用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/vuralserhat86/antigravity-agentic-skills --skill hypothesis-generation命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Guide for conducting comprehensive accessibility audits of code to identify WCAG compliance issues and barriers to inclusive design. This skill should be used when reviewing accessibility, ARIA implementation, keyboard navigation, or screen reader compatibility.
Transform clarified user requests into structured delegation prompts optimized for specialist agents (cto-architect, strategic-cto-mentor, cv-ml-architect). Use after clarification is complete, before routing to specialist agents. Ensures agents receive complete context for effective work.
AGENTS.md dosyaları oluşturma, monorepo yapılandırma ve agent instruction yönetimi rehberi.
基于 SOC 职业分类
正在显示 SKILL.md
| name | hypothesis_generation |
| router_kit | FullStackKit |
| description | Bilimsel hipotez oluşturma, deney tasarımı ve test metodolojisi rehberi. |
| metadata | {"skillport":{"category":"research","tags":["architecture","automation","best practices","clean code","coding","collaboration","compliance","debugging","design patterns","development","documentation","efficiency","git","hypothesis generation","optimization","productivity","programming","project management","quality assurance","refactoring","software engineering","standards","testing","utilities","version control","workflow"]}} |
Bilimsel hipotez oluşturma ve test metodolojisi rehberi.
IF [independent variable/action]
THEN [dependent variable/outcome]
BECAUSE [mechanism/reasoning]
IF we reduce checkout steps from 5 to 3
THEN conversion rate will increase by 15%
BECAUSE fewer steps reduce friction and drop-off
| Kriter | Açıklama |
|---|---|
| Specific | Net ve belirsizlik yok |
| Measurable | Ölçülebilir outcome |
| Testable | Test edilebilir |
| Falsifiable | Yanlışlanabilir |
| Relevant | İş hedefine uygun |
**Hypothesis:** Changing CTA button from blue to green
will increase click rate by 10%
**Metric:** CTA Click Rate
**Baseline:** 2.5%
**Target:** 2.75%
**Sample Size:** 10,000 users
**Duration:** 2 weeks
**Problem:** Users abandon during onboarding
**Hypothesis:** Adding progress indicator will reduce
abandonment by 20%
**Success Metric:** Onboarding completion rate
## Experiment: [Name]
### Hypothesis
[IF-THEN-BECAUSE statement]
### Variables
- Independent: [What we change]
- Dependent: [What we measure]
- Control: [What stays same]
### Metrics
- Primary: [Main KPI]
- Secondary: [Supporting metrics]
- Guardrail: [Safety metrics]
### Design
- Type: A/B / Multivariate
- Split: 50/50
- Duration: [X] weeks
### Analysis Plan
- Statistical test: [t-test, chi-square, etc.]
- Confidence level: 95%
- MDE: [Minimum detectable effect]
| Hypothesis | Impact | Confidence | Ease | Score |
|---|---|---|---|---|
| H1 | 8 | 7 | 6 | 7.0 |
| H2 | 9 | 5 | 4 | 6.0 |
| H3 | 6 | 8 | 9 | 7.7 |
ICE Score = (Impact + Confidence + Ease) / 3
Hypothesis Generation v1.1 - Enhanced
| Aşama | Doğrulama |
|---|---|
| 1 | Hipotez yanlışlanabilir mi? (Her zaman doğruysa hipotez değildir) |
| 2 | Sonuç ölçülebilir bir metrik mi (Click rate, Retention)? |
| 3 | "Because" kısmı mantıklı bir kullanıcı davranışına dayanıyor mu? |