Merge product category taxonomies from multiple e-commerce platforms (Amazon, Facebook, Google Shopping) into a unified 5-level hierarchy. Use when you need to unify category systems across platforms with text normalization, embedding-based clustering, and constraint-validated naming.
Convert Three.js scene definitions to OBJ format for Blender import. Handles regular Mesh, InstancedMesh, nested transforms with non-uniform/mirrored scales, and coordinate system conversion (Y-up to Z-up via -90 degree X rotation). Use when converting Three.js code to simulation-ready 3D assets.
Build database-grounded travel itineraries from structured CSV data. Provides search functions and an end-to-end builder that assembles a multi-day itinerary satisfying caller-supplied constraints like budget, accommodation policies, cuisine preferences, and transport mode restrictions.
Reusable pipeline for detecting anomalous product category sales patterns in e-commerce transaction data and identifying demographic drivers via Difference-in-Differences causal analysis. Handles data cleaning, counterfactual forecasting, feature engineering, and DiD estimation.
Detect filler words in interview videos using Whisper ASR with word-level timestamps, classify disfluencies, save annotations as JSON, and extract/stitch filler clips into an output video. Use when a task requires finding hesitation markers (um, uh, like, you know, etc.) in video/audio and producing both timestamp…
Remove silence and non-teaching content from teaching videos. Detects openings and pauses using data-driven audio energy and visual frame-difference analysis. Produces a compressed video and JSON compression report.
Indexes tutorial videos by extracting audio, transcribing with Whisper, and aligning chapter titles to timestamps. Use for any task requiring video chapter timestamp extraction.
Solve PDDL airport ground-traffic planning tasks from IPC problem suites. Use when given PDDL domain and problem files for airport domains with aircraft taxiing, parking, pushback, and takeoff. Reads problem.json, solves each task with pyperplan, and writes plans in standard PDDL format.
Skill for populating Excel workbooks with INDEX/MATCH lookup formulas, net export percentage calculations, descriptive statistics, and GDP-weighted mean using SUMPRODUCT. Use when a task requires filling in economic data from a source sheet using two-key lookups and computing trade statistics.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: