Claude Code Skills·Claude Skills·The open SKILL.md registry for Claude
ClaudSkills / Security / red-team

Karpathy Metric Pre

Category: Security  ·  Sub-category: red-team  ·  Last updated:
Use this when: red-team my optimization metric, find ways to game my metric, metric pre-mortem, adversarial metric evaluation, gaming vectors for my KPI, what could an agent exploit in my metric, metric failure modes, proxy divergence risk, eval contamination, silent degradation from optimization, metric gaming pre-mortem, is my metric robust enough for auto-improvement, build secondary metrics, evaluation diversity plan, metric countermeasures, what does overfitting look like in my system, holdout scenario design, disappearance test, metric gaming attack surface, is my metric gameable, optimization agent failure modes, what could go wrong with my eval, unsupervised optimization risk, metric red team
Security AStatic scan found no risk patternsHow grading works ›

From the source SKILL.md

<role> You are an adversarial evaluation specialist — a red-teamer for metrics. Your job is to think like an optimization agent that has no values, no common sense, and no understanding of intent — only a score to maximize. You find every crack between what a metric measures and what the human actually wants. You are not here to be reassuring. You are here to surface the failure modes that look like success until they don't. </role>

What this skill does

Karpathy Metric Pre is a community-contributed Claude Code skill in the red-team sub-category. It ships as a SKILL.md file that Claude Code auto-discovers under ~/.claude/skills/karpathy-metric-pre/ and loads when your prompt matches the skill's trigger.

Who uses this skill

The Karpathy Metric Pre 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 153,000+ 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/karpathy-metric-pre
curl -L https://claudskills.com/skills/karpathy-metric-pre/SKILL.md \
  -o ~/.claude/skills/karpathy-metric-pre/SKILL.md

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

Skills live at ~/.claude/skills/karpathy-metric-pre/SKILL.md on macOS/Linux, or %USERPROFILE%\.claude\skills\karpathy-metric-pre\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.

See pricing → Download desktop app

Frequently asked questions

How do I install the Karpathy Metric Pre Claude Code skill?
Install via the ClaudSkills desktop app (one click) or copy SKILL.md from the source repository to ~/.claude/skills/karpathy-metric-pre/SKILL.md and restart Claude Code. Both flows are detailed at claudskills.com/install/.
What does the Karpathy Metric Pre skill do?
Use this when: red-team my optimization metric, find ways to game my metric, metric pre-mortem, adversarial metric evaluation, gaming vectors for my KPI, what could an agent exploit in my metric, metric failure modes, proxy divergence risk, eval contamination, silent degradation from optimization, metric gaming pre-mortem, is my metric robust enough for auto-improvement, build secondary metrics, evaluation diversity plan, metric countermeasures, what does overfitting look like in my system, holdout scenario design, disappearance test, metric gaming attack surface, is my metric gameable, optimization agent failure modes, what could go wrong with my eval, unsupervised optimization risk, metric red team
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 Karpathy Metric Pre skill?
Use Karpathy Metric Pre when your Claude Code task falls under the Security category — specifically in the red team 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 Karpathy Metric Pre" or describe the task and let Claude pick). Browse related skills at /category/security/.
What is a Claude Code skill and how does the Karpathy Metric Pre 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. Karpathy Metric Pre 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
drewid74. (2026). Karpathy Metric Pre [Claude Code skill]. ClaudSkills. https://claudskills.com/skills/karpathy-metric-pre/
BibTeX
@misc{karpathy-metric-pre-2026,
  author    = {drewid74},
  title     = {Karpathy Metric Pre [Claude Code skill]},
  year      = {2026},
  publisher = {ClaudSkills},
  url       = {https://claudskills.com/skills/karpathy-metric-pre/}
}

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/karpathy-metric-pre.svg)](https://claudskills.com/skills/karpathy-metric-pre/?utm_source=badge&utm_medium=readme&utm_campaign=skill_badge)
<script>
<script src="https://claudskills.com/embed/karpathy-metric-pre.js" async></script>
<iframe>
<iframe src="https://claudskills.com/embed/karpathy-metric-pre.html" width="100%" height="160" frameborder="0" loading="lazy" title="ClaudSkills: Karpathy Metric Pre"></iframe>

Security scan

Grade A · scanned 2026-07-18 — 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/karpathy-metric-pre/#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

Categories

Use cases

Popular tags

Learn

Site