orch-subject-evaluation
CommunityOrchestrates end-to-end subject evaluation.
AuthorAKCqhzdy
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Top-level Subject Evaluation Orchestrator coordinates evaluation workflows across leaves, enabling automated metrics, quality audits, and reporting for grading outputs in a subject-agnostic way.
Core Features & Use Cases
- Orchestrates evaluation leaves including eval-metrics, eval-grading-quality-audit, and eval-report to produce end-to-end evaluation results.
- Handles scope determined by START.md (subject, grading_year, groundtruth) and enforces the release and reuse of ground-truth levels with rank-based metrics.
- Provides deterministic re-run behavior with logging and phase-by-phase dispatch similar to the grading orchestrator.
Quick Start
Populate START.md with scope and phase selections, export the SCOPE_SUBJECT, SCOPE_GRADING_YEAR, and SCOPE_GROUNDTRUTH variables, then run the orchestrator.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: orch-subject-evaluation Download link: https://github.com/AKCqhzdy/dse-subject-grading/archive/main.zip#orch-subject-evaluation Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.