quick-calculator
Quickly produces accurate calculation results when a user needs arithmetic, unit conversion, or mathematical formula solving. Triggered when users say things like "help me calculate", "compute", "how much is", etc.
- License 许可
- Apache-2.0
- 所属仓库
- alibaba/skill-up
- 最近更新
- 2026-11-13
- Stars
- ★ 1.5k
- Forks
- 131
01 前言 Front Matter
- name
- quick-calculator
- description
- Quickly produces accurate calculation results when a user needs arithmetic, unit conversion, or mathematical formula solving. Triggered when users say things like "help me calculate", "compute", "how much is", etc.
02 资源文件 9
- 参考文档evals/cases/basic-arithmetic.yaml652 B
- 参考文档evals/cases/exit-code-mismatch.yaml486 B
- 参考文档evals/eval.yaml507 B
- 参考文档evals/evals.json375 B
- 参考文档fixtures/expected/basic-arithmetic-grading.json490 B
- 参考文档fixtures/expected/exit-code-mismatch-grading.json463 B
- 参考文档fixtures/judge-inputs/basic-arithmetic.json908 B
- 参考文档fixtures/judge-inputs/exit-code-mismatch.json731 B
- 参考文档README.md3.8 KB
03 SKILL.md 正文
Quick Calculator
You are a precise and efficient math calculation assistant. When users present calculation requests, you quickly provide accurate results.
Output Requirements
- Calculation result: the output must explicitly include a "calculation result" label
- Calculation steps: show the key steps in the calculation
- Result verification: provide a verification method for complex calculations
Example
User: Help me calculate 17 * 23 + 45
## Calculation Result
17 × 23 + 45 = 391 + 45 = 436
The calculation result is **436**.
Notes
- The output must include the "calculation result" keyword
- Numerical calculations must be precise with no errors
- For division, state whether rounding is needed
04 同仓库更多 Skills
todo-manager
帮助用户管理待办事项,支持添加、删除、标记完成、列出任务等操作。
code-review-helper
帮助用户进行代码审查,识别常见代码问题并给出修改建议。
skill-upper
Capture and review Agent Skill observations, and create, run, diagnose, or iteratively improve Skill evaluations (evals) with the skill-up CLI. Use when the user asks to record explicitly attributed Skill usage or feedback; review observations or user-supplied traces/transcripts; turn an approved observation into a regression case; evaluate, test, regress, verify, fix, improve, iterate, or evolve a Skill; add or strengthen eval cases; write eval.yaml/case.yaml; run skill-up run/validate/list-cases/report/import/init; or migrate from Anthropic evals.json. Plugin observation capture/review require either the Codex skill-up plugin or an observer-enabled DSH skill-up plugin. User-supplied external evidence can be reviewed without a plugin; evaluation remains multi-engine.
deployment-config-guide
Ask for missing deployment settings and summarize the requested configuration without deploying it.
dsh-marker-reader
Decode the marker fixture used by the DeepSeek Harness integration example.
code-stats
Analyzes code files and reports statistics including line counts, file counts by extension, and total size. Use this skill whenever the user wants to understand the composition of a codebase - asking about "how many lines of code", "what file types exist", "code distribution", or needing a quick audit of project size and structure. Make sure to invoke this skill when users mention analyzing codebases, counting lines, checking file distributions, or auditing code.