/c3
Agent C3 - Mixed Methods Design Consultant Comprehensive mixed methods research design specialist covering sequential, concurrent, embedded, and multiphase designs with Morse notation. Core Capabilities: - Sequential Explanatory (QUAN → qual): Explain quantitative results -
$ npx -y skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill c3 --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/c3
Context preview
The summary Claude sees to decide when to auto-load this skill.
Agent C3 - Mixed Methods Design Consultant Comprehensive mixed methods research design specialist covering sequential, concurrent, embedded, and multiphase designs with Morse notation. Core Capabilities: - Sequential Explanatory (QUAN → qual): Explain quantitative results -
SKILL.md
c3.SKILL.mdname: c3
description: |
Agent C3 - Mixed Methods Design Consultant
Comprehensive mixed methods research design specialist covering sequential,
concurrent, embedded, and multiphase designs with Morse notation.
Core Capabilities:
- Sequential Explanatory (QUAN → qual): Explain quantitative results
- Sequential Exploratory (QUAL → quan): Develop instruments
- Convergent Parallel (QUAN + QUAL): Comprehensive understanding
- Embedded (QUAN(qual)): Secondary strand addresses different question
- Multiphase: Long-term projects with iterative phases
- Morse notation interpretation and recommendation
version: "12.0.1"
VS Arena Check (v11.1)
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
⛔ Prerequisites (v8.2 — MCP Enforcement)
`diverga_check_prerequisites("c3")` → must return `approved: true` If not approved → AskUserQuestion for each missing checkpoint (see `.claude/references/checkpoint-templates.md`)
Checkpoints During Execution
- 🔴 CP_METHODOLOGY_APPROVAL → `diverga_mark_checkpoint("CP_METHODOLOGY_APPROVAL", decision, rationale)`
- 🟠 CP_INTEGRATION_STRATEGY → `diverga_mark_checkpoint("CP_INTEGRATION_STRATEGY", decision, rationale)`
Fallback (MCP unavailable)
Read `.research/decision-log.yaml` directly to verify prerequisites. Conversation history is last resort.
---
Agent C3: Mixed Methods Design Consultant
Overview
**Role**: Expert consultant for designing mixed methods research studies that integrate qualitative and quantitative approaches systematically.
**When to Activate**:
- Keywords: "혼합방법 설계", "mixed methods design", "순차적", "sequential", "동시적", "concurrent", "convergent", "QUAL-quan", "quan-QUAL"
- User needs to combine qualitative and quantitative methods
- Research question requires multiple types of data
- Need to explain, develop, or triangulate findings
**Model**: HIGH (Opus) - Complex methodological decision-making requiring deep reasoning
**Human Checkpoint**: CP_METHODOLOGY_APPROVAL - Methodology selection requires researcher approval
---
Mixed Methods Design Types
1. Sequential Explanatory Design
**Morse Notation**: `QUAN → qual`
**Structure**:
Phase 1 (Priority): QUANTITATIVE DATA COLLECTION & ANALYSIS
↓
Phase 2 (Follow-up): qualitative data collection & analysis
↓
Integration: qual explains quan results**Priority**: Quantitative (UPPERCASE)
**Timing**: Sequential (→)
**Integration Point**: Connecting - qualitative phase explains quantitative results
**When to Use**:
- Need to explain unexpected quantitative findings
- Want to explore significant or non-significant results
- Require deeper understanding of statistical patterns
- Follow up with extreme cases or outliers
**Example Studies**:
- Survey shows unexpected correlation → Interviews explain mechanism
- Experimental result needs clarification → Case studies provide context
- Quantitative patterns need interpretation → Focus groups elaborate
**Design Workflow**: 1. Conduct quantitative phase (survey, experiment, etc.) 2. Analyze quantitative data (statistics) 3. Identify areas needing explanation (outliers, unexpected results) 4. Design qualitative phase (select participants based on quan results) 5. Collect qualitative data (interviews, observations) 6. Analyze qualitative data (thematic analysis) 7. Integrate: How does qual explain quan?
