Skip to content
TakoAPI
Back to skills

hle-benchmark-evolver

by wanng-ide

Browser & Automation
434Downloads reported by clawskills.sh
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Runs HLE-oriented benchmark reward ingestion and curriculum generation for capability-evolver.

Description

What This Skill Does

Ingests question-level HLE benchmark results into the capability-evolver reward system and generates curriculum signals for evolution cycles. Converts per-question accuracy data into prioritized queues that focus subsequent training on easier questions first.

Closes the loop between benchmark evaluation and capability evolution by automating reward ingestion, curriculum prioritization, and solidification in a single pipeline command.

When to Use It

  • Processing an HLE report JSON into reward and curriculum signals
  • Running a multi-cycle evolution pipeline with automatic re-evaluation
  • Checking current benchmark accuracy and curriculum stage snapshot
  • Targeting a specific HLE score threshold using easy-first question queues
  • Identifying which subjects and modalities to focus on next

Example Workflow

INPUT

User asks: ingest my HLE report and generate curriculum signals

AGENT
  1. 1

    Validate the report JSON exists at the provided path

  2. 2

    Ingest report into capability-evolver benchmark reward state

  3. 3

    Generate curriculum signals: benchmark_*, curriculum_stage:*, focus_subject:*, question_focus:*

  4. 4

    Print compact result summary as JSON

OUTPUT

JSON with benchmark_id, accuracy, reward, trend, curriculum_stage, queue_size, focus_subjects, and next_questions

Installation

clawhub install wanng-ide/hle-benchmark-evolver

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links