qual-code-deductive skill
Apply established theoretical patterns to remaining documents in a deductive coding pass while remaining open to emergent insights.
- GitHub stars
- 21
- Files
- 1
- Last commit
- Nov 6, 2026
- License
- —
- Allowed tools
- —
What does the qual-code-deductive skill do?
qual-code-deductive is an agent skill. Apply established theoretical patterns to remaining documents in a deductive coding pass while remaining open to emergent insights.
Summary generated from the skill's SKILL.md.
About the qual-code-deductive skill
Qualitative researchers who have completed synthesis and need to process remaining documents can use this skill to apply established theoretical patterns to new data. It functions as a deductive coding pass that maintains an interpretive dialogue between a researcher's framework and the incoming information. Instead of mechanical application, the process focuses on testing framework coverage and identifying where existing patterns might require refinement or where new dimensions are emerging.
An agent should load this skill when a solid integrated framework is already in place and the goal is to code the rest of a dataset. The skill relies on the @dialogical-coder tool to execute coding tasks, show reasoning for pattern assignments, and flag uncertainties or exceptions. It produces structured documentation of the coding process, including strong fits, weak fits, and anomalies. Users can also utilize the PostFiveDocuments hook to perform quality checks every five documents to ensure framework coherence and monitor for theoretical saturation.
What an agent can do with it
- 1Apply established patterns to dataCode a new document using a specific list of existing patterns and show the reasoning for each assignment.
- 2Identify framework gapsFind segments of data that do not fit into the current pattern definitions to identify necessary refinements.
- 3Monitor coding qualityPerform a check every five documents to see if the patterns are still working or if new patterns are emerging.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the qual-code-deductive skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the qual-code-deductive skill in Plugin
/plugin marketplace add linxule/interpretive-orchestration /plugin install interpretive-orchestration@interpretive-orchestration
Install the qual-code-deductive skill in Claude Code
~/.claude/skills/qual-code-deductive/SKILL.md
$ npx degit linxule/interpretive-orchestration/plugin/skills/qual-code-deductive ~/.claude/skills/qual-code-deductiveInstall the qual-code-deductive skill in Claude Code (project)
.claude/skills/qual-code-deductive/SKILL.md
$ npx degit linxule/interpretive-orchestration/plugin/skills/qual-code-deductive .claude/skills/qual-code-deductiveInstall the qual-code-deductive skill in Codex
~/.agents/skills/qual-code-deductive/SKILL.md
$ npx degit linxule/interpretive-orchestration/plugin/skills/qual-code-deductive ~/.agents/skills/qual-code-deductiveInstall the qual-code-deductive skill in Gemini CLI
~/.gemini/skills/qual-code-deductive/SKILL.md
$ npx degit linxule/interpretive-orchestration/plugin/skills/qual-code-deductive ~/.gemini/skills/qual-code-deductiveInstall the qual-code-deductive skill in Claude.ai
npx degit linxule/interpretive-orchestration/plugin/skills/qual-code-deductive qual-code-deductive && zip -r qual-code-deductive.zip qual-code-deductive # claude.ai → Customize → Skills → + → Create skill → Upload a skill → qual-code-deductive.zip
SKILL.md
View on GitHubDeductive Coding Command
This command guides you through applying your synthesized patterns to the remaining documents in a more deductive manner, while remaining open to emergent insights.
Overview
After synthesis, you have an integrated framework of patterns. Now you apply this framework to code your remaining documents, testing and refining as you go.
This is NOT mechanical application. It's a dialogue between your framework and new data.
When to Use Deductive Coding
Use this approach when:
- You've completed parallel streams and synthesis
- Your integrated framework feels solid
- You have remaining documents to code
- You want to test framework coverage
The Deductive Coding Process
Step 1: Prepare Your Framework
Before coding, ensure you have:
- Clear pattern definitions
- Example quotes for each pattern
- Inclusion/exclusion criteria
- Noted variations and edge cases
Step 2: Code with Your Framework
For each document:
- Initial read: Get the overall sense
- Apply patterns: Match segments to your framework
- Note fit: How well do patterns capture the data?
- Flag anomalies: What doesn't fit? What's new?
Step 3: Remain Inductively Open
Deductive doesn't mean closed. Watch for:
- New patterns: Data that needs a new category
- Pattern refinement: Existing patterns need adjustment
- Dimension discovery: Variations you hadn't seen
- Disconfirming evidence: Cases that challenge patterns
Step 4: Update Your Framework
After each batch of documents:
- Revise pattern definitions as needed
- Add new patterns that emerged
- Note dimensional variations
- Document disconfirming cases
Using @dialogical-coder for Deductive Coding
Request @dialogical-coder to:
- Code against your framework: "Apply patterns X, Y, Z to this document"
- Show reasoning: Why does this segment match this pattern?
- Flag uncertainties: Where is the fit ambiguous?
- Identify exceptions: What doesn't fit existing patterns?
Example prompt:
"Using my established patterns [list them], code this document. Show your reasoning for each assignment and flag anything that doesn't fit well."
Quality Checks During Deductive Coding
Every 5 Documents (PostFiveDocuments Hook)
- Are patterns still working?
- What refinements are needed?
- Any new patterns emerging?
- Overall framework coherence?
Pattern Saturation Check
- Are patterns being applied without refinement?
- Are new documents confirming without extending?
- Have you reached theoretical saturation?
Common Issues and Solutions
Issue: Everything Fits Everywhere
Problem: Patterns are too broad Solution: Tighten definitions; add subcategories
Issue: Too Many Anomalies
Problem: Framework may be underdeveloped Solution: Return to synthesis; revisit pattern construction
Issue: Coding Feels Mechanical
Problem: Lost the interpretive engagement Solution: Ask "What is this informant REALLY saying?" before coding
Issue: Framework Isn't Capturing Richness
Problem: Deductive approach is flattening data Solution: Allow new patterns; don't force fit
Documentation During Deductive Coding
Track as you go:
Document: [ID]
Patterns applied: [list]
Strong fits: [which patterns, which quotes]
Weak fits: [ambiguous assignments]
Anomalies: [what doesn't fit]
Refinements needed: [suggested changes]
Tools
- @dialogical-coder: Primary coding assistant
- Step-by-step thinking: Work through ambiguous coding decisions
- Lotus Wisdom: When data seems to both fit and not fit a pattern
Philosophical Note
Deductive coding in qualitative research is different from deductive coding in quantitative research. You're not just "applying codes" - you're continuing the interpretive dialogue. Your framework is a conversation partner, not a straightjacket.
Next Steps
After deductive coding pass:
- Review framework refinements
- Run
/qual-characterize-patternsfor dimensional analysis - Prepare for Stage 3: Dialogue with Tradition
Files in this skill
1qual-code-deductive skill questions
How do I install the qual-code-deductive skill in Claude Code?
Run npx degit linxule/interpretive-orchestration/plugin/skills/qual-code-deductive ~/.claude/skills/qual-code-deductive. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the qual-code-deductive skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
When should I use the deductive coding approach?
Use this approach once you have completed parallel streams and synthesis, your integrated framework feels solid, you have remaining documents to code, and you want to test framework coverage.
How do I prevent deductive coding from becoming a mechanical process?
To avoid losing interpretive engagement, ask yourself 'What is this informant REALLY saying?' before coding.
What should I do if my patterns are too broad and everything seems to fit everywhere?
If you encounter the issue where everything fits everywhere, you should tighten your definitions and add subcategories.