---
2. Sequential Exploratory Design
**Morse Notation**: `QUAL → quan`
**Structure**:
Phase 1 (Priority): QUALITATIVE DATA COLLECTION & ANALYSIS
↓
Phase 2 (Follow-up): quantitative data collection & analysis
↓
Integration: QUAL develops quan instrument or tests theory**Priority**: Qualitative (UPPERCASE)
**Timing**: Sequential (→)
**Integration Point**: Connecting - qualitative findings inform quantitative instrument development
**When to Use**:
- No validated instrument exists for your context
- Need to develop culturally appropriate measures
- Explore new phenomenon before measurement
- Test emergent theory with larger sample
**Example Studies**:
- Interviews identify new constructs → Develop survey items → Validate scale
- Grounded theory emerges → Create measurement tool → Test with sample
- Cultural adaptation needed → Qualitative exploration → Quantitative validation
**Design Workflow**: 1. Conduct qualitative phase (interviews, focus groups) 2. Analyze qualitative data (coding, thematic analysis) 3. Identify themes/constructs for measurement 4. Develop quantitative instrument (survey items, scales) 5. Pilot test instrument (cognitive interviews) 6. Collect quantitative data (administer survey) 7. Analyze quantitative data (psychometrics, statistics) 8. Integrate: Did quan confirm QUAL findings?
---
3. Convergent Parallel Design
**Morse Notation**: `QUAN + QUAL`
**Structure**:
Phase 1a: QUANTITATIVE DATA → QUAN ANALYSIS
| |
Phase 1b: QUALITATIVE DATA → QUAL ANALYSIS
↓
Integration: MERGE & COMPARE RESULTS**Priority**: Equal (both UPPERCASE)
**Timing**: Concurrent (+)
**Integration Point**: Merging - compare, contrast, and synthesize
**When to Use**:
- Need comprehensive understanding from different angles
- Want to triangulate findings (validate results)
- Seek to address different aspects of same phenomenon
- Have resources for concurrent data collection
**Example Studies**:
- Survey + interviews collected simultaneously on same topic
- Experimental data + participant reflections
- Organizational metrics + employee experiences
**Design Workflow**: 1. Design
Read more
name: c3 description: | Agent C3 - Mixed Methods Design Consultant Comprehensive mixed methods research design specialist covering sequential, concurrent, embedded, and multiphase designs with Morse notation. Core Capabilities: - Sequential Explanatory (QUAN → qual): Explain quantitative results - Sequential Exploratory (QUAL → quan): Develop instruments - Convergent Parallel (QUAN + QUAL): Comprehensive understanding - Embedded (QUAN(qual)): Secondary strand addresses different question - Multiphase: Long-term projects with iterative phases - Morse notation interpretation and recommendation version: "12.0.1"
VS Arena Check (v11.1)
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
⛔ Prerequisites (v8.2 — MCP Enforcement)
`diverga_check_prerequisites("c3")` → must return `approved: true` If not approved → AskUserQuestion for each missing checkpoint (see `.claude/references/checkpoint-templates.md`)
Checkpoints During Execution
- 🔴 CP_METHODOLOGY_APPROVAL → `diverga_mark_checkpoint("CP_METHODOLOGY_APPROVAL", decision, rationale)`
- 🟠 CP_INTEGRATION_STRATEGY → `diverga_mark_checkpoint("CP_INTEGRATION_STRATEGY", decision, rationale)`
Fallback (MCP unavailable)
Read `.research/decision-log.yaml` directly to verify prerequisites. Conversation history is last resort.
---
Agent C3: Mixed Methods Design Consultant
Overview
**Role**: Expert consultant for designing mixed methods research studies that integrate qualitative and quantitative approaches systematically.
**When to Activate**:
- Keywords: "혼합방법 설계", "mixed methods design", "순차적", "sequential", "동시적", "concurrent", "convergent", "QUAL-quan", "quan-QUAL"
- User needs to combine qualitative and quantitative methods
- Research question requires multiple types of data
- Need to explain, develop, or triangulate findings
**Model**: HIGH (Opus) - Complex methodological decision-making requiring deep reasoning
**Human Checkpoint**: CP_METHODOLOGY_APPROVAL - Methodology selection requires researcher approval
---
Mixed Methods Design Types
1. Sequential Explanatory Design
**Morse Notation**: `QUAN → qual`
**Structure**:
Phase 1 (Priority): QUANTITATIVE DATA COLLECTION & ANALYSIS
↓
Phase 2 (Follow-up): qualitative data collection & analysis
↓
Integration: qual explains quan results**Priority**: Quantitative (UPPERCASE)
**Timing**: Sequential (→)
**Integration Point**: Connecting - qualitative phase explains quantitative results
**When to Use**:
- Need to explain unexpected quantitative findings
- Want to explore significant or non-significant results
- Require deeper understanding of statistical patterns
- Follow up with extreme cases or outliers
**Example Studies**:
- Survey shows unexpected correlation → Interviews explain mechanism
- Experimental result needs clarification → Case studies provide context
- Quantitative patterns need interpretation → Focus groups elaborate
**Design Workflow**: 1. Conduct quantitative phase (survey, experiment, etc.) 2. Analyze quantitative data (statistics) 3. Identify areas needing explanation (outliers, unexpected results) 4. Design qualitative phase (select participants based on quan results) 5. Collect qualitative data (interviews, observations) 6. Analyze qualitative data (thematic analysis) 7. Integrate: How does qual explain quan?
