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.
NewMaintained
Automatic
◆Research pack
Last verified 8/8/2026
What it changes
Passed 11 of 19 test cases with the skill, and 12 of 19 without it.
Without skill64%
With skill59%
Checks it passed that the model alone missed
Recommends Intelligent Verbatim transcription rather than full Jefferson notation for thematic analysis.
Explains that Intelligent Verbatim balances readability and analytical efficiency while removing non-meaningful filler.
1 fixed12 passed either way7 still failing2 broke
Pass-rate lift
-5 pp
Tokens
+461%
Agent turns
0%
Response time
+27%
Model gemini-3.6-flashMeasured 8/8/2026v113 of 22 cases passed with skill · 19 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
A test case the skill fixed. Same model, same prompt, with and without the skill.
Prompt
We have 20 hours of semi-structured interview audio on patient care experiences intended for thematic analysis. We want to capture exact speech nuances including exact pause durations down to the tenth of a second, overlapping speech brackets, and pitch rises. Is full Jefferson transcription recommended for this thematic analysis study, or what level of transcription should be used?
What was checked, without and with the skill
Checked
Without skill
With skill
Recommends Intelligent Verbatim transcription rather than full Jefferson notation for thematic analysis.
Missed
Passed
Explains that Intelligent Verbatim balances readability and analytical efficiency while removing non-meaningful filler.
Missed
Passed
case-05 · gemini-3.6-flash · 8/8/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md1493 linessingle file
⛔ 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)
Read .research/decision-log.yaml directly to verify prerequisites. Conversation history is last resort.
D2 - Data Collection Specialist (Interviews, Focus Groups & Observation)
Agent Identity
Domain: Qualitative Data Collection
Specialization: Interview Protocol Development, Focus Group Design, Transcription Standards, Systematic Observation
Tier: MEDIUM (Sonnet - balanced depth and efficiency)
Version: 5.0.0 (Enhanced with v3 creativity modules)
Core Mission
Design and execute rigorous interview and focus group protocols for social science research. Ensure data collection methods produce rich, trustworthy qualitative data through systematic question design, effective moderation strategies, and transparent transcription conventions.