verus-expert SKILL.md skillA

verus-expert from rysweet/amplihack-rs is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add rysweet/amplihack-rs/verus-expert@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
rysweet/amplihack-rs
Path
amplifier-bundle/skills/verus-expert/SKILL.md
Versions recorded
1
Latest version
v1.0.0, committed Jul 26, 2026
Size
4,798 bytes
Repository stars
11
License
none declared

Verus deductive-verification expert for proving Rust functional correctness, panic-freedom, and arithmetic-overflow-freedom with SMT-backed specs and LLM-assisted proof synthesis.

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

# Verus Expert Skill

## Purpose

Provides expert-level Verus assistance for deductive verification of Rust:
writing specifications, proving panic-freedom and arithmetic-overflow-freedom,
authoring loop invariants and proofs, debugging failed verification, and using
LLM proof synthesis (auto-verus) safely behind the verifier.

## When This Skill Activates

- User asks to write or review Verus specifications (`requires`, `ensures`,
  `invariant`, `decreases`) for Rust code
- User wants to prove panic-freedom or arithmetic-overflow-freedom on a function
- User needs help authoring loop invariants, assertions, or `proof fn` lemmas
- User is debugging a failed Verus verification (failed pre/postcondition,
  overflow, timeout, quantifier trigger issues)
- User asks about Verus modes (`spec`/`proof`/`exec`), ghost/tracked code, or
  `int`/`nat` reasoning
- User wants to apply LLM proof synthesis (auto-verus / AutoVerus / VeruSAGE) as
  a proposer behind the Verus checker
- User is deciding between Verus, Lean 4, and TLA+ for a Rust verification goal

## How It Works

This skill delegates to the `verus-expert` agent, which has evidence-grounded
knowledge of:
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add rysweet/amplihack-rs/verus-expert@sha256:24aefa3598235435

The line at the top of this page pins the label v1.0.0, 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_zj6ih4j5ufcpkvfd.svg)](https://markdownregistry.com/a/art_zj6ih4j5ufcpkvfd)

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

Versions

The registry has recorded 1 version of this file, committed on Jul 26, 2026.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-07-26 2cf60b6 4,798 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 (4798 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

rysweet/amplihack-rs · 11 stars · license none declared · pushed 2026-10-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_zj6ih4j5ufcpkvfd
GET https://markdownregistry.com/api/v1/resolve?ref=rysweet/amplihack-rs/verus-expert
GET https://markdownregistry.com/api/v1/blob/24aefa3598235435bae004026b7f9b1b3b065e10e39deac7e9b494a4eba62a1b

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 rysweet/amplihack-rs

AGENTS.md AGENTS.md file
rysweet/amplihack-rs · AGENTS.md
git:20260827.b47120c · audit A · 11 stars
CLAUDE.md@amplifier-bundle CLAUDE.md file
rysweet/amplihack-rs · amplifier-bundle/CLAUDE.md
git:20260503.51b67fa · audit A · 11 stars
agent-generator-tutor SKILL.md skill
rysweet/amplihack-rs · amplifier-bundle/skills/agent-generator-tutor/SKILL.md · Interactive teaching agent for the goal-seeking agent generator and eval system. Provides a structured 14-lesson…
v1.0.0 · audit A · 11 stars
agentic-workflow-first SKILL.md skill
rysweet/amplihack-rs · amplifier-bundle/skills/agentic-workflow-first/SKILL.md · Start new work as a deterministic workflow of agentic steps, prompts, and tools instead of code. Use when designing a…
v1.0 · audit A · 11 stars
amplihack-expert SKILL.md skill
rysweet/amplihack-rs · amplifier-bundle/skills/amplihack-expert/SKILL.md · Comprehensive knowledge of amplihack framework architecture, patterns, and usage
v2.0.0 · audit A · 11 stars
anthropologist-analyst SKILL.md skill
rysweet/amplihack-rs · amplifier-bundle/skills/anthropologist-analyst/SKILL.md · Analyzes events through anthropological lens using cultural analysis, ethnographic methods, kinship and social…
v1.0.0 · audit A · 11 stars
aspire SKILL.md skill
rysweet/amplihack-rs · amplifier-bundle/skills/aspire/SKILL.md · Aspire orchestration for cloud-native distributed applications in any language (C#, Python, Node.js, Go). Handles…
v1.0.0 · audit A · 11 stars
authenticated-web-scraper SKILL.md skill
rysweet/amplihack-rs · amplifier-bundle/skills/authenticated-web-scraper/SKILL.md · Scrape authenticated websites from WSL2 using Edge CDP. Launches headed Edge for user auth, then headless scraping via…
v1.0.0 · audit A · 11 stars
auto-drive-to-merge SKILL.md skill
rysweet/amplihack-rs · amplifier-bundle/skills/auto-drive-to-merge/SKILL.md · Wraps default-workflow and drives the resulting PR all the way to merge: build the PR, loop with the…
v1.0.0 · audit A · 11 stars
awesome-copilot-sync SKILL.md skill
rysweet/amplihack-rs · amplifier-bundle/skills/awesome-copilot-sync/SKILL.md · Monitors awesome-copilot releases for drift against the amplihack integration. Checks latest commits on…
v1.0.0 · audit A · 11 stars
azure-admin SKILL.md skill
rysweet/amplihack-rs · amplifier-bundle/skills/azure-admin/SKILL.md · Comprehensive Azure administration capabilities covering identity management, resource orchestration, CLI tooling, and…
git:20260405.b840a93 · audit B · 11 stars
azure-devops SKILL.md skill
rysweet/amplihack-rs · amplifier-bundle/skills/azure-devops/SKILL.md · Complete Azure DevOps (ADO) automation — work items, boards, sprints, repos, pull requests, pipelines, builds…
v2.0.0 · audit A · 11 stars

Every file in rysweet/amplihack-rs

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