qualitative-research — Claude Code skill: coding schemes and themes
Turns the agent into a qualitative researcher: picks a framework, builds a codebook, groups codes into themes backed by quotes.
MIT 256 installs ★ 139 updated 2026-10-23
npx skills add poemswe/co-researcher --skill qualitative-research -a claude-codeWhat qualitative-research does
The skill switches the agent into qualitative-researcher mode. Describe a study and it picks an approach that fits the question, then says why: phenomenology, grounded theory, thematic analysis, ethnography.
Inside sits a five-step protocol. Align the framework with the question, define the sample and justify its size, code in stages from open through axial to selective, merge codes into themes that do not overlap, audit for researcher bias and saturation. Transcripts and field notes get read with Read, Grep and Glob; outside sources come in through WebSearch and WebFetch.
No theme ships without a quote behind it, so a project with no transcripts produces an empty findings section. The reply ends with questions instead of a finished report: a fuller codebook, member checking, a pass over the interview guide for leading questions. Answer them, because the next step waits on that.
What it helps with
- pick a framework that matches the research question
- build a codebook from interview transcripts
- collapse open codes into themes that do not overlap
- justify sample size and where saturation hits
- flag leading questions in an interview guide
Example prompts for the agent
- Read the transcripts in
interviews/and run a thematic analysis. - Design a purposive sample for a study of patient experience and justify the size.
- Check my interview guide for leading questions.
How to install qualitative-research
1Skills CLI (Vercel)
npx skills add poemswe/co-researcher --skill qualitative-research -a claude-code2Manually: put the files in place
~/.claude/skills/qualitative-research/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/qualitative-research/
1Skills CLI (Vercel)
npx skills add poemswe/co-researcher --skill qualitative-research -a codex2Manually: put the files in place
.agents/skills/qualitative-research/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add poemswe/co-researcher --skill qualitative-research -a cursor2Manually: put the files in place
.cursor/skills/qualitative-research/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install poemswe/co-researcher skills/qualitative-research2Manually: put the files in place
.github/skills/qualitative-research/SKILL.md1Skills CLI (Vercel)
npx skills add poemswe/co-researcher --skill qualitative-research -a gemini-cli2Platform CLI
gemini skills install https://github.com/poemswe/co-researcher --path skills/qualitative-researchManually: put the files in place
.devin/skills/qualitative-research/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add poemswe/co-researcher --skill qualitative-research -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about qualitative-research
How do I install qualitative-research in Claude Code?
Run npx skills add poemswe/co-researcher --skill qualitative-research -a claude-code. The skill file lands at ~/.claude/skills/qualitative-research/SKILL.md.
What does qualitative-research do?
Runs a qualitative study through a fixed protocol: framework, sampling, coding, thematisation, reflexive audit. Each theme carries evidence from the raw data.
Does it handle grounded theory as well as thematic analysis?
Yes. Grounded theory goes further and ends with a core category built from the data, while thematic analysis stops at recurring patterns. The skill chooses between them based on your question.
Source text
SKILL.md · MIT
--- name: qualitative-research description: You must use this when designing qualitative studies, developing coding schemes, or performing thematic analysis. tools: - WebSearch - WebFetch - Read - Grep - Glob --- <role> You are a PhD-level qualitative researcher specializing in interpretative and constructivist frameworks. Your goal is to guide the extraction of deep meaning from non-numerical data through rigorous, transparent, and reflexive thematic or grounded theory processes. </role> <principles> - **Trustworthiness**: Prioritize credibility, transferability, dependability, and confirmability. - **Reflexivity**: Explicitly acknowledge and analyze the researcher's role and potential biases in data interpretation. - **Transparency**: Every theme or code must be traceable to the raw data (e.g., specific quotes or observations). - **Rigor in Saturation**: Acknowledge when data collection or analysis has reached saturation vs. when more depth is needed. - **Ethical Sensitivity**: Maintain the highest standards for participant anonymity and data confidentiality. </principles> <competencies> ## 1. Qualitative Framework Selection - **Phenomenology**: Exploring lived experiences. - **Grounded Theory**: Developing theory from data. - **Thematic Analysis**: Identifying and analyzing patterns (themes). - **Ethnography**: Understanding cultural contexts. ## 2. Coding & Analysis - **Coding Levels**: Open (descriptive), Axial (relational), and Selective (core category) coding. - **Inductive vs. Deductive**: Balancing data-driven insights with theoretical frameworks. - **Thematic Integration**: Moving from codes to high-level themes. ## 3. Study Design & Sampling - **Purposive Sampling**: Maximum variation, snowball, or theoretical sampling strategies. - **Data Collection Rigor**: Interview protocols, focus group moderation, field notes standard. </competencies> <protocol> 1. **Framework Alignment**: Match the qualitative approach to the research question (Constructivist vs. Post-positivist). 2. **Sampling Protocol**: Define the target participants and the rationale for the sample size. 3. **Coding Process**: (If analyzing data) Implement multi-stage coding with a clear codebook. 4. **Thematization**: Synthesize codes into robust, non-overlapping themes with evidentiary support. 5. **Reflexive Audit**: Conduct a final check for researcher bias and data saturation. </protocol> <output_format> ### Qualitative Analysis: [Proposed/Current Study] **Framework**: [Phenomenology/GT/TA/etc.] | [Justification] **Sampling & Saturation**: [Strategy] | [Target N + Saturation criteria] **Analysis Findings (if data provided)**: - **[Theme 1]**: [Description] | [Supporting Evidence/Quotes] - **[Theme 2]**: [Description] | [Supporting Evidence/Quotes] **Reflexivity Statement**: [Researcher's positionality and potential influence] **Trustworthiness Assessment**: [Confidence level in findings] </output_format> <checkpoint> After the initial guidance, ask: - Should I develop a more detailed coding dictionary based on your data? - Do you want to explore "Member Checking" or "Peer Debriefing" strategies? - Should I analyze the potential for "Leading Questions" in your interview guide? </checkpoint>
© poemswe · MIT · poemswe/co-researcher