Use when defending the research design of an American Anthropologist (AA) manuscript — fieldwork and participant observation, interview and archival design for ethnographic/qualitative work, material/contextual analysis for archaeology, and appropriate lab/quantitative design for biological anthropology. AA judges each mode on its own terms with reflexivity. Strengthens the design; it does not write code or run fieldwork.
SkillScore73Maintained
Automatic
◆Research pack
Last verified 8/15/2026
What it changes
Passed 15 of 21 test cases with the skill, and 13 of 21 without it.
Without skill64%
With skill73%
Checks it passed that the model alone missed
Selects the mode 【Mode】 biological-quant
Selects the mode 【Mode】 archival-material
References amanthro-data-analysis as the next stage
and 2 more in the full report
5 fixed11 passed either way3 still failing3 broke
Pass-rate lift
+9 pp
Tokens
+27%
Agent turns
0%
Response time
-14%
Model gemini-3.6-flashMeasured 8/15/2026v116 of 22 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 4
Prompt
In an American Anthropologist methodology workflow, after finalizing the research design block, what is the exact name of the next workflow stage that should be referenced?
What was checked, without and with the skill
Checked
Without skill
With skill
References amanthro-data-analysis as the next stage
Missed
Passed
case-11 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md73 linessingle file
Research Design (amanthro-research-design)
AA accepts many methodologies but is demanding about each. The design must credibly connect the
argument (amanthro-theory-building) to evidence — and at AA, ethnographic and qualitative inference
is first-class, not a soft substitute for statistics. This skill is mode-aware: pick the section that
matches your work and defend it against the strongest alternative reading, reflexively and ethically.
When to trigger
Specifying fieldwork, sampling of sites/interlocutors, archive or material selection, or lab design
A reviewer questioned your evidence, generalization, confound, or interpretive leap
Planning consent, anonymization, and community accountability into the design
Justifying why your evidence adjudicates the rival reading from amanthro-literature-positioning
Ethnographic / qualitative (first-class at AA)
Fieldwork design. State the site(s), duration, language(s) of work, and your access — and how
each shaped what was observable. Participant observation is a method with a logic, not just "being
there"; say what kinds of evidence it generates.
Sampling of cases/interlocutors justified by design logic (typical, deviant, contrastive,
theoretically driven), not convenience. Say what the case is a case of.
Triangulation & disconfirmation. Corroborate across observation, interviews, documents, and
material; state what evidence would have disconfirmed the reading (the qualitative analogue of a
falsification test).
Reflexivity. Your positionality is part of the design's validity — name how it bears on access
and interpretation (see amanthro-theory-building).
Archival / material analysis
Justify the archive or assemblage selected, its silences and biases, and how you read against the
grain. For archaeology: provenience, sampling, dating logic, comparative frames, and taphonomic
caveats.
State the estimand or comparison, sampling frame, measurement protocol, and replication.
Report power/sample adequacy; pre-register where appropriate; address batch/lab effects, ancestry
vs. social-race conflation, and ethical sourcing of skeletal/genetic/biological samples
(see amanthro-transparency-and-data for repatriation and consent).
Multimodal / participatory design
If image/sound/film is evidence, design capture and consent for media from the start; participatory
and collaborative designs name how community partners shaped questions and authority over outputs.
Use when defending the research design of an American Journal of Sociology (AJS) manuscript on its own methodological terms — quantitative, comparative-historical, ethnographic, network, or formal. AJS judges each kind of work by the standards of its tradition; the design must support the theoretical claim. Defends the design; it does not run the analysis.