token-budget-advisor

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Token Budget Advisor

Token预算顾问

This skill provides early assessment of token-heavy tasks and recommends chunking strategies to ensure successful completion within context window constraints.

此技能可提前评估高Token消耗任务，并推荐任务拆分策略，以确保在上下文窗口限制内成功完成任务。

When to Use This Skill

何时使用此技能

Trigger this skill before beginning work when you detect:

Multiple file uploads (3+ documents) combined with analysis requests
Requests for "comprehensive", "complete", "thorough", or "full" analysis
Multi-document comparative analysis
Complex workflows requiring 10+ tool calls (extensive web research + synthesis)
Tasks combining heavy research with large artifacts (reports, presentations)
Queries spanning multiple dimensions (temporal + categorical + quantitative)
Requests to "analyze everything" or "create a complete report on all aspects"

当你检测到以下情况时，在开始工作前触发此技能：

结合分析请求的多文件上传（3份及以上文档）
包含“全面的”“完整的”“彻底的”或“全部的”等表述的分析请求
多文档对比分析
需要10次以上工具调用的复杂工作流（大量网页研究+信息整合）
结合大量研究与大型成果（报告、演示文稿）的任务
跨越多个维度的查询（时间+类别+量化）
“分析所有内容”或“创建涵盖所有方面的完整报告”类请求

Core Function

核心功能

This skill serves two purposes:

Early warning system: Assess whether a task will likely exceed token limits
Strategic planning: Provide specific, actionable chunking recommendations

此技能有两个核心用途：

早期预警系统：评估任务是否可能超出Token限制
战略规划：提供具体、可执行的任务拆分建议

Token Estimation Framework

Token估算框架

Quick Assessment Heuristics

快速评估准则

Estimate token consumption using these rough guidelines:

Input costs:

Uploaded document: ~1,000-5,000 tokens each (depending on length)
Web search result: ~500-1,500 tokens
Web fetch (full article): ~2,000-8,000 tokens
Google Drive document: ~1,000-10,000 tokens (varies significantly)

Output costs:

Simple response: 500-2,000 tokens
Detailed analysis: 2,000-5,000 tokens
Long-form report: 5,000-15,000 tokens
Complex artifact (presentation, document): 5,000-20,000 tokens

Tool call overhead:

Each tool call includes the query, results, and reasoning: ~1,000-3,000 tokens average

Warning thresholds:

Caution zone (60-80% of budget): Task is achievable but tight; consider efficiency
Danger zone (80-95% of budget): High risk; strongly recommend chunking
Exceeds budget (95%+ of budget): Task requires chunking; cannot complete in one conversation

使用以下大致准则估算Token消耗：

输入成本：

上传文档：每份约1000-5000 Token（取决于长度）
网页搜索结果：约500-1500 Token
网页抓取（完整文章）：约2000-8000 Token
Google Drive文档：约1000-10000 Token（差异较大）

输出成本：

简单回复：500-2000 Token
详细分析：2000-5000 Token
长篇报告：5000-15000 Token
复杂成果（演示文稿、文档）：5000-20000 Token

工具调用开销：

每次工具调用包含查询、结果和推理：平均约1000-3000 Token

预警阈值：

注意区（预算的60-80%）：任务可完成但空间紧张；需考虑效率优化
危险区（预算的80-95%）：高风险；强烈建议拆分任务
超出预算（95%以上）：任务必须拆分；无法在单次对话中完成

Task Complexity Multipliers

任务复杂度乘数

Apply these mental adjustments:

Synthesis required: Add 30-50% to output estimate (comparing, integrating multiple sources)
Iterative refinement: Add 20-30% (when task involves reviewing and improving)
Multiple formats: Add 20% per additional output type (report + presentation + spreadsheet)

应用以下调整系数：

需要信息整合：在输出估算基础上增加30-50%（对比、整合多来源信息）
迭代优化：增加20-30%（当任务涉及审查和改进时）
多种格式：每增加一种输出类型增加20%（报告+演示文稿+电子表格）

Chunking Strategy Framework

任务拆分策略框架

When a task exceeds token budget, recommend specific chunking approaches. Choose strategies based on task structure:

当任务超出Token预算时，推荐具体的拆分方法。根据任务结构选择策略：

1. Sequential Processing

1. 顺序处理

Best for: Time-series data, chronological analysis, ordered workflows

Pattern:

"This analysis of 12 months of data will exceed our token budget. I recommend we split it into quarters:
- Part 1: Q1-Q2 analysis (Jan-Jun)
- Part 2: Q3-Q4 analysis (Jul-Dec)  
- Part 3: Synthesis and recommendations

Should I start with Part 1?"

