# Claim verify

> Claim verify is an open-source agent skill. Use when the user has a results draft or a set of data-backed claims and wants each one adversarially verified against the underlying datase. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

- **Kind:** Skill
- **Pricing:** Open source
- **Platforms:** Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- **Website:** https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/claim-verify
- **Repository:** https://github.com/gaasher/agent-loop-skills
- **GitHub stars:** 183
- **License:** MIT
- **Skill name:** claim-verify
- **Collection:** https://github.com/gaasher/Agent-Loop-Skills
- **Listing updated:** 2026-11-17

## About

Use when the user has a results draft or a set of data-backed claims and wants each one adversarially verified against the underlying dataset before publishing — a pre-publication red-team of the findings. Extracts the discrete checkable claims from the draft, reproduces each claim's number against the data, stress-tests it against the threats most likely to kill it (outliers, confounds, Simpson's reversals, tiny subgroups, alternative specifications), and marks it verified, fragile, or refuted; fragile and refuted claims are revised — hedged, scoped, or retracted — until every claim is verified or appropriately qualified. The result is a draft where every surviving claim has been reproduced and survived a stress test. Not for open-ended discovery of new findings over a dataset (that is a data-analysis task), and not for diagnosing a single known anomaly or pipeline failure — this is a gate over an existing draft.

## When your agent uses it

> Use when the user has a results draft or a set of data-backed claims and wants each one adversarially verified against the underlying dataset before publishing — a pre-publication red-team of the findings. Extracts the discrete checkable claims from the draft, reproduces each claim's number against the data, stress-tests it against the threats most likely to kill it (outliers, confounds, Simpson's reversals, tiny subgroups, alternative specifications), and marks it verified, fragile, or refuted; fragile and refuted claims are revised — hedged, scoped, or retracted — until every claim is verified or appropriately qualified. The result is a draft where every surviving claim has been reproduced and survived a stress test. Not for open-ended discovery of new findings over a dataset (that is a data-analysis task), and not for diagnosing a single known anomaly or pipeline failure — this is a gate over an existing draft.

## What it can access

From a static check of the files on GitHub; nothing was run.

- [Instructions only, no scripts](https://github.com/gaasher/Agent-Loop-Skills/tree/HEAD/loops/claim-verify)
- [License: MIT](https://github.com/gaasher/Agent-Loop-Skills/tree/HEAD/loops/claim-verify)

## Install

### Claude Code

This skill ships in the `agent-loops` plugin. In Claude Code, add the marketplace and install the plugin (it may include other skills too):

```sh
/plugin marketplace add gaasher/Agent-Loop-Skills
/plugin install agent-loops@agent-loop-skills
```

Or copy only this skill to `~/.claude/skills/claim-verify`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/claim-verify &&
cp -R "$tmp/loops/claim-verify" ~/.claude/skills/claim-verify &&
rm -rf "$tmp"
```

For one project only, put the folder in `.claude/skills/claim-verify` inside it instead.

### Codex

Copy the skill folder to `~/.agents/skills/claim-verify` to use it in every repository:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/claim-verify &&
cp -R "$tmp/loops/claim-verify" ~/.agents/skills/claim-verify &&
rm -rf "$tmp"
```

For one repository only, put the folder in `.agents/skills/claim-verify` inside it instead.

### Cursor

Copy the skill folder to `~/.cursor/skills/claim-verify` to use it in every project:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/claim-verify &&
cp -R "$tmp/loops/claim-verify" ~/.cursor/skills/claim-verify &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/claim-verify` inside it instead.

### Gemini CLI

Run in a terminal (add `--scope workspace` to install it for the current workspace only):

```sh
gemini skills install https://github.com/gaasher/Agent-Loop-Skills.git --path loops/claim-verify
```

Or copy the folder to `~/.gemini/skills/claim-verify` yourself.

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/claim-verify`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/claim-verify &&
cp -R "$tmp/loops/claim-verify" ~/.copilot/skills/claim-verify &&
rm -rf "$tmp"
```

For one project only, put the folder in `.github/skills/claim-verify` inside it instead.

### Other agents

Get the folder:

```sh
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git
```

Then copy `Agent-Loop-Skills/loops/claim-verify` into your agent's skills folder as `claim-verify`. Agents that support SKILL.md read one folder per skill.

## FAQ

### How do I install Claim verify in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/claim-verify to use it in all your projects, or to .claude/skills/claim-verify in one project. Or install the agent-loops plugin, which includes it: /plugin marketplace add gaasher/Agent-Loop-Skills, then /plugin install agent-loops@agent-loop-skills.

### Does Claim verify run scripts?

No. It is instructions only, with no scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

### Which AI agents can use Claim verify?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

---
Source: https://ai-powered.com/skills/claim-verify
