Agent Skills Hub

design-references

Provides predefined design system references for UI reviews, including Material Design 3, Apple HIG, Tailwind UI, Ant Design, and Shadcn/ui.

data-cleaning-pipeline-generator

Generates data cleaning pipelines for pandas/polars/PySpark, handling missing values, duplicates, outliers, type conversions, and validation.

variant-analysis

Find similar vulnerabilities and bugs across codebases using pattern-based analysis. Use when hunting bug variants, building CodeQL/Semgrep queries, or performing systematic code audits.

flaky-detect

Identify, categorize, and troubleshoot flaky tests by analyzing CI history, execution patterns, and code structure to improve test suite reliability.

security-audit

Automated security validation, RLS enforcement, OWASP compliance, and vulnerability scanning for AI-assisted development workflows.

skill-vetter

Security-first vetting protocol for AI agent skills. Detects red flags like credential theft, obfuscated code, and unauthorized data exfiltration before installation.

doncheli-visual-test

Perform automated visual regression testing by comparing UI screenshots against established baselines to identify layout shifts, color changes, and rendering regressions.

retro

Weekly engineering retrospective tool that analyzes commit history, coding patterns, and quality metrics with automated session detection and trend tracking.

kreuzberg

High-performance document intelligence library for extracting text, tables, code, and metadata from 91+ file formats, with OCR and LLM-ready output.

novelty-check

Verify research idea novelty against recent literature. Use when user says '查新', 'novelty check', or needs to confirm if a method is original.

box-least-squares

BLS periodogram tool for detecting transiting exoplanets and eclipsing binaries in photometric light curves. An astropy-based implementation for period, duration, and depth analysis.

light-curve-preprocessing

Preprocessing and cleaning astronomical light curves using Lightkurve. Tools for outlier removal, flattening, trend detrending, and quality flag handling for time-series analysis.