classify-capability

Classify robotics research papers into frontier capability tiers with structured JSON output.

Updated Aug 23, 2026

Search Tags:#robotics #capability #classify #paper-analysis #research-evaluation #frontier-mapping

Ready to run

npx skills add https://github.com/ZhangHanbo/alpha_research --skill classify-capability

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: classify-capability
Source: https://github.com/ZhangHanbo/alpha_research/tree/main/skills/classify-capability
Command: npx skills add https://github.com/ZhangHanbo/alpha_research --skill classify-capability

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Assigns a concise, evidence-backed capability tier to a single research paper to help frontier-mapping pipelines aggregate and compare demonstrated robotics capabilities consistently.

Core Features & Use Cases

Heuristic Triage: Applies ordered checks on real-world vs. simulation evaluation, success rates, diversity of objects/environments, independent reproduction, and guideline overlap to determine tier.
Structured Output: Produces a JSON-style classification containing tier, capability_description, evidence list, rationale, confidence, and boundary notes for downstream aggregation.
Use Case: Called in a loop by a frontier-mapping pipeline to classify many papers rapidly and conservatively for research prioritization and survey synthesis.

Quick Start

Classify the paper arxiv:2501.12345 using its task_chain and reported_results and return tier, capability_description, evidence, rationale, and confidence.

Frequently Asked Questions about classify-capability

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I classify robotics research papers by demonstrated capability for frontier mapping?▼

To classify robotics research papers by demonstrated capability, you can apply heuristic checks to single-paper inputs containing task chains and reported results, assigning each paper to a reliable, sometimes, or can't-yet tier for frontier mapping pipelines.

What criteria determine if a robotics capability is reliable or can't-yet?▼

Criteria for reliable versus can't-yet robotics capability tiers include evaluation realism, diversity of objects and environments, success-rate thresholds with confidence intervals, independent reproduction status, and guideline overlap assessed from the paper's reported results.

How do I evaluate evaluation realism and success rates from a robotics paper?▼

Evaluating evaluation realism and success rates involves applying ordered heuristic checks on reported_results data, specifically analyzing real_robot versus simulation environments, success rates, n_objects_tested, and perturbation_tested fields to determine capability confidence.

Can I process multiple robotics papers in a loop to aggregate demonstrated capabilities?▼

Yes, you can process multiple robotics papers in a loop to aggregate demonstrated capabilities, as this classification function is designed to be called repeatedly by frontier-mapping pipelines to rapidly and conservatively triage many papers for research prioritization.

What structured output format does the paper capability classification produce?▼

The paper capability classification produces a structured JSON output containing the assigned tier, capability_description, evidence list, rationale, confidence score, and boundary_notes to enable consistent downstream aggregation and survey synthesis.

What input fields are required to classify a research paper's capability tier?▼

Required input fields to classify a research paper's capability tier include task_chain, reported_results with success rate and n_objects_tested, environments, real_robot status, perturbation_tested, ablation_strong, venue, year, and domain.