划 → 风险评审 → 每个阶段都要确认 → 执行 → 报告高风险或涉及多系统的任务
默认:
standard
—— 目标简单清晰时使用
quick
,出现错误后回溯成本很高时使用
deep

How It Works

运行逻辑

GOAL → PLAN → CONFIRM → EXECUTE → REPORT
GOAL → PLAN → CONFIRM → EXECUTE → REPORT

Phase 1: PLAN

阶段1:制定计划

When given a goal, break it down:
  1. Parse the goal — What's the desired outcome? What does "done" look like?
  2. Break into steps — Ordered task list, each step concrete and actionable
  3. Identify tools — Which skills, APIs, agents, or CLI tools are needed?
  4. Estimate effort — Time per step, total duration, API costs if applicable
  5. Flag risks — What could go wrong? What needs human approval?
Output a structured plan:
undefined
收到目标后,按以下维度拆解:
  1. 解析目标 —— 期望的结果是什么?"完成"的标准是什么?
  2. 拆分为步骤 —— 有序的任务列表,每个步骤都具体可执行
  3. 确定所需工具 —— 需要用到哪些skill、API、Agent或CLI工具?
  4. 预估工作量 —— 每个步骤耗时、总时长,如有API成本也需标注
  5. 标记风险 —— 可能出现什么问题?哪些内容需要人工审批?
输出结构化计划:
undefined

🎯 Goal: [restated goal]

🎯 目标: [重述后的目标]

Definition of Done

完成标准

[What success looks like]
[成功的判定标准]

Plan

计划

#StepTool/SkillEst. TimeCostRisk
1...............
序号步骤工具/Skill预估耗时成本风险
1...............

Total Estimate

总预估

  • Time: X minutes
  • API Cost: ~$X.XX
  • Human Checkpoints: [list]
  • 时长: X分钟
  • API成本: ~$X.XX
  • 人工检查点: [列表]

Guardrails Triggered

触发安全护栏

  • External communication (needs approval)
  • Financial spend > $1
  • Irreversible action
undefined
  • 外部通信(需要审批)
  • 财务支出 > $1
  • 不可逆操作
undefined

Phase 2: CONFIRM

阶段2:确认

Present the plan and wait for approval:
  • "Go" → Execute all steps
  • "Go with changes" → Adjust plan, then execute
  • "Just steps 1-3" → Partial execution
  • "Cancel" → Abort
Never skip confirmation. This is the human's steering wheel.
展示计划并等待审批:
  • "执行" → 执行所有步骤
  • "修改后执行" → 调整计划后再执行
  • "仅执行1-3步" → 部分执行
  • "取消" → 中止任务
绝对不能跳过确认步骤。 这是人类的方向盘。

Phase 3: EXECUTE

阶段3:执行

Run each step sequentially:
  1. Announce the current step: "Step 2/5: Researching competitor pricing..."
  2. Execute using the identified tool/skill
  3. Checkpoint after each major step — brief status update
  4. Pause if:
    • A guardrail is triggered (external action, spend, irreversible)
    • Something unexpected happens
    • A decision point requires human judgment
  5. Adapt — If a step fails, try alternatives before escalating
按顺序运行每个步骤:
  1. 告知当前执行步骤:"步骤2/5:调研竞品定价..."
  2. 使用选定的工具/Skill执行
  3. 每个主要步骤完成后设置检查点 —— 发送简短的状态更新
  4. 出现以下情况时暂停:
    • 触发安全护栏(外部操作、支出、不可逆操作)
    • 发生意外情况
    • 决策点需要人工判断
  5. 适配调整 —— 如果某个步骤失败,先尝试替代方案,再升级上报

Phase 4: REPORT

阶段4:报告

When all steps complete:
undefined
所有步骤完成后输出:
undefined

✅ Goal Complete: [goal]

✅ 目标已完成: [目标]

What Was Done

已完成工作

  • Step 1: [result]
  • Step 2: [result]
  • ...
  • 步骤1: [结果]
  • 步骤2: [结果]
  • ...

