# Fact Check

> Verify technical claims against primary sources — docs, source code, changelogs, reproducible examples — and mark what couldn't be verified instead of masking it with a confident tone. Use when you say "fact-check this", "verify these claims", doubt a technical statement, or before shipping material with disputed claims.

- **Type:** Skill
- **Install:** `agentstack add skill-archiesa-skills-fact-check`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ArchieSA](https://agentstack.voostack.com/s/archiesa)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ArchieSA](https://github.com/ArchieSA)
- **Source:** https://github.com/ArchieSA/skills/tree/main/fact-check

## Install

```sh
agentstack add skill-archiesa-skills-fact-check
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Fact-check against primary sources

## Procedure

1. Pull every statement that reads as a technical fact: API behavior, numbers, comparisons, versions, limits.
2. Classify each: fact / personal experience / hypothesis. Experience and hypotheses must be marked as such ("in my experience", "seems like") — they can't read as law.
3. For each fact, find a primary source: official docs, source code, changelog, RFC, issue, or a reproducible example. A secondary retelling (a blog, a chat) is a lead to the source, not proof.
4. Verdict per claim: confirmed (with the source) / refuted (and what's actually true) / couldn't verify.
5. Fix: correct what's refuted; soften the unverified to experience or hypothesis, or cut it; reframe an unproven "X is faster than Y" into the logic of a concrete scenario.
6. Report back: claim → verdict → source. Name the unverified plainly — don't mask it with a confident tone.

## What to check with

- **Web:** official docs, the project repository, changelogs, RFCs.
- **Code:** a short reproducible example right here (a REPL, a sandbox) — often faster and more reliable than searching.

## Red flags

- "always / everywhere / in all versions" — often the residue of compression that dropped the reason.
- A pretty claim you'd rather not check — check it first (confirmation bias).
- A number with no measurement method behind it.
- A comparison ("X is cheaper / faster than Y") stated as a general law from a single case.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [ArchieSA](https://github.com/ArchieSA)
- **Source:** [ArchieSA/skills](https://github.com/ArchieSA/skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-archiesa-skills-fact-check
- Seller: https://agentstack.voostack.com/s/archiesa
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.