dev-sciomc
Scientific method scaffolding — hypothesis → experiment → evidence → conclusion. Use when you need rigorous causal reasoning rather than vibes-based debugging.
适合你,如果需要在调试或研究中应用科学方法而非直觉判断。
/ 通过 npx 安装 校验哈希
npx oh-my-skill add evolution-foundation/evo-nexus/dev-sciomc/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- evolution-foundation/evo-nexus/dev-sciomc/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify evolution-foundation/evo-nexus/dev-sciomc安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
509GitHub stars
~438上下文体积 · 单文件
索引托管
怎么用
商店整理自技能原文 · 版本 7f5dd76 · 表述以原文为准它做什么
装上后,Claude 会按照科学方法框架进行工程调查:先明确一个可证伪的假设,然后设计实验(包括变量、对照组和样本量),收集原始数据,进行统计分析,最后给出暂定结论和局限性。
什么时候触发
当你需要严谨的因果推理(而非凭感觉调试)时触发,例如性能优化、A/B 比较或高成本错误场景。
装好后可以这样说
Claude 会生成假设、实验步骤和对照方案。
触发完整的科学调查流程。
技能原文 SKILL.md
Dev Sciomc (Scientific Method)
Derived from oh-my-claudecode (MIT, Yeachan Heo). Adapted for the EvoNexus Engineering Layer.
Scientific method discipline applied to engineering investigations. Forces explicit hypothesis statement, experimental design, evidence collection, and provisional conclusions.
Use When
- Investigation requires rigor beyond "let me try X"
- Performance optimization (you need controls and measurements, not guesses)
- A/B comparison of two implementations
- Anything where the cost of being wrong is high
Do Not Use When
- Trivial bug → use
@hawk-debugger - Pure exploration → use
@scout-explorer
Workflow
Phase 1 — Hypothesis
- State the hypothesis as a falsifiable claim
- "X is faster than Y" not "X feels faster"
- Identify the dependent variable, independent variables, controls
Phase 2 — Experiment Design
- What measurement will prove/disprove the hypothesis?
- What's the minimum sample size for statistical significance?
- What confounders need to be controlled?
Phase 3 — Evidence Collection
- Run the experiment
- Collect raw data
- Note environmental factors that could affect results
Phase 4 — Analysis
- Apply statistical tests (delegate to
@prism-scientist) - Calculate effect size, CI, p-value
- Compare against the hypothesis
Phase 5 — Conclusion
- Provisional, never absolute
- State limitations
- Identify follow-up experiments
Output
Saved to workspace/development/research/[C]sciomc-{topic}-{date}.md:
## Scientific Investigation — {topic}
### Hypothesis
{Falsifiable claim}
### Experimental Design
- Dependent variable: {what we measure}
- Independent variables: {what we vary}
- Controls: {what we hold constant}
- Sample size: {N}
### Method
{Step-by-step protocol}
### Results
{Raw data summary}
### Statistical Analysis
[delegated to @prism-scientist]
### Conclusion
{Provisional conclusion + limitations}
### Follow-ups
- {next experiment}
Pairs With
@prism-scientist(for statistical analysis)@trail-tracer(when investigation is causal)@apex-architect(when conclusion implies architecture change)
按 Apache-2.0 许可原样转载,未经改动 · 在 GitHub 查看 →
评论
登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。
…