Fact Check
- 217 installs
- 48 repo stars
- Updated March 22, 2026
- collaborative-deep-research/agent-papers-cli
Fact-check is an agent skill that verifies claims via decomposed sub-claims, web and academic search, and cited Supported/Unsupported verdicts.
About
Fact-check is an agent skill from the agent-papers-cli stack that turns a single bold statement into an evidence-backed assessment solo builders can trust before they write landing copy, pitch decks, or technical posts. When a user asks to verify, fact-check, or confirm something, the skill first decomposes the claim into verifiable sub-claims, then runs structured paper-search queries across the open web and Semantic Scholar, drills into arXiv sections or browsed URLs for primary material, assigns one of four verdicts per sub-claim, and finishes with an overall assessment plus cited URLs. It fits indie researchers who cannot afford a human fact desk but still need to avoid publishing hallucinated statistics or misquoted papers. The allowed-tools surface (Bash, Read, Glob, Grep, Write) implies network-backed CLI search rather than guesswork from model weights. Use it in early Idea research, during Validate when testing positioning claims, or in Launch/Grow when auditing public-facing statements. It is not a legal compliance review or real-time news wire—latency and coverage depend on what paper-search returns.
- Five-step workflow: Decompose → Search → Verify Sources → Assess → Report
- paper-search against Google web, Semantic Scholar snippets, and paper lists (--limit 5)
- paper read and paper-search browse for primary-source verification
- Four verdict buckets: Supported, Partially supported, Unsupported, Uncertain
- Mandatory citation rule: no verdict without specific sources and URLs
Fact Check by the numbers
- 217 all-time installs (skills.sh)
- Ranked #2,765 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: MEDIUM risk (skills.sh audit)
- Data as of Jul 29, 2026 (Skillselion catalog sync)
npx skills add https://github.com/collaborative-deep-research/agent-papers-cli --skill fact-checkAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 217 |
|---|---|
| repo stars | ★ 48 |
| Security audit | 2 / 3 scanners passed |
| Last updated | March 22, 2026 |
| Repository | collaborative-deep-research/agent-papers-cli ↗ |
What it does
Verify a user claim by decomposing it, searching web and Semantic Scholar, reading primary sources, and returning cited verdicts per sub-claim.
Who is it for?
Best when you're validating technical, scientific, or market statements before shipping content, specs, or investor narratives.
Skip if: Situations requiring certified legal review, classified sources, or instant breaking-news confirmation without search tooling.
When should I use this skill?
The user asks to verify, fact-check, or confirm a statement (argument-hint: claim to verify).
What you get
You receive a structured report with per sub-claim verdicts, an overall assessment, and URLs to the sources your agent inspected.
- Sub-claim list with Supported/Partially supported/Unsupported/Uncertain verdicts
- Overall assessment with cited URLs
By the numbers
- 5-step fact-check workflow (Decompose through Report)
- 4 verdict categories per sub-claim
- Semantic Scholar paper search default --limit 5
Files
Fact-check the following claim: "$ARGUMENTS"
1. Decompose
Break the claim into specific, verifiable sub-claims. List them explicitly before searching.
2. Search for Evidence
For each sub-claim:
paper-search google web "<sub-claim as question>"
paper-search semanticscholar snippets "<sub-claim keywords>"
paper-search semanticscholar papers "<sub-claim keywords>" --limit 53. Verify Sources
For each promising source:
paper read <arxiv_id> <relevant section> # for academic papers
paper-search browse <url> # for web pagesPrefer primary sources (original papers, official data) over secondary reports.
4. Assess
For each sub-claim, assign a verdict:
- Supported: strong evidence from multiple reliable sources
- Partially supported: some evidence, with caveats
- Unsupported: no evidence found, or evidence contradicts the claim
- Uncertain: insufficient evidence to judge
5. Report
Present:
- The original claim
- Each sub-claim with its verdict and supporting evidence
- An overall assessment
- All sources cited with URLs
Guidelines
- Always cite specific sources — never state a verdict without evidence.
- Distinguish between "no evidence found" and "evidence contradicts."
- Note the quality and recency of sources.
- If a claim is about a specific paper, read that paper directly rather than relying on summaries.
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10How it compares
Structured evidence workflow with academic CLI search—not a generic web-scrape skill or single-shot LLM 'true/false' answer.
FAQ
Who is fact-check for?
founders, technical writers, and agent users who need cited verification of specific statements using web and Semantic Scholar sources.
When should I use fact-check?
In Idea/research before trusting a stat; in Validate when testing positioning; in Launch/Grow when confirming claims in SEO copy or release notes—the trigger is 'verify, fact-check, or confirm' a statement.
Is fact-check safe to install?
It uses Bash and network search tools—check the Security Audits panel on this page and restrict credentials before granting shell on production machines.