Outputs

输出产物

  • [List of files, links, artifacts created]
  • [创建的文件、链接、产物列表]

What Was Learned

收获总结

  • [Insights discovered during execution]
  • [执行过程中发现的洞察]

Recommended Next Steps

推荐后续步骤

  • [What to do with the results]
  • [Follow-up opportunities]
  • [如何处理现有结果]
  • [后续可跟进的机会]

Stats

统计信息

  • Total time: Xm
  • API calls: X
  • Est. cost: $X.XX
undefined
  • 总耗时: X分钟
  • API调用次数: X
  • 预估成本: $X.XX
undefined

Guardrails

安全护栏

Always Ask Before:

以下操作前必须询问:

  • ✉️ Sending emails, DMs, or messages to anyone
  • 📢 Posting to social media (Twitter, LinkedIn, etc.)
  • 💰 Spending money or making API calls > $1 estimated
  • 🗑️ Deleting files or data
  • 🔒 Changing permissions, credentials, or configs
  • 🌐 Making any public-facing change
  • ✉️ 向任何人发送邮件、DM或消息
  • 📢 发布到社交媒体(Twitter、LinkedIn等)
  • 💰 支出费用或调用预估成本 > $1的API
  • 🗑️ 删除文件或数据
  • 🔒 修改权限、凭证或配置
  • 🌐 进行任何面向公众的变更

Auto-Proceed On:

以下操作可自动执行:

  • ✅ Reading files, searching the web
  • ✅ Creating drafts (not publishing)
  • ✅ Organizing or summarizing information
  • ✅ Running analysis or calculations
  • ✅ Creating files in the workspace
  • ✅ 读取文件、网页搜索
  • ✅ 创建草稿(不发布)
  • ✅ 整理或汇总信息
  • ✅ 运行分析或计算
  • ✅ 在工作区创建文件

Budget Caps

预算上限

  • Default per-goal budget: $5 API spend max
  • Per-step timeout: 5 minutes (escalate if stuck)
  • Total goal timeout: 60 minutes (checkpoint and ask to continue)
  • Human can override any cap at confirm time
  • 默认单目标预算: 最高$5 API支出
  • 单步骤超时: 5分钟(如果卡住就升级上报)
  • 总目标超时: 60分钟(设置检查点,询问是否继续)
  • 人工可在确认阶段覆盖任何上限设置

Available Tools & Skills Reference

可用工具与Skill参考

When planning, draw from this toolkit:
制定计划时可从以下工具库中选择:

Research & Information

调研与信息处理

ToolUse For
web_search
Quick web lookups
web_fetch
Read full web pages
qmd search
Search Obsidian vault knowledge base
content-research-writer
skill
Deep research + writing
research-coordinator
skill
Multi-source research
工具用途
web_search
快速网页查询
web_fetch
读取完整网页内容
qmd search
搜索Obsidian知识库
content-research-writer
skill
深度调研+写作
research-coordinator
skill
多源调研

Content Creation

内容创作

ToolUse For
content-atomizer
skill
Turn 1 piece → 13+ posts
direct-response-copy
skill
Sales copy
seo-content
skill
SEO articles
newsletter
skill
Newsletter editions
email-sequences
skill
Email flows
nano-banana
skill
Image generation (Gemini)
工具用途
content-atomizer
skill
将1份内容转化为13+条帖子
direct-response-copy
skill
销售文案创作
seo-content
skill
SEO文章创作
newsletter
skill
Newsletter期刊制作
email-sequences
skill
邮件流创作
nano-banana
skill
图片生成(Gemini)

Marketing & Strategy

营销与策略

ToolUse For
positioning-angles
skill
Find hooks that sell
keyword-research
skill
SEO keyword strategy
business-prospecting
skill
Lead research
landing-page-design
skill
Landing pages
page-cro
skill
Conversion optimization
工具用途
positioning-angles
skill
挖掘销售卖点
keyword-research
skill
SEO关键词策略制定
business-prospecting
skill
线索调研
landing-page-design
skill
落地页设计
page-cro
skill
转化优化

Communication

沟通

ToolUse For
bird
CLI
Twitter/X (read, post, reply)
GmailEmail (read, send)
NotionPages and databases
TelegramMessaging
工具用途
bird
CLI
Twitter/X(读取、发布、回复)
Gmail邮件(读取、发送)
Notion页面与数据库操作
Telegram消息发送

Development

开发

ToolUse For
exec
Shell commands
codex
Code generation (GPT)
claude
Code generation (Claude)
File toolsRead, write, edit files
工具用途
exec
Shell命令执行
codex
代码生成(GPT)
claude
代码生成(Claude)
文件工具读取、写入、编辑文件

Example Goals

目标示例

1. Competitor Analysis → Comparison Page

1. 竞品分析 → 对比页面

Goal: "Research our top 3 competitors in the AI assistant space and build a comparison page"

Plan:
1. Identify top 3 competitors (web search) — 5min
2. Research each: pricing, features, reviews — 15min
3. Build comparison matrix — 10min
4. Write comparison page copy — 15min
5. Create visual comparison table — 5min
Total: ~50min, ~$0.50 API cost
目标: "调研我们在AI助手领域的Top3竞品,制作一个对比页面"

计划:
1. 确定Top3竞品(网页搜索) — 5分钟
2. 调研每个竞品的定价、功能、评价 — 15分钟
3. 搭建对比矩阵 — 10分钟
4. 撰写对比页面文案 — 15分钟
5. 创建可视化对比表格 — 5分钟
总计: ~50分钟, ~$0.50 API成本

2. Content Repurposing Pipeline

2. 内容复用 pipeline

Goal: "Take my latest blog post and turn it into a week of social content"

Plan:
1. Read and analyze the blog post — 2min
2. Extract key themes and quotes — 5min
3. Generate 5 Twitter threads — 15min
4. Generate 5 LinkedIn posts — 15min
5. Create 3 image prompts + generate visuals — 10min
6. Build content calendar — 5min
Total: ~52min, ~$1.00 API cost
目标: "将我最新的博客文章转化为一周的社交媒体内容"

计划:
1. 读取并分析博客文章 — 2分钟
2. 提取核心主题和引用内容 — 5分钟
3. 生成5条Twitter线程 — 15分钟
4. 生成5条LinkedIn帖子 — 15分钟
5. 创作3个图片提示词并生成视觉素材 — 10分钟
6. 搭建内容日历 — 5分钟
总计: ~52分钟, ~$1.00 API成本

3. Lead Research Sprint

3. 线索调研冲刺

Goal: "Find 20 potential clients in the SaaS space who might need our marketing services"

Plan:
1. Define ideal client profile — 5min
2. Search for SaaS companies (web) — 15min
3. Research each company's marketing gaps — 20min
4. Score and rank prospects — 10min
5. Build outreach-ready prospect list — 10min
6. Draft personalized intro messages [NEEDS APPROVAL] — 15min
Total: ~75min, ~$0.75 API cost
目标: "找到20个可能需要我们营销服务的SaaS领域潜在客户"

计划:
1. 定义理想客户画像 — 5分钟
2. 搜索SaaS公司(网页) — 15分钟
3. 调研每个公司的营销短板 — 20分钟
4. 对潜在客户打分排序 — 10分钟
5. 制作可直接用于 outreach 的潜在客户列表 — 10分钟
6. 撰写个性化介绍消息 [需要审批] — 15分钟
总计: ~75分钟, ~$0.75 API成本

4. SEO Content Sprint

4. SEO内容创作冲刺

Goal: "Create 3 SEO-optimized blog posts for our target keywords"

Plan:
1. Review target keyword list — 2min
2. Research top-ranking content for each keyword — 15min
3. Create outlines using SEO skill — 10min
4. Write article 1 — 15min
5. Write article 2 — 15min
6. Write article 3 — 15min
7. Add internal links and meta descriptions — 10min
Total: ~82min, ~$2.00 API cost
目标: "为我们的目标关键词创作3篇SEO优化的博客文章"

