Skip to main content
skill CX Codex

ae-evaluation — Claude Code skill: agent evaluation and setup

The ae-evaluation Claude Code skill manages Agent Evaluation tasks through ae-cli. It configures and runs agent or preset-output evaluations, then helps inspect their results.

no license 126 installs ★ 23 updated 2026-10-22

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add ThinkingAIAgenticEngine/ae-cli --skill ae-evaluation -a claude-code
Open on GitHub

What ae-evaluation does

The skill manages evaluation datasets and assets on Agent Evaluation. It configures models, credentials and integrations, starts evaluation runs, and analyzes their results. It also handles recurring schedules and resource access.

Remote evaluation requires the online platform and an AE_EVAL_ACCESS_TOKEN. In an AE sandbox, the CLI obtains a short-lived session automatically; set AE_EVAL_TE_PROJECT_ID when the sandbox token can reach multiple TE projects. Outside a sandbox, a missing token means no network request is sent. Commands use the current Agent Evaluation host by default; select another with --host.

What it helps with

  • create and publish an evaluation dataset
  • configure a model and an agent under test
  • run an evaluation and inspect its results
  • schedule recurring evaluation runs

Example prompts for the agent

  • Create an evaluation dataset from this CSV file.
  • Configure the agent and run an evaluation against the selected dataset.
  • Show the results and traces from the latest run.

How to install ae-evaluation

1Skills CLI (Vercel)

npx skills add ThinkingAIAgenticEngine/ae-cli --skill ae-evaluation -a claude-code

2Manually: put the files in place

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

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

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

Questions about ae-evaluation

How do I install ae-evaluation in Claude Code?

Run npx skills add ThinkingAIAgenticEngine/ae-cli --skill ae-evaluation -a claude-code. The skill file is at ~/.claude/skills/ae-evaluation/SKILL.md.

What does ae-evaluation do?

It manages Agent Evaluation assets, configures and runs evaluations for agents or preset outputs, and helps analyze run results.

What does ae-evaluation need to run?

It requires access to the online Agent Evaluation platform and an AE_EVAL_ACCESS_TOKEN. In an AE sandbox, the CLI obtains a session token automatically; use AE_EVAL_TE_PROJECT_ID to select a TE project when the token can access several.

Similar skills

All skills for Testing and QA →

From the same set25

The whole set →
ae-use-agent ae-use-agent — a skill for Claude Code, Codex, Cursor and other platforms: loads instructions and dependencies of a custom te-agent agent and runs the task on the client's local model. CX Codex +1 468installs ae-current-context ae-current-context reads active AE/TE product page context directly into an agent run. Useful when referencing selected items, active filters, or UI adjustments. CX Codex +1 402installs ae-migrate-tracking-code ae-migrate-tracking-code moves existing Firebase, Amplitude, Mixpanel, Sensors Data, or GA4 tracking calls to the AE SDK. Choose a full switch or keep the old SDK and send events to both. CX Codex +1 401installs ae-automation The ae-automation Claude Code skill creates scheduled automations on the AE platform. It responds to requests for recurring tasks, reports, reminders, or monitoring. CX Codex +1 166installs ae-things The ae-things Claude Code skill manages Things in a clearly selected AgentSpace. It activates around assignments, deliverables, milestones, and next steps. CX Codex +1 166installs ae-workspace The ae-workspace Claude Code skill manages AgentSpaces through ae-cli. Requests to change members, capabilities, or files activate it. CX Codex +1 165installs ae-things-progress The ae-things-progress Claude Code skill gathers Thing activity and drafts daily or weekly reports. Request a summary for a workspace, an assignee, or selected Things. CX Codex +1 165installs ae-things-review The ae-things-review Claude Code skill reviews workspace tasks for scope changes, missing progress records, ownership and completion evidence. Run it against a space, an assignee or selected tasks. CX Codex +1 165installs

Project sponsors

Companies that keep this analytics open