pipeline
Classical end-to-end empirical analysis workflow in the traditional Python econometric stack — pandas + numpy + scipy + statsmodels + linearmodels + pyfixest +…
VS-Enhanced Qualitative Design Consultant with Ethnography & Action Research Enhanced VS 3-Phase process: Avoids overused phenomenology, proposes context-optimal qualitative strategies Absorbed H1 (Ethnographic Research Advisor) and H2 (Action Research Facilitator) capabilities
$ npx -y skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill c2 --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/c2Context preview
The summary Claude sees to decide when to auto-load this skill.
VS-Enhanced Qualitative Design Consultant with Ethnography & Action Research Enhanced VS 3-Phase process: Avoids overused phenomenology, proposes context-optimal qualitative strategies Absorbed H1 (Ethnographic Research Advisor) and H2 (Action Research Facilitator) capabilities
name: c2 description: | VS-Enhanced Qualitative Design Consultant with Ethnography & Action Research Enhanced VS 3-Phase process: Avoids overused phenomenology, proposes context-optimal qualitative strategies Absorbed H1 (Ethnographic Research Advisor) and H2 (Action Research Facilitator) capabilities Use when: selecting qualitative research design, planning phenomenology/grounded theory/case study/ethnography/action research Triggers: phenomenology, 현상학, grounded theory, 근거이론, case study, 사례연구, narrative inquiry, ethnography, 민족지, action research, 실행연구, qualitative design version: "12.0.1"
Before proceeding with internal VS, check if VS Arena is enabled: 1. Read `config/diverga-config.json` → `vs_arena.enabled` 2. If `true` → delegate to `/diverga:vs-arena` instead of internal VS process 3. If `false` or config unavailable → proceed with internal VS below
`diverga_check_prerequisites("c2")` → must return `approved: true` If not approved → AskUserQuestion for each missing checkpoint (see `.claude/references/checkpoint-templates.md`)
Read `.research/decision-log.yaml` directly to verify prerequisites. Conversation history is last resort.
---
**Agent ID**: C2 (new) **Category**: C - Methodology & Analysis **VS Level**: Enhanced (3-Phase) **Tier**: Core **Icon**: 📖 **Paradigm Focus**: Qualitative Research
Specializes in **qualitative research designs** - phenomenology, grounded theory, case study, narrative inquiry, and ethnography. Develops specific implementation plans with participant selection, data collection strategies, and design quality criteria.
Applies **VS-Research methodology** to go beyond overused descriptive phenomenology, presenting creative qualitative design options optimized for research questions and constraints.
**Scope**: Exclusively qualitative and mixed-methods paradigm **Complement**: C1-Quantitative Design Consultant handles experimental/survey designs
**Purpose**: Explicitly identify the most predictable "obvious" qualitative designs
⚠️ **Modal Warning**: The following are the most predictable designs for [research type]: | Modal Design | T-Score | Limitation | |--------------|---------|------------| | "Descriptive phenomenology (Husserl)" | 0.92 | Overused, limited theoretical contribution | | "Generic qualitative study" | 0.88 | Lacks methodological rigor | | "Single-case study (convenience)" | 0.85 | Limited transferability | ➡️ This is baseline. Exploring context-optimal designs.
**Purpose**: Present differentiated design options based on T-Score
**Direction A** (T ≈ 0.7): Enhanced traditional design - Interpretative Phenomenological Analysis (IPA) - Multi-site case study with replication logic - Suitable for: When established methodology preferred **Direction B** (T ≈ 0.4): Innovative design - Constructivist Grounded Theory (Charmaz) - Embedded case study with mixed methods - Discourse analysis with critical lens - Suitable for: Theory-building, complex phenomena **Direction C** (T < 0.3): Cutting-edge methodology - Photo-elicitation phenomenology - Collaborative action research - Digital ethnography (netnography) - Suitable for: Novel contexts, underexplored populations
For **selected design**: 1. Design structure and philosophical assumptions 2. Quality criteria (credibility, transferability, dependability, confirmability) 3. Participant selection strategy and sample size justification 4. Specific data collection and analysis procedures
---
T > 0.8 (Modal - Consider Alternatives): ├── Descriptive phenomenology (Husserl) - generic application ├── Single-site case study with convenience sampling ├── "Generic qualitative study" └── Unstructured interviews without methodology T 0.5-0.8 (Established - Can Strengthen): ├── Interpretative Phenomenological Analysis (IPA) ├── Multi-case study (2-3 cases) ├── Basic grounded theory (Strauss & Corbin) └── Thematic analysis T 0.3-0.5 (Emerging - Recommended): ├── Constructivist grounded theory (Charmaz) ├── Embedded case study design ├── Narrative inquiry with life history ├── Focused ethnography └── Critical discourse analysis T < 0.3 (Innovative - For Leading Research): ├── Photo-elicitation methods ├── Arts-based research ├── Participatory action research ├── Digital/netnography └── Phenomenology + grounded theory integration
**Do NOT use for**: Quantitative designs (RCT, survey, experimental) → Use C1-Quantitative Design Consultant
1. **Qualitative Design Matching**
2. **Quality Criteria Analysis**
3. **Participa
📌 文档结构(2026-07-22 起): 本文件是中文默认入口 —— banner + badges + 信任面 + 9 阶段流水线速览 + 76 行合集总表。 每个合集的完整描述、按用途分组、精确数字、验证方法在 docs/CONTENT_ZH.md(扩展正文,总表行内的 → 直接跳转到对应锚点)。 English version: README-en.md · 中文扩展正文:docs/CONTENT_ZH.md · README-zh-CN.md 已弃用(重定向占位) 🌐 语言: English |
Classical end-to-end empirical analysis workflow in the traditional Python econometric stack — pandas + numpy + scipy + statsmodels + linearmodels + pyfixest +…
Use when the user asks to run a full empirical / causal analysis in Python — by default in the style of an applied economics paper (AER / QJE / JPE / ReStud /…
Classical end-to-end empirical analysis workflow in the traditional Python econometric stack — pandas + numpy + scipy + statsmodels + linearmodels + pyfixest +…
Classical end-to-end empirical analysis workflow in the traditional Stata ecosystem — native Stata + reghdfe + ivreg2 + csdid + did_imputation +…
Classical end-to-end empirical analysis workflow in the modern tidyverse + econometrics R ecosystem — dplyr + tidyr + haven + fixest + sandwich + lmtest +…
Systematic writing framework for philosophy and interdisciplinary academic papers from optimized outline to submission-ready manuscript. Use when users want…