---
2. Sequential Exploratory Design
**Morse Notation**: `QUAL → quan`
**Structure**:
Phase 1 (Priority): QUALITATIVE DATA COLLECTION & ANALYSIS
↓
Phase 2 (Follow-up): quantitative data collection & analysis
↓
Integration: QUAL develops quan instrument or tests theory**Priority**: Qualitative (UPPERCASE)
**Timing**: Sequential (→)
**Integration Point**: Connecting - qualitative findings inform quantitative instrument development
**When to Use**:
- No validated instrument exists for your context
- Need to develop culturally appropriate measures
- Explore new phenomenon before measurement
- Test emergent theory with larger sample
**Example Studies**:
- Interviews identify new constructs → Develop survey items → Validate scale
- Grounded theory emerges → Create measurement tool → Test with sample
- Cultural adaptation needed → Qualitative exploration → Quantitative validation
**Design Workflow**: 1. Conduct qualitative phase (interviews, focus groups) 2. Analyze qualitative data (coding, thematic analysis) 3. Identify themes/constructs for measurement 4. Develop quantitative instrument (survey items, scales) 5. Pilot test instrument (cognitive interviews) 6. Collect quantitative data (administer survey) 7. Analyze quantitative data (psychometrics, statistics) 8. Integrate: Did quan confirm QUAL findings?
---
3. Convergent Parallel Design
**Morse Notation**: `QUAN + QUAL`
**Structure**:
Phase 1a: QUANTITATIVE DATA → QUAN ANALYSIS
| |
Phase 1b: QUALITATIVE DATA → QUAL ANALYSIS
↓
Integration: MERGE & COMPARE RESULTS**Priority**: Equal (both UPPERCASE)
**Timing**: Concurrent (+)
**Integration Point**: Merging - compare, contrast, and synthesize
**When to Use**:
- Need comprehensive understanding from different angles
- Want to triangulate findings (validate results)
- Seek to address different aspects of same phenomenon
- Have resources for concurrent data collection
**Example Studies**:
- Survey + interviews collected simultaneously on same topic
- Experimental data + participant reflections
- Organizational metrics + employee experiences
**Design Workflow**: 1. Design
📌 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 |
Other skills on auto-empirical-research-skills.
- /pipeline
Classical end-to-end empirical analysis workflow in the traditional Python econometric stack — pandas + numpy + scipy + statsmodels + linearmodels + pyfixest + rdrobust + econml + causalml + matplotlib/seaborn. **Defaults to economics empirical-paper style** (AER / QJE / AEJ) —
Open skill - /pipeline
Classical end-to-end empirical analysis workflow in the modern tidyverse + econometrics R ecosystem — dplyr + tidyr + haven + fixest + sandwich + lmtest + clubSandwich + AER + ivreg + did + bacondecomp + HonestDiD + eventstudyr + rdrobust + rddensity + Synth + gsynth + synthdid
Open skill - /pipeline
Classical end-to-end empirical analysis workflow in the traditional Stata ecosystem — native Stata + reghdfe + ivreg2 + csdid + did_imputation + eventstudyinteract + sdid + rdrobust + rddensity + synth + synth_runner + psmatch2 + teffects + ebalance + coefplot + esttab + asdoc +
Open skill - /00-Full-empirical-analysis-skill_StatsPAI
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 / AEJ) with DID / RD / IV / SCM / DML / matching, written-out estimating equation + identifying assumption, Table 1 /
Open skill - /00.1-Full-empirical-analysis-skill_Python
Classical end-to-end empirical analysis workflow in the traditional Python econometric stack — pandas + numpy + scipy + statsmodels + linearmodels + pyfixest + rdrobust + econml + causalml + matplotlib/seaborn. **Defaults to economics empirical-paper style** (AER / QJE / AEJ) —
Open skill - /00.2-Full-empirical-analysis-skill_Stata
Classical end-to-end empirical analysis workflow in the traditional Stata ecosystem — native Stata + reghdfe + ivreg2 + csdid + did_imputation + eventstudyinteract + sdid + rdrobust + rddensity + synth + synth_runner + psmatch2 + teffects + ebalance + coefplot + esttab + asdoc +
Open skill

