Claude Code Skills·Claude Skills·The open SKILL.md registry for Claude
ClaudSkills / Security / forensics

Aether Verify

Category: Security  ·  Sub-category: forensics  ·  Last updated:
lang:rusttype:audit
Verify AI-generated answers and catch hallucinations with the Aether MCP tools, which proxy a claim to an upstream tribunal that decomposes it, cross-examines it (proposer/critic/verifier + red-team), scores trust, and returns a cryptographically signed warrant. Use whenever the user wants to fact-check, verify, trust-check, validate, confirm, corroborate, vet, or audit an AI answer, claim, statement, citation, quote, figure, or response before relying on it; guard against hallucination, fabrication, confabulation, or made-up facts; get a trust score, verdict, certification, or signed warrant / attestation / proof / receipt; or re-explain or fetch the full proof of a prior check by its verification_id. Fires on: verify, verify this, verify the answer, verify the claim, verification, reverify, fact-check, fact check, factcheck, check the facts, check this, check that, double-check, double check, triple-check, cross-check, cross-reference, sanity-check, sanity check, gut-check, reality-check, spot-check, validate, validation, confirm, confirm this, corroborate, substantiate, verify accuracy, vet, vet this, vet the claim, audit, audit this, audit this claim, review this claim, scrutinize, interrogate the claim; trust score, trustworthy, trustworthiness, trust check, trust-check, how trustworthy, can I trust this, should I trust this, do I trust this, is this reliable, reliability, is this legit, is this legitimate, is this solid; is this true, is that true, is this real, is this accurate, is this correct, is that right, is this factual, is this right, does this check out, holds up, accuracy, correctness, veracity, truthfulness; is this a hallucination, hallucination, hallucinate, hallucinating, made up, made-up, making it up, is it making this up, fabricated, fabrication, confabulation, invented, not real, bogus, is this BS, is this nonsense, is this wrong, could this be wrong, catch errors, catch mistakes, catch falsehoods, flag hallucinations, spot the lie, find the error; warrant, attestation, attest, attested, certified, certification, signed proof, cryptographic proof, proof, receipt, signed receipt, evidence, evidence trail, provenance, signed hash, get the proof, get the warrant, pull the warrant, show me the warrant, fetch the warrant, look up the warrant, explain the verdict, explain this verdict, why was it rejected, why contested, why is the score low, what did it flag, look up a verification, by verification_id, by warrant id; guard against, guardrail, safety-check, before I rely on this, before I send this, before I ship this, before I publish this, before I cite this, before I quote this, before I act on this, before I trust this, is this safe to use, is this answer safe; the AI said, the model said, ChatGPT said, Claude said, the chatbot said, an LLM told me, LLM output, model output, AI output, this answer, this response; check this source, does this source support the claim, is this grounded, is it grounded, source-backed, backed by sources, grounding, run it through Aether, run Aether, verify with Aether, check with Aether, Aether check, use Aether, ask Aether. NOT for general web search or finding new citations from scratch (use a search / research skill — Aether checks a claim you already have, it does not go find one), and NOT for running the tribunal locally — Aether is a thin proxy in front of the Base44 engine and cannot regenerate a warrant it never cached.
Security AStatic scan found no risk patternsHow grading works ›

About this skill (catalog notes)

Aether Verify includes explicit scope boundaries (an explicit 'when not to use' or 'out of scope' section); a dedicated installation section; pricing or quota commentary. At roughly 1,599 words the SKILL.md is on the longer end of the catalog distribution.

License
MIT
Original author
Deepsea1
Indexed lastmod
Catalog position
Security · forensics
Indexed related skills
10

How Aether Verify fits the catalog

Aether Verify sits in the Security category under the forensics sub-topic in the ClaudSkills catalog. There are 10 related skills indexed alongside it; comparing a few before installing usually reveals which fits your workflow best.

These notes are auto-generated from features detected in the SKILL.md file and from this catalog's structure — they aren't part of the source repository.

From the source SKILL.md

Aether checks whether an AI-generated answer is trustworthy. You submit the answer text (plus optional source URLs); an upstream tribunal decomposes it, cross-examines it, scores it, and signs a warrant (a durable proof record). These MCP tools are the interface to that engine. Use them to put a verdict and a trust score on any claim before the user relies on it.

What this skill does

Aether Verify is a community-contributed Claude Code skill in the forensics sub-category. It ships as a SKILL.md file that Claude Code auto-discovers under ~/.claude/skills/aether-verify/ and loads when your prompt matches the skill's trigger.

