帮助用户在回答前选择简短、标准或详细版本,控制回复深度与 token 用量。
复制安装指令,让 AI 自动完成配置 · 推荐新手
请帮我安装 askskill 上的 "token-budget-advisor" 技能: 1. 下载 https://raw.githubusercontent.com/affaan-m/ECC/main/skills/token-budget-advisor/SKILL.md 2. 保存为 ~/.claude/skills/token-budget-advisor/SKILL.md 3. 装好后重载技能,告诉我可以用了
我想控制 token 预算。请先给我三个选项:精简版、标准版、详细版,再等我选择后回答。
先提供不同回答深度及大致成本说明,等待用户选择后再展开回答。
请用尽量少的 token 总结这篇文章,并告诉我如果改成详细版会多讲哪些内容。
输出精简总结,并补充详细版可能增加的要点范围说明。
这个问题请按 100、300、800 token 三档说明你会怎么回答,让我选一个。
给出三档回答策略或大纲,体现不同篇幅下的信息密度差异。
Intercept the response flow to offer the user a choice about response depth before Claude answers.
Do not trigger when: user already set a level this session (maintain it silently), or the answer is trivially one line.
Use the repository's canonical context-budget heuristics to estimate the prompt's token count mentally.
Use the same calibration guidance as context-budget:
words × 1.3chars / 4For mixed content, use the dominant content type and keep the estimate heuristic.
Classify the prompt, then apply the multiplier range to get the full response window:
| Complexity |
|---|
| Multiplier range |
|---|
| Example prompts |
|---|
| Simple | 3× – 8× | "What is X?", yes/no, single fact |
| Medium | 8× – 20× | "How does X work?" |
| Medium-High | 10× – 25× | Code request with context |
| Complex | 15× – 40× | Multi-part analysis, comparisons, architecture |
| Creative | 10× – 30× | Stories, essays, narrative writing |
Response window = input_tokens × mult_min to input_tokens × mult_max (but don’t exceed your model’s configured output-token limit).
Present this block before answering, using the actual estimated numbers:
Analyzing your prompt...
Input: ~[N] tokens | Type: [type] | Complexity: [level] | Language: [lang]
Choose your depth level:
[1] Essential (25%) -> ~[tokens] Direct answer only, no preamble
[2] Moderate (50%) -> ~[tokens] Answer + context + 1 example
[3] Detailed (75%) -> ~[tokens] Full answer with alternatives
[4] Exhaustive (100%) -> ~[tokens] Everything, no limits
Which level? (1-4 or say "25% depth", "50% depth", "75% depth", "100% depth")
Precision: heuristic estimate ~85-90% accuracy (±15%).
Level token estimates (within the response window):
min + (max - min) × 0.25min + (max - min) × 0.50min + (max - min) × 0.75max| Level | Target length | Include | Omit |
|---|---|---|---|
| 25% Essential | 2-4 sentences max | Direct answer, key conclusion | Context, examples, nuance, alternatives |
| 50% Moderate | 1-3 paragraphs | Answer + necessary context + 1 example | Deep analysis, edge cases, references |
| 75% Detailed | Structured response | Multiple examples, pros/cons, alternatives | Extreme edge cases, exhaustive references |
| 100% Exhaustive | No restriction | Everything — full analysis, all code, all perspectives | Nothing |
If the user already signals a level, respond at that level immediately without asking:
| What they say | Level |
|---|---|
| "1" / "25% depth" / "short version" / "brief answer" / "tldr" | 25% |
…
帮助开发者使用 Bun 进行运行、打包、测试与依赖管理,并评估替代 Node 的时机。
用于创建、编辑与优化AI技能,并评测其效果与触发准确性。