Browsing:

najicham

validate-historical is a skill that audits historical data integrity across a date range, identifying gaps and providing specific remediation steps to resolve cascade effects.

aehrc

Tools that make it easier to use FHIR and clinical terminology within data analytics, built on Apache Spark.

huggingface

Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.

KengoTODA

Fast, CLI-first static analysis tool for JVM class and JAR files. Designed for coding agents.

axiomhq

Validates PR code against Architecture Decision Records (ADRs). Uses oracle for deep analysis of implementation compliance.

IsKenKenYa

ui-visual-validator is a skill for expert visual validation specialists, focused on verifying UI modifications, design system compliance, and accessibility implementation through rigorous analysis methodologies.

dudusoar

Code for sentiment analysis and topic modeling of public perceptions toward sidewalk delivery robots using YouTube comments (TRR 2025).

bierecode

build-check is a skill that automates the build process analysis by running a series of commands, including `cd bierecode && npm run build`, to identify and suggest fixes for errors.

yudame

Research tools and frameworks for evidence-based analysis across technology, health, economics, and human performance. Outputs include podcasts, reports, and educational materials.

EthanAlgoX

MarketBot is a finance-customized version of openclaw, built as a dedicated AI agent for market intelligence, trading analysis, and decision support.

Aniket-a14

AI-powered Software Requirements Analysis (SRA) system that evaluates requirement quality, detects ambiguities, and suggests structured improvements for more reliable and complete SRS documents.

qte77

A Multi-Agent System (MAS) evaluation framework using PydanticAI that generates and evaluates scientific paper reviews through a three-tiered assessment approach: traditional metrics, LLM-as-a-Judge, and graph-based complexity analysis.