sv-report

Community

Generate SV-Bench metrics reports

Authorintertwine
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill automates the generation and validation of performance metrics reports for evaluation runs within the SV-Bench framework, ensuring data integrity and comparability.

Core Features & Use Cases

  • Per-run Reporting: Generates summary.json and report.md for individual evaluation runs.
  • Batch Reporting: Processes multiple evaluation runs simultaneously for efficiency.
  • Report Validation: Enforces strict adherence to defined metrics contracts.
  • Use Case: After running multiple agent evaluations on the network-logs environment, use this Skill to consolidate the results into a single, human-readable report for analysis and presentation.

Quick Start

Generate a strict report for the E1 run located in outputs/evals/sv-env-network-logs--gpt-5-mini/your_run_id.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 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: sv-report
Download link: https://github.com/intertwine/security-verifiers/archive/main.zip#sv-report

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.