When to use:

Historical data analysis
Period-over-period comparisons
Multi-phase projects

最适用于： 时间序列数据、 chronological分析、有序工作流

示例话术：

"对12个月数据的分析将超出我们的Token预算。我建议按季度拆分：
- 第一部分：Q1-Q2分析（1-6月）
- 第二部分：Q3-Q4分析（7-12月）  
- 第三部分：信息整合与建议

我可以从第一部分开始吗？"

适用场景：

历史数据分析
同期对比分析
多阶段项目

2. Dimensional Breakdown

2. 维度拆分

Best for: Multi-faceted analysis, different aspects of same topic

Pattern:

"A complete market analysis covering financial, competitive, regulatory, and technological factors will strain our token budget. Let's break it into:
- Session 1: Financial performance and market size
- Session 2: Competitive landscape and positioning
- Session 3: Regulatory environment and compliance
- Session 4: Technology trends and synthesis

Which dimension should we tackle first?"

When to use:

Multi-stakeholder analysis
Different analytical lenses on same subject
Complex business cases

最适用于： 多方面分析、同一主题的不同维度

示例话术：

"涵盖财务、竞争、监管和技术因素的完整市场分析会让Token预算吃紧。我们可以拆分为：
- 环节1：财务表现与市场规模
- 环节2：竞争格局与定位
- 环节3：监管环境与合规性
- 环节4：技术趋势与信息整合

我们先处理哪个维度？"

适用场景：

多利益相关方分析
同一主题的不同分析视角
复杂商业案例

3. Depth Progression

3. 深度递进

Best for: Tasks requiring outline → draft → refinement

Pattern:

"Creating a comprehensive 50-slide presentation with detailed research will exceed our budget. I recommend:
- Round 1: Build structure and outline (30 min)
- Round 2: Develop content for slides 1-25 (45 min)
- Round 3: Develop content for slides 26-50 (45 min)
- Round 4: Refinement pass (30 min)

Let's start with the outline?"

When to use:

Large documents or presentations
When quality refinement is important
Creative projects benefiting from iteration

最适用于： 需要大纲→草稿→优化的任务

示例话术：

"创建包含详细研究的50页演示文稿会超出预算。我建议：
- 第一轮：构建结构和大纲（30分钟）
- 第二轮：制作第1-25页内容（45分钟）
- 第三轮：制作第26-50页内容（45分钟）
- 第四轮：优化完善（30分钟）

我们先从大纲开始？"

适用场景：

大型文档或演示文稿
注重质量优化的任务
可从迭代中受益的创意项目

4. Subset Sampling

4. 子集抽样

Best for: Large document sets where representative sampling works

Pattern:

"Analyzing all 15 contracts will exceed our budget. I suggest:
- Part 1: Analyze 5 representative contracts (different types/dates)
- Part 2: Based on patterns found, confirm with 5 more
- Part 3: Quick scan of remaining 5 for exceptions, then synthesize

This gives thorough coverage while managing tokens. Sound good?"

When to use:

Document review at scale
Pattern identification across many files
Risk-based sampling approaches

最适用于： 可采用代表性抽样的大型文档集

示例话术：

"分析全部15份合同会超出预算。我建议：
- 第一部分：分析5份代表性合同（不同类型/日期）
- 第二部分：基于发现的模式，再分析5份
- 第三部分：快速扫描剩余5份以查找例外情况，然后整合信息

这种方式既能保证全面覆盖，又能管控Token消耗。可以吗？"

适用场景：

大规模文档审查
跨多文件的模式识别
基于风险的抽样方法

5. Parallel Track Processing

5. 并行追踪处理

Best for: Independent workstreams that can be combined later

Pattern:

"Comparing our product vs 5 competitors across features, pricing, and positioning is too large for one session. Let's split by competitor:
- Session 1: Competitors A & B full analysis
- Session 2: Competitors C & D full analysis  
- Session 3: Competitor E + synthesis matrix

Each session stays focused and manageable."

