A specialized skill for the researcher and fact-checker agents covering investigative research. Provides primary/secondary source collection, source reliability assessment, data triangulation, and bias analysis methodologies. Use for 'research,' 'fact-checking,' 'source verification,' 'investigative techniques,' and similar topics.
Scanned 9/8/2026
Install to Claude Code
npx -y skills add revfactory/harness-100 --skill investigative-research --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Investigative Research?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/revfactory-investigative-research-harness-100)More formats (shields.io, HTML) on the badges page.
---
name: investigative-research
description: "A specialized skill for the researcher and fact-checker agents covering investigative research. Provides primary/secondary source collection, source reliability assessment, data triangulation, and bias analysis methodologies. Use for 'research,' 'fact-checking,' 'source verification,' 'investigative techniques,' and similar topics."
---
# Investigative Research — Investigative Research Methodology
Specialized knowledge used by the researcher and fact-checker agents when investigating and verifying materials for documentaries.
## Why Systematic Research Is Needed
A documentary's credibility depends on the **depth and accuracy of its research**. A single incorrect statistic can undermine the entire program's trust. There is a fundamental difference between "casually searching and using" versus "verifying at investigative journalism standards."
## Source Collection Hierarchy: PRIMA Framework
| Tier | Description | Reliability | Example |
|------|-------------|-------------|---------|
| **P**rimary | Primary sources — original data, direct interviews | Highest | Census raw data, firsthand testimony |
| **R**efereed | Peer-reviewed academic sources | High | Academic papers, meta-analyses |
| **I**nstitutional | Reports published by institutions | Medium-High | WHO reports, central bank statistics |
| **M**edia | Verified news coverage | Medium | Major news outlet articles, reportage |
| **A**necdotal | Anecdotes, personal experiences | Low | Social media, blogs, community posts |
### Source Collection Rules
1. **Minimum 3 independent sources**: Cross-confirm key facts from 3 different sources
2. **Primary sources first**: Whenever possible, verify original data or reports directly
3. **Recency**: Statistics within the last 3 years; for fast-changing fields, within 1 year
4. **Collect opposing views**: Intentionally collect materials from opposing positions
## Source Reliability Assessment: CRAAP Test
| Criterion | Question | Weight |
|-----------|----------|--------|
| **C**urrency | When was it published? Updated? | 20% |
| **R**elevance | Is it directly related to the topic? | 15% |
| **A**uthority | What are the author/institution's expertise and credentials? | 25% |
| **A**ccuracy | Does it match other sources? Is there evidence? | 25% |
| **P**urpose | Information? Persuasion? Advertising? Political purpose? | 15% |
### Reliability Grades
| Score | Grade | Usability |
|-------|-------|-----------|
| 80-100 | A (Highly Reliable) | Can be used as core fact |
| 60-79 | B (Reliable) | Use as supporting material, cross-check recommended |
| 40-59 | C (Caution) | Reference only, cross-check required |
| 20-39 | D (Suspect) | Do not use directly, cite only as a perspective |
| 0-19 | F (Disqualified) | Do not use |
## Data Triangulation
### 3 Verification Axes
```
Method Triangulation
(Different research methods)
^
/ \
/ \
/ \
Data Triangulation --- Investigator Triangulation
(Different data sources) (Different analysts)
```
| Type | Method | Example |
|------|--------|---------|
| **Data Triangulation** | Confirm the same fact from different sources | Government statistics + academic paper + field observation |
| **Method Triangulation** | Verify the same phenomenon with different methods | Interview + statistical analysis + literature review |
| **Perspective Triangulation** | Confirm from different stakeholders' viewpoints | Government + NGO + affected parties |
## Bias Analysis Checklist
| Bias Type | Detection Question | Countermeasure |
|-----------|-------------------|----------------|
| **Confirmation Bias** | Are we only collecting data that supports our desired conclusion? | Intentionally search for counter-evidence |
| **Survivorship Bias** | Are we only looking at success stories? What about failures? | Investigate failure cases with equal weight |
| **Selection Bias** | Are we only representing a specific group? | Include materials from diverse demographic groups |
| **Recency Bias** | Are we overvaluing recent events? | Include historical context |
| **Framing Bias** | Are we defining the problem in only one way? | Try redefining with a different frame |
## Research Documentation Standard
### Source Card Format
```
## Source #[Number]
- **Title**: [Material title]
- **Author/Institution**: [Name]
- **Publication Date**: [YYYY-MM-DD]
- **Type**: [PRIMA tier]
- **URL/DOI**: [Access path]
- **CRAAP Score**: [Score/100]
- **Key Citation**: "[Direct quote — quotation marks required]"
- **Summary**: [1-2 sentence key content]
- **Related Section**: [Which part of the documentary treatment will use this]
- **Cross-Check**: [Does it match other sources? Compare with Source #XX]
```
## Sensitive Topic Research Guide
### Legal/Ethical Checklist
- [ ] Is there no potential violation of personal data protection laws?
- [ ] Have facts been verified for any content that could constitute defamation?
- [ ] Have special protection standards been applied for information involving minors?
- [ ] Have quoted statements not been distorted by being taken out of context?
- [ ] Are appropriate warnings included for trauma-related content?
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!