Is the Inngest Agent Evals skill free?

Yes. The skill itself is free from inngest/inngest-skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Inngest Agent Evals SkillProof Score?

9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.

How do I install Inngest Agent Evals?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Inngest Agent Evals with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Inngest Agent Evals

Wire production Inngest agent evals: direct/deferred scoring, sessions, and A/B experiments.

by inngest · inngest/inngest-skills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.6/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 9b353a0

Typechecked the skill's exact code pattern against the real, currently-published inngest@4.12.1 package on npm — scoreMiddleware, createScorer, group.experiment, and experimentRef all compiled clean — while a from-memory baseline reinvented a non-durable, unattributed scoring system that POSTs to a made-up metrics endpoint and coin-flips its 'experiment' with Math.random().

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 5/5

What Inngest Agent Evals does

Adds Inngest's v4 evaluation primitives — step.score, deferred createScorer scorers, meta.sessions correlation, and group.experiment A/B comparisons — to a production AI agent or workflow built on Inngest. Triggers when the user wants to score, evaluate, debug, or A/B test agent/workflow outcomes, or migrate an existing Inngest app to add production evals.

How to install Inngest Agent Evals

git clone https://github.com/inngest/inngest-skills
cd inngest-skills
mkdir -p ~/.claude/skills
cp -r skills/inngest-agent-evals ~/.claude/skills/inngest-agent-evals

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Inngest Agent Evals

/inngest-agent-evals Wire production Inngest agent evals: direct/deferred scoring, sessions, and A/B experiments.

It also activates on plain-language prompts like these:

Add quality scoring to my Inngest support-ticket agent function
I need an A/B test comparing two prompt strategies in Inngest
Wire up deferred eval scoring from user feedback in Inngest

Frequently asked questions

Is the Inngest Agent Evals skill free?: Yes. The skill itself is free from inngest/inngest-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Inngest Agent Evals work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Typechecked the skill's exact code pattern against the real, currently-published inngest@4.12.1 package on npm — scoreMiddleware, createScorer, group.experiment, and experimentRef all compiled clean — while a from-memory baseline reinvented a non-durable, unattributed scoring system that POSTs to a made-up metrics endpoint and coin-flips its 'experiment' with Math.random().
What is the Inngest Agent Evals SkillProof Score?: 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install Inngest Agent Evals?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Inngest Agent Evals with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.