When to invoke it: Use whenever the user wants to fact-check, verify, trust-check, validate, confirm, corroborate, vet, or audit an AI answer, claim, statement, citation, quote, figure, or response before relying on it; guard against hallucination, fabrication, confabulation, or made-up facts; get a trust score, verdict, certification, or signed warrant / attestation / proof / receipt; or re-explain or fetch the full proof of a prior check by its verification_id. Fires on: verify, verify this, verify the answer, verify the claim, verification, reverify, fact-check, fact check, factcheck, check the facts, check this, check that, double-check, double check, triple-check, cross-check, cross-reference, sanity-check, sanity check, gut-check, reality-check, spot-check, validate, validation, confirm, confirm this, corroborate, substantiate, verify accuracy, vet, vet this, vet the claim, audit, audit this, audit this claim, review this claim, scrutinize, interrogate the claim; trust score, trustworthy, trustworthiness, trust check, trust-check, how trustworthy, can I trust this, should I trust this, do I trust this, is this reliable, reliability, is this legit, is this legitimate, is this solid; is this true, is that true, is this real, is this accurate, is this correct, is that right, is this factual, is this right, does this check out, holds up, accuracy, correctness, veracity, truthfulness; is this a hallucination, hallucination, hallucinate, hallucinating, made up, made-up, making it up, is it making this up, fabricated, fabrication, confabulation, invented, not real, bogus, is this BS, is this nonsense, is this wrong, could this be wrong, catch errors, catch mistakes, catch falsehoods, flag hallucinations, spot the lie, find the error; warrant, attestation, attest, attested, certified, certification, signed proof, cryptographic proof, proof, receipt, signed receipt, evidence, evidence trail, provenance, signed hash, get the proof, get the warrant, pull the warrant, show me the warrant, fetch the warrant, look up the warrant, explain the verdict, explain this verdict, why was it rejected, why contested, why is the score low, what did it flag, look up a verification, by verification_id, by warrant id; guard against, guardrail, safety-check, before I rely on this, before I send this, before I ship this, before I publish this, before I cite this, before I quote this, before I act on this, before I trust this, is this safe to use, is this answer safe; the AI said, the model said, ChatGPT said, Claude said, the chatbot said, an LLM told me, LLM output, model output, AI output, this answer, this response; check this source, does this source support the claim, is this grounded, is it grounded, source-backed, backed by sources, grounding, run it through Aether, run Aether, verify with Aether, check with Aether, Aether check, use Aether, ask Aether.

Who uses this skill

The Aether Verify Claude Code skill is built for security engineers, penetration testers, DevSecOps practitioners, and development teams hardening codebases and infrastructure. It's part of ClaudSkills (also referred to as Claude Skills or Claude Code Skills) — the open community-curated registry of 185,000+ SKILL.md files for Anthropic's Claude Code agent and the wider Claude ecosystem (Claude API, Claude Agent SDK).

How to install

Free

Manual install (2 steps)

mkdir -p ~/.claude/skills/aether-verify
curl -L https://claudskills.com/skills/aether-verify/SKILL.md \
  -o ~/.claude/skills/aether-verify/SKILL.md

Or just download SKILL.md directly and drop it into ~/.claude/skills/aether-verify/. Claude Code auto-discovers it on next session.

Skills live at ~/.claude/skills/aether-verify/SKILL.md on macOS/Linux, or %USERPROFILE%\.claude\skills\aether-verify\SKILL.md on Windows. See the full install guide for step-by-step instructions.

Telegram

📱 Install from your phone or desktop Telegram

Open @claudskills_bot on Telegram, tap Open Desktop App, and the desktop app installs this skill for you. Or share the bot link with a colleague — they get the same one-tap install. Learn more →

Pro

One-click install via the desktop app

The ClaudSkills desktop app installs any skill directly into ~/.claude/skills/ with one click — no terminal required. Pro starts at $9/mo or $149 lifetime.

Pro

For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.

