Custom Engine e2e fixture

SkillAI & models

custom-engine is a skill in the ai-models category that lets your AI evaluate and evolve Agent Skills. Once added, your AI can measure how a skill performs and refine it over time. The source is available at github.com/alibaba/skill-up.

Available today. Use it from your connected AI after setup.

Add the skill, then ask your AI to evaluate a skill you already have and refine it based on the results.

Then ask your AI: use the Custom Engine e2e fixture skill

What your AI can do with it

  • Evaluate how an Agent Skill performs
  • Improve an Agent Skill through repeated refinement
  • Test whether a change actually made a skill better

What this skill tells your AI

The instructions your AI receives, as published by alibaba/skill-up in e2e/testdata/custom-engine/SKILL.md and read by ahel’s review.

This directory is a minimal skill-up fixture that exercises the Custom Engine local and http transports end-to-end. It is consumed by e2e/custom_engine_test.go.

agent.sh + evals/eval.yaml cover the local transport: agent.sh is a deterministic stand-in for a real custom agent that reads the SessionInput JSON the framework writes to ${input_file} and emits a fixed SessionResult on stdout. The case asserts that final_message flows from the agent's stdout into the report.

evals/eval-http.yaml exercises the http transport against the same hello.yaml case. TestPipeline_CustomEngine_HTTPTransport starts an in-process httptest server, points ${CUSTOM_AGENT_ENDPOINT} at it, and asserts the posted SessionInput reaches the server and the returned SessionResult flows into the report — so the http stand-in agent lives in the test rather than in agent.sh.

Signals

GitHub stars
892
Forks
68
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
custom-engine
Source
github.com/alibaba/skill-up