Skip to content
NarraNexus
All teams
educationteam

Gaokao Grading Team

by NarraNexus team Β· MIT

Local Build assumes a NarraNexus instance running at localhost:5173 β€” start it first with bash run.sh.

Desktop App requires the NarraNexus DMG installed to /Applications/ (and opened at least once so macOS registers the narranexus:// handler).

Gaokao Grading Team is a 5-agent team for reviewing Gaokao-style exam performance. A candidate agent works with subject-specific graders for Chinese, Math, and English, then a comprehensive evaluator synthesizes the subject feedback into an overall assessment. The template includes dedicated answer-reference skills for 2026 Chinese Paper 1, Math Paper 1, and English Paper 1, allowing each subject grader to evaluate against the bundled material rather than acting as a generic tutor. Use it as a structured demo of multi-agent grading, subject-specialist review, and final report synthesis.

How to use it

Start with the θ€ƒη”Ÿ agent to submit or discuss answers. The subject graders handle their own domains, and η»Όεˆθ―„δΌ° is the final synthesis point. Suggested flow: - Ask θ€ƒη”Ÿ to provide the exam response or start a review session - Let θ―­ζ–‡ι˜…ε·, ζ•°ε­¦ι˜…ε·, and θ‹±θ―­ι˜…ε· evaluate their subject areas - Ask η»Όεˆθ―„δΌ° for the final cross-subject summary, strengths, weaknesses, and improvement priorities Expect: subject-level grading feedback followed by an integrated assessment. Configure your LLM providers in Settings β†’ Providers before running the team.

Agents in this team

  • ζ•°ε­¦ι˜…ε·
  • θ‹±θ―­ι˜…ε·
  • θ―­ζ–‡ι˜…ε·
  • η»Όεˆθ―„δΌ°
  • θ€ƒη”Ÿ

How to install (manual)

  1. Click Download .nxbundle above.
  2. Open your NarraNexus app and go to Settings β†’ Import bundle.
  3. Drag the downloaded file in, review the preflight, confirm.

One-click install (a deep link that imports directly into your cloud or desktop NarraNexus) is the next milestone.