Skip to main content
affpapa.org
RU EN
skill

agent-evaluation · davila7 — Claude Code skill: agent testing and installation

Evaluate an agent’s behavior, capabilities, and consistency across runs. Use the skill when you need to test an agent beyond a single benchmark result.

Install into Claude Code · claude-code-templates All methods and platforms ↓ 
npx claude-code-templates@latest --skill ai-research/agent-evaluation
Open on GitHub

What agent-evaluation does

This skill outlines ways to assess LLM agents through behavioral checks, capability assessments, reliability measures, and regression tests. Repeating tests and examining how results vary can reveal issues that a single successful run would miss. A strong benchmark result can still fail to reflect performance on practical tasks.

The approaches include checking behavioral invariants and actively probing for failure cases. The skill also covers flaky tests, metric gaming, and test data leaking into training or prompts. Testing fundamentals and knowledge of LLMs are prerequisites; without them, choosing suitable checks and interpreting results will be difficult.

What it helps with

  • check whether an agent follows behavioral requirements across runs
  • assess an agent’s capabilities on different tasks
  • detect inconsistent results between test runs
  • find cases where an agent optimizes for a metric instead of the task
  • review tests for data leakage into training or prompts

Example prompts for the agent

  • Check whether the agent follows its behavioral requirements across repeated runs.
  • Draft an evaluation plan for the agent’s capabilities on different tasks.
  • Review the agent tests for unstable results, metric gaming, and data leakage.

How to install agent-evaluation

1claude-code-templates

npx claude-code-templates@latest --skill ai-research/agent-evaluation

2Skills CLI (Vercel)

npx skills add davila7/claude-code-templates --skill agent-evaluation -a claude-code

3Manually: put the files in place

~/.claude/skills/agent-evaluation/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/agent-evaluation/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about agent-evaluation

How do I install agent-evaluation in Claude Code?

Run npx claude-code-templates@latest --skill ai-research/agent-evaluation.

What does agent-evaluation do?

It outlines methods for testing LLM agents, including behavioral checks, capability assessment, reliability measures, and regression testing.

What should I know before using agent-evaluation?

You need testing fundamentals and an understanding of LLMs.

Similar skills

All skills for Testing and QA →

agent-evaluation by other authors comes first.

agent-evaluation sickn33 A skill for comparing agent, prompt or tool changes against versioned cases with explicit verifiers. Useful for reproducing a failure or running a regression pass. CX Codex +1 971installs agent-evaluation NeoLabHQ Framework for testing agents, prompts, and skills using multi-dimensional scoring rubrics and LLM-as-judge prompts. CX Codex +1 1,300installs agent-evaluation mlflow A skill that runs systematic LLM agent evaluation through MLflow: datasets, scorers, tracing. Useful when an agent picks the wrong tool or returns incomplete answers. CX Codex +1 1,100installs improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. 1,163,035installs design-taste-frontend Leonxlnx This skill directs the design of public pages and work screens, then checks the result in a browser through screenshots. Use it when an interface feels generic or unfinished. CX Codex +1 678,700installs tdd Matt Pocock Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details. 1,141,062installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. 414,180installs agent-browser vercel-labs A CLI skill for browser control: it opens pages, fills forms, clicks buttons, and tests web apps. Use it when an agent needs to act inside a website. CX Codex +1 1,200,000installs prototype Matt Pocock Creates throwaway prototypes for checking state logic or exploring UI before committing the decision to the main codebase. 986,201installs

From the same set495

The whole set →
data-scientist A Claude Code skill for statistical analysis, machine learning, and data exploration. Use it when a task needs model selection, forecasting, or evidence-based analysis. 385installs scientific-visualization Build publication-ready scientific figures with multi-panel layouts, error bars, accessible colors, and exports for journal workflows. 384installs nextjs-middleware-creator Generates modular Next.js middleware and helper scripts for routing. It sets up JWT authentication, rate limiting, and security headers. 381installs invoice-organizer Sorts invoices, receipts and bank statements into folders, renames every file to one pattern and writes a CSV your accountant can use. 380installs interactive-documentation A slash command that builds documentation with runnable code examples, playgrounds and API testing. Useful once a plain README stops being enough. 372installs agents-crewai A Claude skill for assembling teams of autonomous agents with roles, memory, and sequential or hierarchical task execution. 371installs add-performance-monitoring Sets up application performance monitoring, alerting rules, and observability metrics. Useful when preparing an application for production workloads. 369installs report Generate task, sprint, and performance reports with /task-report. Use it for a standup, project review, or a closer look at blockers and dependencies. 368installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor