Nw Research Methodology Skill for Claude
Research output templates, distillation workflow, and quality standards for evidence-driven research
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/nWave-ai/nWave --skill nw-research-methodologyThe instruction itself
10 sections, as written by the authorResearch Methodology
Research Output Template
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}
Skill Distillation Workflow
When creating a skill (via *create-skill or skill_for specified):
Phase 1: Research
Execute comprehensive research, create full doc in docs/research/{category}/{topic}-comprehensive-research.md, complete quality gates.
Phase 2: Distillation
- Read comprehensive research
- Transform: academic -> practitioner-focused
- Preserve 100% essential concepts (no lossy compression)
- Remove: verbose explanations, extensive examples, redundant cross-refs
- Keep: core concepts, practical tools, methodologies, decision heuristics
- Make self-contained (no external refs) | Target <1000 tokens/file
- Write to
~/.claude/skills/nw-{skill-name}/SKILL.md{topic}-methodology.md
Phase 3: Validation
Verify all essential concepts present | Confirm practitioner focus | Check self-containment
Quality Standards
Per-Claim Requirements (Adaptive to Turn Budget)
Source requirements adapt to available turn budget:
- Ideal: 3+ independent sources per major claim
- Acceptable: 2 credible sources when budget is constrained
- Minimum: 1 authoritative source (official docs, RFC, specification) with explicit confidence note
- Never: 0 sources -- unsourced claims must be flagged as "[unverified]"
When budget runs low, prioritize BREADTH (cover all claims with minimum sources) over DEPTH (exhaust sources for one claim while ignoring others).
Additional requirements:
- Each source validated against trusted source config from prompt context
- Cross-reference status documented per finding
Confidence Ratings
- High: 3+ high-reputation sources agree, no contradictions
- Medium: 2+ agree, minor contradictions or some medium-trust
- Low: single source or significant contradictions
Quality Gates (before finalizing)
- Every major claim has citations (3+ ideal, 2 acceptable, 1 authoritative minimum) | 2. All sources from trusted domains
- All findings evidence-backed | 4. Knowledge gaps documented | 5. Output in allowed directories
- Claims with fewer than 3 sources have confidence rating adjusted accordingly
Other skills for the same job
different authors, same section of the catalogue
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.
Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews.
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries.
Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches.
Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.
Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming.
How to use it
Take nwave-ai/nw-research-methodology from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.