When to use:

Comparative analysis
Multiple independent subjects
When parts don't need each other's context

最适用于： 可后续合并的独立工作流

示例话术：

"对比我们的产品与5个竞争对手的功能、定价和定位，单次会话无法完成。我们按竞争对手拆分：
- 环节1：竞争对手A和B的完整分析
- 环节2：竞争对手C和D的完整分析  
- 环节3：竞争对手E分析+整合矩阵

每个环节都聚焦且易于管理。"

适用场景：

对比分析
多个独立主题
各部分无需彼此上下文的任务

Communication Guidelines

沟通准则

Messaging Framework

话术框架

When recommending chunking, use this structure:

Acknowledge the request clearly
Provide token budget assessment (brief, 1 sentence)
Recommend specific chunking approach (numbered list, 2-4 parts)
Ask for confirmation to proceed (keep user in control)

Example:

I'll help you analyze these 8 financial reports and create a comprehensive presentation. 
This task will exceed our token budget given the research and artifact creation required. 
I recommend splitting it into:
1. Reports 1-4: Analysis and key findings
2. Reports 5-8: Analysis and key findings  
3. Synthesize all findings into presentation

Should I start with reports 1-4?

推荐任务拆分时，使用以下结构：

清晰确认请求
简要说明Token预算评估（1句话）
推荐具体拆分方法（编号列表，2-4个部分）
请求确认以推进（让用户掌控进度）

示例：

我会帮你分析这8份财务报告并创建一份全面的演示文稿。
考虑到所需的研究和成果创建工作，此任务将超出我们的Token预算。
我建议拆分为：
1. 报告1-4：分析与关键发现
2. 报告5-8：分析与关键发现  
3. 将所有发现整合为演示文稿

我可以从报告1-4开始吗？

What NOT to Do

禁忌事项

❌ Don't over-explain token budgets or get technical about context windows ❌ Don't apologize excessively or sound limiting ❌ Don't provide vague suggestions like "maybe split this up somehow" ❌ Don't start work and then stop mid-task saying "we've run out of tokens"

✅ Do be matter-of-fact and solution-oriented ✅ Do provide specific, actionable breakdowns ✅ Do keep the momentum going toward task completion ✅ Do frame chunking as a quality improvement (thoroughness) not limitation

❌ 不要过度解释Token预算或深入讲解上下文窗口的技术细节 ❌ 不要过度道歉或表现出局限性 ❌ 不要给出模糊建议，比如“也许可以想办法拆分一下” ❌ 不要开始工作后中途停止说“我们的Token用完了”

✅ 要实事求是，以解决方案为导向 ✅ 要提供具体、可执行的拆分方案 ✅ 要保持推进任务完成的势头 ✅ 要将任务拆分表述为提升质量（更彻底）而非限制

Handling Edge Cases

边缘场景处理

User Insists on Single Session

用户坚持单次会话完成

If user pushes back on chunking:

"I understand you'd prefer this in one go. I'll do my best to complete it, but I may need to:
- Prioritize the most critical elements
- Provide a condensed version
- Focus on breadth over depth in some areas

Let me start and we'll see how far we can get. What aspects are highest priority?"

如果用户反对拆分：

"我理解你希望一次性完成。我会尽力完成，但可能需要：
- 优先处理最关键的内容
- 提供精简版结果
- 在某些领域侧重广度而非深度

我现在开始，看看能完成多少。哪些方面是最高优先级？"

Task Becomes Too Large Mid-Stream

任务进行中变得过大

If partway through, token budget becomes concerning:

"I'm about halfway through and we're approaching token limits. I have two options:
1. Complete this current section and continue in a fresh conversation (recommended - maintains quality)
2. Accelerate through remaining sections with lighter analysis

Which approach works better for you?"

如果在任务中途，Token预算出现问题：

"我已完成约一半工作，即将达到Token限制。我有两个选项：
1. 完成当前部分，在新会话中继续（推荐 - 保证质量）
2. 加快剩余部分的处理，简化分析

哪种方式更适合你？"

Uncertain Estimation

估算不确定

When task scope is ambiguous:

"I want to make sure we complete this successfully. The scope could go in different directions. Could you clarify:
- [Specific question about depth]
- [Specific question about breadth]

This helps me gauge whether we should chunk this task."

当任务范围不明确时：

"我想确保我们能成功完成任务。任务范围可能有不同方向。你能澄清一下：
- [关于深度的具体问题]
- [关于广度的具体问题]

这有助于我判断是否需要拆分任务。"

Integration with Other Skills

与其他技能的集成

This skill works in conjunction with domain-specific skills:

Before heavy document analysis: Check token budget, then use docx/pdf/xlsx skills
Before comprehensive research: Assess scope, then execute research process
Before complex artifacts: Plan chunking, then use pptx/docx/xlsx creation skills

Think of this skill as a "pre-flight check" before embarking on token-intensive tasks.

此技能可与特定领域技能配合使用：

在大型文档分析前：检查Token预算，然后使用docx/pdf/xlsx技能
在全面研究前：评估范围，然后执行研究流程
在创建复杂成果前：规划拆分，然后使用pptx/docx/xlsx创建技能

将此技能视为执行高Token消耗任务前的“预检步骤”。

Examples in Action

实际应用示例

Example 1: Multi-Document Analysis

示例1：多文档分析

User query: "Analyze all these uploaded contracts and tell me the common terms and differences" [User has uploaded 12 PDF contracts]

Response: "I'll help you analyze these 12 contracts. Given the volume, I recommend we process this in batches to ensure thorough analysis:

Contracts 1-4: Extract key terms, obligations, and unique clauses
Contracts 5-8: Same analysis
Contracts 9-12: Same analysis
Synthesis: Common terms across all + key differences

This ensures I can give each contract proper attention. Should I start with contracts 1-4?"

用户查询： "分析所有上传的这些合同，告诉我共同条款和差异" [用户已上传12份PDF合同]

回复： "我会帮你分析这12份合同。考虑到数量，我建议分批处理以确保分析彻底：

合同1-4：提取关键条款、义务和独特条款
合同5-8：相同分析
合同9-12：相同分析
整合：所有合同的共同条款+关键差异

我可以从合同1-4开始吗？"

Example 2: Comprehensive Research Report

示例2：全面研究报告

User query: "Research the AI chip market and create a detailed report covering market size, key players, technology trends, and 5-year forecast"

Response: "I'll create a comprehensive AI chip market report. This research and report creation will be substantial, so I recommend:

Market overview: Size, growth, segments (research + draft)
Competitive landscape: Key players, market share, strategies (research + draft)
Technology trends: Current developments, emerging tech (research + draft)
Future outlook: 5-year forecast, implications (research + draft)
Final report assembly: Executive summary, polish, formatting

Each section gets thorough research and quality writing. Should I begin with the market overview?"

用户查询： "研究AI芯片市场，创建一份涵盖市场规模、关键玩家、技术趋势和5年预测的详细报告"

回复： "我会创建一份全面的AI芯片市场报告。这项研究和报告创建工作体量较大，我建议拆分为：

市场概述：规模、增长、细分领域（研究+草稿）
竞争格局：关键玩家、市场份额、策略（研究+草稿）
技术趋势：当前发展、新兴技术（研究+草稿）
未来展望：5年预测、影响（研究+草稿）
最终报告整合：执行摘要、润色、格式调整

每个部分都能得到充分研究和高质量撰写。我可以从市场概述开始吗？"

Example 3: Simple Task (No Chunking)

示例3：简单任务（无需拆分）

User query: "Summarize this 10-page PDF and give me the key takeaways"

Response: [No trigger - proceed normally without invoking this skill] "I'll read through the PDF and extract the key points for you."

Rationale: Single document summary is well within normal token budget.

用户查询： "总结这份10页的PDF，告诉我关键要点"

回复： [不触发此技能 - 正常执行] "我会通读这份PDF并为你提取关键要点。"

理由：单文档摘要完全在正常Token预算范围内。

Skill Maintenance

技能维护

This skill should be updated when:

Token budget limits change
New patterns of token-heavy tasks emerge
Chunking strategies prove ineffective in practice
User feedback indicates communication could be clearer

当出现以下情况时，应更新此技能：

Token预算限制变更
出现新的高Token消耗任务模式
任务拆分策略在实践中被证明无效
用户反馈表明沟通方式需更清晰