claims-verifier SKILL.md skillA

claims-verifier from skillmedev/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add skillmedev/skills/claims-verifier@git:20261005.bea4ea5

Pins git:20261005.bea4ea5 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
skillmedev/skills
Path
skills/claims-verifier/SKILL.md
Versions recorded
3
Latest version
git:20261005.bea4ea5, committed Oct 5, 2026
First version recorded
Jul 5, 2026
Size
7,355 bytes
Repository stars
19
License
MIT

Decomposes a claim into checkable propositions, traces each through the citation chain to its primary source, appraises the evidence for method and independence, and issues a verdict from Supported to Contradicted with confidence. Use when someone asks "is this claim actually backed by the study it cites", "verify the claims in this whitepaper", "trace this statistic to its source", or needs an evidentiary audit of research, marketing, or policy claims. Do NOT use for a quick true/false…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Claims Verifier

The job is to determine whether a claim is supported by evidence - not whether it sounds plausible. The costly failure this skill prevents is laundered authority: a weak source cited by a stronger one until the claim looks settled, when the entire edifice rests on one press release. Extraordinary claims require extraordinary evidence.

## Inputs to collect

1. **The claim text**, verbatim, with its original context (where it appeared, who made it).
2. **The stakes**: what decision the verdict will inform. High-stakes claims get deeper chain-tracing.
3. **Any citations already attached** to the claim.
4. **Access constraints**: paywalled sources the user can or cannot retrieve. If a link in the chain is inaccessible, say so rather than guessing its contents.

## Operating procedure

### Step 1: Decompose the claim

Restate the claim as one or more single, falsifiable propositions. Apply the decomposition rules:

- One proposition per checkable fact. "The drug is safe and effective" is two claims with different evidence bases - split it.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add skillmedev/skills/claims-verifier@sha256:fba8b1ba7d69801d

The line at the top of this page pins the label git:20261005.bea4ea5, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_vi2idlco46slr3pl.svg)](https://markdownregistry.com/a/art_vi2idlco46slr3pl)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Jul 5, 2026 and Oct 5, 2026, about one every 46 days.

versioncommittedcommitsizeaudit
git:20261005.bea4ea5 latest2026-10-05 bea4ea5 7,355 BA view · diff
git:20260705.a28c4ce2026-07-05 a28c4ce 7,318 BA view · diff
git:20260705.acb55712026-07-05 acb5571 7,360 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7355 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

skillmedev/skills · 19 stars · license MIT · pushed 2026-10-13 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_vi2idlco46slr3pl
GET https://markdownregistry.com/api/v1/resolve?ref=skillmedev/skills/claims-verifier
GET https://markdownregistry.com/api/v1/blob/fba8b1ba7d69801d91cecc99a4f23f17debb353b10a2eded419b74dd91ef9adf

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from skillmedev/skills

1on1-agenda SKILL.md skill
skillmedev/skills · skills/1on1-agenda/SKILL.md · Structures recurring manager-report 1:1s with a rolling shared agenda that balances check-in, blockers, two-way…
git:20261005.bea4ea5 · audit A · 19 stars
ab-test-analyzer SKILL.md skill
skillmedev/skills · skills/ab-test-analyzer/SKILL.md · Analyzes an A/B experiment to a defensible verdict - sample-size and minimum-detectable-effect math, two-proportion…
git:20261005.bea4ea5 · audit A · 19 stars
abandoned-cart-sequence SKILL.md skill
skillmedev/skills · skills/abandoned-cart-sequence/SKILL.md · Drafts a margin-aware 3-email cart-recovery sequence that reminds, handles objections, then incentivizes only as a last…
git:20261005.bea4ea5 · audit A · 19 stars
academic-essay SKILL.md skill
skillmedev/skills · skills/academic-essay/SKILL.md · Structures and drafts argumentative academic essays - a contestable thesis, claim-evidence-analysis body paragraphs, a…
git:20261005.bea4ea5 · audit A · 19 stars
accessibility-audit SKILL.md skill
skillmedev/skills · skills/accessibility-audit/SKILL.md · Runs a full WCAG 2.2 accessibility audit of an interface - keyboard, screen reader, contrast and zoom, forms, and…
git:20261005.bea4ea5 · audit A · 19 stars
ad-creative-testing SKILL.md skill
skillmedev/skills · skills/ad-creative-testing/SKILL.md · Designs a disciplined ad creative testing system with hooks, isolated variables, and statistical rigor. Use when…
git:20261005.bea4ea5 · audit A · 19 stars
aeo-answer-blockifier SKILL.md skill
skillmedev/skills · skills/aeo-answer-blockifier/SKILL.md · Rewrites a section or page into concise, self-contained answer blocks that AI answer engines and search snippets can…
git:20261005.bea4ea5 · audit A · 19 stars
agency-monthly-report SKILL.md skill
skillmedev/skills · skills/agency-monthly-report/SKILL.md · Build the monthly client report that renews retainers - results-first structure with business outcomes before activity…
git:20260705.a28c4ce · audit A · 19 stars
agency-positioning SKILL.md skill
skillmedev/skills · skills/agency-positioning/SKILL.md · Reposition a generalist agency around a vertical or service specialization, write the "we're the agency that X for Y"…
git:20260705.a28c4ce · audit A · 19 stars
agency-qbr-upsell SKILL.md skill
skillmedev/skills · skills/agency-qbr-upsell/SKILL.md · Run agency quarterly business reviews that expand accounts - the four-part QBR agenda (results retrospective, goal…
git:20260705.a28c4ce · audit A · 19 stars
agent-orchestration SKILL.md skill
skillmedev/skills · skills/agent-orchestration/SKILL.md · Designs reliable multi-agent LLM systems - choosing a topology, writing handoff contracts between agents, deciding what…
git:20261005.bea4ea5 · audit A · 19 stars
alert-tuning SKILL.md skill
skillmedev/skills · skills/alert-tuning/SKILL.md · Reduces alert noise by making alerts actionable, symptom-based, and tied to SLOs. Identifies and kills flappy…
git:20261005.bea4ea5 · audit A · 19 stars

Every file in skillmedev/skills

Browse by kind, by grade A, or by owner.