Frequently asked questions

How do I install the Aether Verify Claude Code skill?
Install via the ClaudSkills desktop app (one click) or copy SKILL.md from the source repository to ~/.claude/skills/aether-verify/SKILL.md and restart Claude Code. Both flows are detailed at claudskills.com/install/.
What does the Aether Verify skill do?
Verify AI-generated answers and catch hallucinations with the Aether MCP tools, which proxy a claim to an upstream tribunal that decomposes it, cross-examines it (proposer/critic/verifier + red-team), scores trust, and returns a cryptographically signed warrant. Use whenever the user wants to fact-check, verify, trust-check, validate, confirm, corroborate, vet, or audit an AI answer, claim, statement, citation, quote, figure, or response before relying on it; guard against hallucination, fabrication, confabulation, or made-up facts; get a trust score, verdict, certification, or signed warrant / attestation / proof / receipt; or re-explain or fetch the full proof of a prior check by its verification_id. Fires on: verify, verify this, verify the answer, verify the claim, verification, reverify, fact-check, fact check, factcheck, check the facts, check this, check that, double-check, double check, triple-check, cross-check, cross-reference, sanity-check, sanity check, gut-check, reality-check, spot-check, validate, validation, confirm, confirm this, corroborate, substantiate, verify accuracy, vet, vet this, vet the claim, audit, audit this, audit this claim, review this claim, scrutinize, interrogate the claim; trust score, trustworthy, trustworthiness, trust check, trust-check, how trustworthy, can I trust this, should I trust this, do I trust this, is this reliable, reliability, is this legit, is this legitimate, is this solid; is this true, is that true, is this real, is this accurate, is this correct, is that right, is this factual, is this right, does this check out, holds up, accuracy, correctness, veracity, truthfulness; is this a hallucination, hallucination, hallucinate, hallucinating, made up, made-up, making it up, is it making this up, fabricated, fabrication, confabulation, invented, not real, bogus, is this BS, is this nonsense, is this wrong, could this be wrong, catch errors, catch mistakes, catch falsehoods, flag hallucinations, spot the lie, find the error; warrant, attestation, attest, attested, certified, certification, signed proof, cryptographic proof, proof, receipt, signed receipt, evidence, evidence trail, provenance, signed hash, get the proof, get the warrant, pull the warrant, show me the warrant, fetch the warrant, look up the warrant, explain the verdict, explain this verdict, why was it rejected, why contested, why is the score low, what did it flag, look up a verification, by verification_id, by warrant id; guard against, guardrail, safety-check, before I rely on this, before I send this, before I ship this, before I publish this, before I cite this, before I quote this, before I act on this, before I trust this, is this safe to use, is this answer safe; the AI said, the model said, ChatGPT said, Claude said, the chatbot said, an LLM told me, LLM output, model output, AI output, this answer, this response; check this source, does this source support the claim, is this grounded, is it grounded, source-backed, backed by sources, grounding, run it through Aether, run Aether, verify with Aether, check with Aether, Aether check, use Aether, ask Aether. NOT for general web search or finding new citations from scratch (use a search / research skill — Aether checks a claim you already have, it does not go find one), and NOT for running the tribunal locally — Aether is a thin proxy in front of the Base44 engine and cannot regenerate a warrant it never cached.
Is this skill free to install?
Yes. ClaudSkills is an open registry — every skill keeps its source repository's license, and manual install via copy is free. ClaudSkills Pro ($9/mo, $79/yr, or $149 one-time) adds one-click install via the desktop app and a multi-signal Quality Score.
When should I use the Aether Verify skill?
Use Aether Verify when your Claude Code task falls under the Security category — specifically in the forensics area. Claude Code auto-discovers installed skills and invokes the right one based on the task description, so you can also ask Claude directly (e.g. "use Aether Verify" or describe the task and let Claude pick). Browse related skills at /category/security/.
What is a Claude Code skill and how does the Aether Verify skill fit in?
A Claude Code skill is a SKILL.md file that lives under ~/.claude/skills/<name>/ and tells the Claude Code CLI agent how to perform a specific task (instructions, prompts, allowed tools). Skills are auto-discovered at session start. Aether Verify is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the Security category. Learn more at /learn/what-is-a-claude-skill/.

Attribution & license

Cite this skill

If you reference this skill in a blog post, paper, or documentation, you can cite it as:

APA
Deepsea1. (2026). Aether Verify [Claude Code skill]. ClaudSkills. https://claudskills.com/skills/aether-verify/
BibTeX
@misc{aether-verify-2026,
  author    = {Deepsea1},
  title     = {Aether Verify [Claude Code skill]},
  year      = {2026},
  publisher = {ClaudSkills},
  url       = {https://claudskills.com/skills/aether-verify/}
}

Embed this skill

Promote, attribute, or link this skill from your own README, blog post, or documentation. All three snippets are free to use — no sign-up, no API key. More distribution surfaces →

Badge
[![ClaudSkills](https://claudskills.com/badge/aether-verify.svg)](https://claudskills.com/skills/aether-verify/?utm_source=badge&utm_medium=readme&utm_campaign=skill_badge)
<script>
<script src="https://claudskills.com/embed/aether-verify.js" async></script>
<iframe>
<iframe src="https://claudskills.com/embed/aether-verify.html" width="100%" height="160" frameborder="0" loading="lazy" title="ClaudSkills: Aether Verify"></iframe>

Security scan

Grade A · scanned 2026-08-14 — free static scan against the OWASP Agentic Skills Top 10.

No risk patterns were found in any of the ten OWASP-aligned categories. How grading works ›

Show this grade on your repo (click to copy):

[![Security: A](https://img.shields.io/badge/Security-A-2e7d32)](https://claudskills.com/skills/aether-verify/#security)

Free. No spam. Unsubscribe in one click.

More Security skills

Browse all Security skills in the ClaudSkills registry, or explore these other picks from the same category:

Browse all Security skills → Top 100 skills
Part of ClaudSkills — the open registry for Claude Skills & Claude Code Skills.  ·  What's New  ·  Install guide  ·  About  ·  llms.txt

Part of Acreator Store — Adam Lankamer's AI tools: PerfectStudio · Ucaption · UTagger · AutoXPoster · TestYourSkills · AutomationFlows · Au Naturel · Telegram @acreatorstore