
SkillsBench evaluates how well skills work and how effective agents are at using them
@benchflow-ai/skillsbench
Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.
@benchflow-ai/skillsbench
Read and process GLM output files. Use when you need to extract temperature data from NetCDF output, convert depth coordinates, or calculate RMSE against observations.
@benchflow-ai/skillsbench
An overview of the core data API of ObsPy, a Python framework for processing seismological data. It is useful for parsing common seismological file formats, or manipulating custom data into standard objects for downstream use cases such as ObsPy's signal processing routines or SeisBench's modeling API.
@benchflow-ai/skillsbench
VERIFY your changes work. Measure CLS, detect theme flicker, test visual stability, check performance. Use BEFORE and AFTER making changes to confirm fixes. Includes ready-to-run scripts: measure-cls.ts, detect-flicker.ts
@benchflow-ai/skillsbench
Migrate Java EE javax.* imports to Jakarta EE jakarta.* namespace. Use when upgrading to Spring Boot 3.x, migrating javax.persistence, javax.validation, javax.servlet imports, or fixing compilation errors after Jakarta EE transition. Covers package mappings, batch sed commands, and verification steps.
@benchflow-ai/skillsbench
Cluster audio segments by speaker identity for diarization.
@benchflow-ai/skillsbench
Vercel's comprehensive UI guidelines for building accessible, performant web interfaces. Use this skill when reviewing or building UI components for compliance with best practices around accessibility, performance, animations, and visual stability.
@benchflow-ai/skillsbench
Basic usage of the General Lake Model (GLM) for lake temperature simulation. Use when you need to run GLM, understand input files, or modify configuration parameters.
@benchflow-ai/skillsbench
Performs initial binary triage by surveying memory layout, strings, imports/exports, and functions to quickly understand what a binary does and identify suspicious behavior. Use when first examining a binary, when user asks to triage/survey/analyze a program, or wants an overview before deeper reverse engineering.
@benchflow-ai/skillsbench
Prevent Cross-Site Scripting (XSS) attacks through input sanitization, output encoding, and Content Security Policy. Use when handling user-generated content in web applications.
@benchflow-ai/skillsbench
Fast workflow to inspect PCAPs and extract protocol-level details using tshark
@benchflow-ai/skillsbench
Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.
@benchflow-ai/skillsbench
This skill provides semantic search capabilities using embedding-based similarity matching for code and text. Enables meaning-based search beyond keyword matching, with optional document parsing (PDF, DOCX, PPTX) support.
@benchflow-ai/skillsbench
Count occurrences of an object in the image using computer vision algorithm.
@benchflow-ai/skillsbench
Analyze images and multi-frame sequences using OpenAI GPT vision models
@benchflow-ai/skillsbench
This skill should be used when debugging memory-related issues in the Breenix kernel including page faults, double faults, frame allocation problems, page table issues, heap allocation failures, stack overflows, and virtual memory mapping errors.
@benchflow-ai/skillsbench
Download YouTube video transcripts when user provides a YouTube URL or asks to download/get/fetch a transcript from YouTube. Also use when user wants to transcribe or get captions/subtitles from a YouTube video.
@benchflow-ai/skillsbench
Guidance for analyzing network packet captures (PCAP files) and computing network statistics using Python, with tested utility functions.
@benchflow-ai/skillsbench
Design in pseudocode first, iterate approaches, then translate to code
@benchflow-ai/skillsbench
Harbor framework for agent evaluation. Use when: (1) Running harbor commands (harbor run, harbor tasks check), (2) Creating/validating SkillsBench tasks, (3) Understanding task format or debugging failures.
@benchflow-ai/skillsbench
Finds and recovers content from Claude Code session history files. This skill should be used when searching for deleted files, tracking changes across sessions, analyzing conversation history, or recovering code from previous Claude interactions. Triggers include mentions of "session history", "recover deleted", "find in history", "previous conversation", or ".claude/projects".
@benchflow-ai/skillsbench
Analyzes 3D mesh files (STL) to calculate geometric properties (volume, components) and extract attribute data. Use this skill to process noisy 3D scan data and filter debris.
@benchflow-ai/skillsbench
This skill should be used when the user asks to "pentest SSH services", "enumerate SSH configurations", "brute force SSH credentials", "exploit SSH vulnerabilities", "perform SSH tunneling", or "audit SSH security". It provides comprehensive SSH penetration testing methodologies and techniques.
@benchflow-ai/skillsbench
Extract text content from images using Tesseract OCR via Python
@benchflow-ai/skillsbench
Manage Google Calendar - search, create, update events and answer calendar questions. Use when user wants to interact with their Google Calendar for scheduling and calendar operations.
@benchflow-ai/skillsbench
Guidance for configuring Nginx web servers with custom logging, rate limiting, and static content serving. This skill should be used when tasks involve setting up Nginx server blocks, configuring custom log formats, implementing rate limiting, or serving static files on specific ports.
@benchflow-ai/skillsbench
Guidance for creating Python packages and serving them via a local PyPI server. This skill applies when tasks involve building Python packages (with pyproject.toml or setup.py), setting up local package repositories, or serving packages via HTTP for pip installation. Use when the goal is to create installable Python packages and make them available through a local index URL.
@benchflow-ai/skillsbench
Estimate driving/taxi duration, distance, and rough cost between two cities using the bundled distance matrix CSV. Use this skill when comparing ground travel options or validating itinerary legs.