🎯

skill-benchmark

🎯Skill

from workersio/spec

What it does

Part of the workers.io spec collection for software correctness, this skill benchmarks whether an AI agent skill actually improves outcomes, alongside tools for formal verification, model checking, and security auditing.

📦

Same repository

workersio/spec(9 items)

skill-benchmark

Installation

Vibe Index InstallInstalls to .claude/skills/ - auto-recognized by Claude Code

npx vibeindex add workersio/spec --skill skill-benchmark

skills.sh Install⚠ Installs to .agents/skills/ - may not be auto-recognized by Claude Code

npx skills add workersio/spec --skill skill-benchmark

Manual InstallCopy SKILL.md content and save to the path below

~/.claude/skills/skill-benchmark/SKILL.md

SKILL.md

92Installs

AddedMar 14, 2026

View on GitHub Back to Skills

More from this repository8

Skill

Skill

A structured security audit skill for Solana smart contracts covering 25 vulnerability types, systematically walking through attack vectors from missing signer checks and PDA validation to re-initialization attacks and arithmetic overflows.

🎯

axiom-verify🎯Skill

Part of the workers.io software correctness skills suite, providing Lean 4 proof verification and repair capabilities as a Claude Code slash command for formal verification of mathematical proofs and program correctness.

🎯

workers-app-tester🎯Skill

Part of workers.io's software correctness skills for Claude Code covering formal verification, model checking, and security auditing as slash commands. Provides mobile application security testing capabilities alongside proof repair and benchmarking tools.

🎯

fuzzer🎯Skill

Skill

🎯

audit-context-building🎯Skill

Skill

🎯

kage🎯Skill

Skill