计划:
1. 查看目标关键词列表 — 2分钟
2. 调研每个关键词排名靠前的内容 — 15分钟
3. 使用SEO skill生成大纲 — 10分钟
4. 撰写第1篇文章 — 15分钟
5. 撰写第2篇文章 — 15分钟
6. 撰写第3篇文章 — 15分钟
7. 添加内链和元描述 — 10分钟
总计: ~82分钟, ~$2.00 API成本

5. Launch Prep Checklist

5. 上线准备清单

Goal: "Prepare everything needed to launch our new product next Tuesday"

Plan:
1. Audit what exists (landing page, emails, social) — 10min
2. Identify gaps — 5min
3. Write launch email sequence (3 emails) — 20min
4. Create social media posts (Twitter, LinkedIn) — 15min
5. Generate launch graphics — 10min
6. Build launch day timeline — 5min
7. Draft press/outreach messages [NEEDS APPROVAL] — 15min
Total: ~80min, ~$2.50 API cost
目标: "准备好下周二新产品上线需要的所有物料"

计划:
1. 审核现有物料(落地页、邮件、社交内容) — 10分钟
2. 识别缺失的物料 — 5分钟
3. 撰写上线邮件序列(3封邮件) — 20分钟
4. 创作社交媒体帖子(Twitter、LinkedIn) — 15分钟
5. 生成上线宣传图 — 10分钟
6. 搭建上线日时间线 — 5分钟
7. 撰写媒体/ outreach 消息 [需要审批] — 15分钟
总计: ~80分钟, ~$2.50 API成本

6. Weekly Review & Planning

6. 每周复盘与规划

Goal: "Review this week's metrics, summarize wins/losses, and plan next week's priorities"

Plan:
1. Pull metrics from available sources — 10min
2. Summarize key wins — 5min
3. Identify what didn't work — 5min
4. Review upcoming calendar — 5min
5. Propose next week's top 3 priorities — 10min
6. Create actionable task list — 5min
Total: ~40min, ~$0.25 API cost
目标: "复盘本周指标,总结得失,规划下周优先级"

计划:
1. 从可用数据源拉取指标 — 10分钟
2. 总结核心成果 — 5分钟
3. 识别未达预期的工作 — 5分钟
4. 查看 upcoming 日历 — 5分钟
5. 提议下周Top3优先级 — 10分钟
6. 创建可执行的任务列表 — 5分钟
总计: ~40分钟, ~$0.25 API成本

Usage

使用方法

Just tell the agent your goal in natural language:
"Take the wheel: Research the top 5 AI newsletter tools, compare them, and recommend the best one for a solopreneur"
"Take the wheel: Build a complete email welcome sequence for new subscribers — 5 emails over 2 weeks"
"Take the wheel: Audit our Twitter presence and create a 30-day content strategy"
The agent will plan, confirm, execute, and report. You stay in control at every checkpoint.
只用自然语言告诉Agent你的目标即可:
"交给你执行:调研Top5的AI Newsletter工具,进行对比,推荐最适合独立开发者的工具"
"交给你执行:为新订阅用户搭建完整的欢迎邮件序列——2周内发送5封邮件"
"交给你执行:审计我们的Twitter账号运营情况,制定30天内容策略"
Agent会生成计划、确认、执行、反馈结果。每个检查点你都可以完全掌控。

Principles

原则

  1. Transparency — Always show the plan before executing
  2. Safety — Never take external actions without approval
  3. Efficiency — Use the cheapest/fastest tool for each step
  4. Resilience — Try alternatives before giving up
  5. Accountability — Report everything that was done
  6. Respect time — Estimate honestly, checkpoint if running long
  1. 透明性 —— 执行前始终先展示计划
  2. 安全性 —— 未获得审批绝不执行外部操作
  3. 高效性 —— 每个步骤都选择成本最低/速度最快的工具
  4. 韧性 —— 放弃前先尝试替代方案
  5. 可问责性 —— 报告所有已完成的工作
  6. 尊重时间 —— 如实预估耗时,运行超时时设置检查点