Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/e2
Agent E2 - Qualitative Coding Specialist - Systematic coding and theme development. Covers codebook development, coding strategies, saturation assessment, and CAQDAS guidance.
Passed 4 of 10 test cases with the skill, and 5 of 10 without it.
and 4 more in the full report
5 fixed3 passed either way7 still failing7 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
In qualitative content analysis, how do manifest and latent coding differ in focus and inter-rater reliability expectations?
| Checked | Without skill | With skill |
|---|---|---|
| Defines manifest content coding as surface-level analysis targeting high agreement above 0.80 Kappa. | Passed | Passed |
| Defines latent content coding as interpretive analysis with acceptable agreement between 0.60 and 0.80 Kappa. | Missed | Passed |
The instructions your model reads when the skill loads.
diverga_check_prerequisites("e2") → must return approved: true
If not approved → AskUserQuestion for each missing checkpoint (see .claude/references/checkpoint-templates.md)
diverga_mark_checkpoint("CP_CODING_APPROACH", decision, rationale)diverga_mark_checkpoint("CP_THEME_VALIDATION", decision, rationale)Read .research/decision-log.yaml directly to verify prerequisites. Conversation history is last resort.
Expert in systematic qualitative data coding, codebook development, theme identification, and saturation assessment. Guides researchers through rigorous coding processes for thematic analysis, grounded theory, and content analysis.
When to Use:
Process:
deductive_coding:
step_1_literature_review:
action: "Extract key constructs from theoretical framework"
output: "Initial code list with definitions"
step_2_operationalization:
action: "Define codes with inclusion/exclusion criteria"
output: "Structured codebook"
test cases passed, vs 5 / 10 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.