Research output templates, distillation workflow, and quality standards for evidence-driven research
Use for all research documents in docs/research/.
# Research: {Topic}
**Date**: {ISO-8601} | **Researcher**: nw-researcher (Nova) | **Confidence**: {High/Medium/Low} | **Sources**: {count}
## Executive Summary
{2-3 paragraph overview of key findings, main insights, and overall conclusion}
## Research Methodology
**Search Strategy**: {how sources were found}
**Source Selection**: Types: {academic/official/industry/technical_docs} | Reputation: {high/medium-high min} | Verification: {cross-referencing approach}
**Quality Standards**: Target 3 sources/claim (min 1 authoritative) | All major claims cross-referenced | Avg reputation: {0.0-1.0}
## Findings
### Finding 1: {Descriptive Title}
**Evidence**: "{Direct quote or specific data point}"
**Source**: [{Source Name}]({URL}) - Accessed {YYYY-MM-DD}
**Confidence**: {High/Medium/Low}
**Verification**: [{Source 2}]({URL2}), [{Source 3}]({URL3})
**Analysis**: {Brief interpretation or context}
{Repeat Finding structure as needed}
## Source Analysis
| Source | Domain | Reputation | Type | Access Date | Cross-verified |
|--------|--------|------------|------|-------------|----------------|
| {name} | {domain} | {High/Medium-High/Medium} | {academic/official/industry/technical} | {YYYY-MM-DD} | {Y/N} |
Reputation: High: {count} ({%}) | Medium-high: {count} ({%}) | Avg: {0.0-1.0}
## Knowledge Gaps
### Gap 1: {Description}
**Issue**: {missing/unclear info} | **Attempted**: {sources searched} | **Recommendation**: {how to address}
## Conflicting Information (if applicable)
### Conflict 1: {Topic}
**Position A**: {Statement} — Source: [{Name}]({URL}), Reputation: {score}, Evidence: {quote}
**Position B**: {Contradictory statement} — Source: [{Name}]({URL}), Reputation: {score}, Evidence: {quote}
**Assessment**: {Which source more authoritative and why}
## Recommendations for Further Research
1. {Specific recommendation with rationale}
## Full Citations
[1] {Author}. "{Title}". {Publication}. {Date}. {URL}. Accessed {YYYY-MM-DD}.
## Research Metadata
Duration: {X min} | Examined: {count} | Cited: {count} | Cross-refs: {count} | Confidence: High {%}, Medium {%}, Low {%} | Output: docs/research/{filename}
When creating a skill (via *create-skill or skill_for specified):
Execute comprehensive research, create full doc in docs/research/{category}/{topic}-comprehensive-research.md, complete quality gates.
~/.claude/skills/nw-{skill-name}/SKILL.md{topic}-methodology.mdVerify all essential concepts present | Confirm practitioner focus | Check self-containment
Source requirements adapt to available turn budget:
When budget runs low, prioritize BREADTH (cover all claims with minimum sources) over DEPTH (exhaust sources for one claim while ignoring others).
Additional requirements: