Help us improve
Share bugs, ideas, or general feedback.
From interpretive-orchestration-cowork
This skill should be used when users ask about which AI model to use for coding, mentions 'cost', 'batch', 'API', 'configure analysis', wants to process multiple documents, or needs to understand model capabilities and costs for Stage 2.
npx claudepluginhub linxule/interpretive-orchestration --plugin interpretive-orchestration-coworkHow this skill is triggered — by the user, by Claude, or both
Slash command
/interpretive-orchestration-cowork:skills/analysis-orchestrationThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Model selection, cost estimation, and batch processing setup for AI-assisted coding. Helps researchers configure their analysis approach with awareness of tradeoffs.
Routes Claude Code tasks to optimal models (Haiku, Sonnet, Opus) using decision matrices, cost tables, complexity signals, and subagent assignments for cost/quality tradeoffs.
Guides designing qualitative studies, developing coding schemes, and performing thematic analysis using grounded theory, phenomenology, and reflexive protocols for trustworthiness.
Recommends optimal Claude model (Haiku, Sonnet, Opus) for tasks using decision matrix for technical, business, strategy, creative, and command complexity.
Share bugs, ideas, or general feedback.
Model selection, cost estimation, and batch processing setup for AI-assisted coding. Helps researchers configure their analysis approach with awareness of tradeoffs.
Use this skill when:
| Model | Best For | Cost | Quality |
|---|---|---|---|
| Claude Opus 4.5 | Complex interpretive coding, nuanced themes | $$$ | Highest |
| Claude Sonnet 4 | Balanced quality and cost for systematic coding | $$ | High |
| Claude Haiku | Initial passes, high volume, simple categorization | $ | Good |
Deep Interpretive Coding (@dialogical-coder)
Initial Categorization
Pattern Characterization
| Documents | Model | Estimated Cost |
|---|---|---|
| 10 interviews (~50 pages) | Opus | $15-25 |
| 10 interviews (~50 pages) | Sonnet | $5-10 |
| 50 documents | Opus | $75-125 |
| 50 documents | Sonnet | $25-50 |
Variables:
Estimates API costs based on document characteristics.
node skills/analysis-orchestration/scripts/estimate-costs.js \
--documents 25 \
--avg-pages 5 \
--model sonnet \
--passes 2
Returns: Estimated cost range and token counts.
Is this initial exploratory coding?
├── Yes → Consider Haiku for volume, validate with Sonnet
└── No, this is interpretive coding
├── Budget constrained?
│ ├── Yes → Sonnet 4 (good balance)
│ └── No → Opus 4.5 (best quality)
└── Need to process >50 documents?
├── Yes → Two-pass: Haiku then Sonnet on subset
└── No → Single-pass with Sonnet or Opus
Using @dialogical-coder (4-stage process)?
├── Yes → 5-10 documents per session (reflection breaks)
└── No, systematic application?
├── Complex coding scheme → 10-15 documents
└── Simple categorization → 20-30 documents
/qual-configure-analysis triggers this skillcoding-workflow/ for batch processing execution