Claude Code Skills·Claude Skills·The open SKILL.md registry for Claude
ClaudSkills / Engineering / testing

Subagent Eval

Category: Engineering  ·  Sub-category: testing  ·  Last updated:
ai:agent
Empirically evaluate and optimise a Claude Code sub-agent via a blinded head-to-head against the production baseline, then pick its model on data. Use when tuning a sub-agent's prompt, choosing or re-checking its model (e.g. a new model release), proving an agent change before committing, or testing whether a specialist beats native Explore. To author a new agent first, read AUTHORING.md.
Security AStatic scan found no risk patternsHow grading works ›

From the source SKILL.md

Prove a sub-agent change with evidence before shipping it. Run three times to date (codebase-, thoughts-, docs-*) — reproduce that loop. Quality is the deciding metric; cost/latency break ties only.

What this skill does

Subagent Eval is a community-contributed Claude Code skill in the testing sub-category. It ships as a SKILL.md file that Claude Code auto-discovers under ~/.claude/skills/subagent-eval/ and loads when your prompt matches the skill's trigger.

When to invoke it: Use when tuning a sub-agent's prompt, choosing or re-checking its model (e.g.

Who uses this skill

The Subagent Eval Claude Code skill is built for software engineers, backend developers, full-stack teams, and technical leads building and maintaining production systems. It's part of ClaudSkills (also referred to as Claude Skills or Claude Code Skills) — the open community-curated registry of 211,000+ 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/subagent-eval
curl -L https://claudskills.com/skills/subagent-eval/SKILL.md \
  -o ~/.claude/skills/subagent-eval/SKILL.md

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

Skills live at ~/.claude/skills/subagent-eval/SKILL.md on macOS/Linux, or %USERPROFILE%\.claude\skills\subagent-eval\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 Subagent Eval Claude Code skill?
Install via the ClaudSkills desktop app (one click) or copy SKILL.md from the source repository to ~/.claude/skills/subagent-eval/SKILL.md and restart Claude Code. Both flows are detailed at claudskills.com/install/.
What does the Subagent Eval skill do?
Empirically evaluate and optimise a Claude Code sub-agent via a blinded head-to-head against the production baseline, then pick its model on data. Use when tuning a sub-agent's prompt, choosing or re-checking its model (e.g. a new model release), proving an agent change before committing, or testing whether a specialist beats native Explore. To author a new agent first, read AUTHORING.md.
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 Subagent Eval skill?
Use Subagent Eval when your Claude Code task falls under the Engineering category — specifically in the testing 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 Subagent Eval" or describe the task and let Claude pick). Browse related skills at /category/engineering/.
What is a Claude Code skill and how does the Subagent Eval 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. Subagent Eval is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the Engineering 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
samjmarshall. (2026). Subagent Eval [Claude Code skill]. ClaudSkills. https://claudskills.com/skills/subagent-eval/
BibTeX
@misc{subagent-eval-2026,
  author    = {samjmarshall},
  title     = {Subagent Eval [Claude Code skill]},
  year      = {2026},
  publisher = {ClaudSkills},
  url       = {https://claudskills.com/skills/subagent-eval/}
}

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

Security scan

Grade A · scanned 2026-10-25 — 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/subagent-eval/#security)

Free. No spam. Unsubscribe in one click.

More Engineering skills

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

Browse all Engineering 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