d2
Agent D2 - Data Collection Specialist - Interviews, Focus Groups & Observation. Covers protocol development, question design, probing strategies, transcription conventions, and systematic observation. Absorbed D3 (Observation Protocol Designer) capabilities.
npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill d2 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Design and execute rigorous interview and focus group protocols for social science research, including protocol development, question design, probing strategies, transcription conventions, and systematic observation. Absorbed D3 (Observation Protocol Designer) capabilities.
How it works
Provides a framework for interview types (Structured, Semi-Structured, Unstructured), question design principles (Grand Tour, Mini-Tour, Experience/Behavior, etc.), and probing strategies. Includes a configurable Focus Group design section with composition criteria, moderator roles, and a template discussion guide. Contains explicit example structures, sequencing logic (Funnel and Inverted Funnel), and process checkpoints for quality assurance. Also outlines dynamic creativity modules and iterative variants for protocol development, plus multiple example structures and templates for both interviews and focus groups.
When to use it
Use when designing qualitative data collection protocols requiring interviews, focus groups, or observational components, particularly for studies exploring lived experience, perceptions, meanings, or grounded theory approaches. Activated by triggers related to interview, focus group, transcription, and related qualitative methods, and when there is a need for structured protocol design, probing strategies, and transcription conventions.
What it can touch
Includes guidance on protocol development, question design, and focus group composition. References to recording, transcription conventions, and data quality assurance are integral to the procedures.
Caveats
No explicit licensing text in the provided excerpt; relies on internal best practices and documented methodologies. Responsible for ensuring ethical safeguards for participant confidentiality and appropriate moderator neutrality within the discussed templates.
## ⛔ Prerequisites (v8.2 — MCP Enforcement) `diverga_check_prerequisites("d2")` → must return `approved: true` If not approved → AskUserQuestion for each missing checkpoint (see `.claude/references/checkpoint-templates.md`) ### Checkpoints During Execution - 🟠 CP_SAMPLING_STRATEGY → `diverga_mark_checkpoint("CP_SAMPLING_STRATEGY", decision, rationale)` ### Fallback (MCP unavailable) Read `.resear
What does the d2 skill do?
Agent D2 - Data Collection Specialist - Interviews, Focus Groups & Observation. Covers protocol development, question design, probing strategies, transcription conventions, and systematic observation. Absorbed D3 (Observation Protocol Designer) capabilities.
How do I install it?
Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill d2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From brycewang-stanford/Auto-Empirical-Research-Skills, a repository with 3,244 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.