# research-claim-map

research-claim-map — a skill for Claude Code and Codex that systematically investigates claims and triangulates sources. Runs during fact-checking, due diligence workflows, and conflicting evidence reviews.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 101 installs · ★ 203 repo stars
- Author: lyndonkl
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/lyndonkl/claude/tree/HEAD/skills/research-claim-map/SKILL.md
- Updated: 2026-09-01
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/research-claim-map

## What it does

The skill formalizes claims into narrow, testable statements featuring concrete figures or milestones, then groups collected references into supporting and opposing evidence buckets. It classifies material across three tiers: primary evidence like raw records and audit trails, secondary syntheses like peer-reviewed literature, and tertiary summaries like corporate PR or encyclopedia articles. Unsubstantiated posts and circular citations are flagged as non-evidence.

Every citation receives scrutiny across expertise, commercial independence, past error rates, and procedural transparency. Instead of vague labels, the output assigns a concrete confidence metric between 0 and 100% while highlighting blind spots and core assumptions. The delivery workflow enforces a self-audit via `resources/evaluators/rubric_research_claim_map.json`, requiring an average rubric score of at least 3.5 before outputting results.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill research-claim-map -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/research-claim-map/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/research-claim-map/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill research-claim-map -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/research-claim-map/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill research-claim-map -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/research-claim-map/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install lyndonkl/claude skills/research-claim-map
```

2. **Manually: put the files in place**
- File: `.github/skills/research-claim-map/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill research-claim-map -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/lyndonkl/claude --path skills/research-claim-map
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/research-claim-map/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill research-claim-map -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/lyndonkl/claude/tree/HEAD/skills/research-claim-map/SKILL.md

## When to use it
- verify vendor marketing metrics against actual system logs
- spot methodological flaws and sample skew in academic claims
- disentangle contradictory press reports by tracing back to source records
- assign calibrated confidence percentages to complex business statements

## Example prompts
- Fact-check this vendor claim about 99.9% uptime using research-claim-map
- Evaluate these conflicting news reports and map their primary sources
- Run due diligence on this statistical study before our technical review

## Similar
- [claim-investigation](https://affpapa.org/en/nevibecode/skills/claim-investigation.md) — skill · 374 installs
- [content-research-and-sourcing](https://affpapa.org/en/nevibecode/skills/content-research-and-sourcing.md) — skill · 1300 installs
- [deep-research](https://affpapa.org/en/nevibecode/skills/genspark-ai-deep-research.md) — skill · ★ 12746 repo stars
- [financial-deep-research](https://affpapa.org/en/nevibecode/skills/financial-deep-research.md) — skill · 987 installs
- [research](https://affpapa.org/en/nevibecode/skills/danjdewhurst-research.md) — skill · 463 installs
- [stock-research-executor](https://affpapa.org/en/nevibecode/skills/stock-research-executor.md) — skill · 1800 installs

From the same set: [lyndonkl/claude](https://affpapa.org/en/nevibecode/by/lyndonkl/claude.md) — 49 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
