Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)
Generates and validates Suricata 7.0 rules for detecting data exfiltration hidden in HTTP telemetry traffic, using sticky buffers, exact URI matching, header inspection, and PCRE body pattern matching.
Generates syzkaller syzlang descriptions for the Linux ppdev (parallel port) driver, covering all 28 ioctls (including 5 obsolete ones), structs, IEEE 1284 mode flags, and PP flags with architecture-specific constants for amd64 and 386.
Parse a Three.js createScene() file in headless Node.js, identify part-level structure (Groups and standalone Meshes), and export OBJ files for both individual sub-meshes per part and merged part assemblies (links). Use when extracting decomposed 3D object structure from Three.js scene definitions.
Generates a Node.js ES module script that dynamically imports a Three.js object definition file, constructs a scene graph, applies a -90 deg X-rotation for Y-up to Z-up coordinate conversion (Blender compatibility), forces world matrix updates, serializes the scene to Wavefront OBJ format using OBJExporter, and writes…
Convert Three.js scene graphs to Wavefront OBJ format suitable for Blender (Z-up coordinate system). Handles InstancedMesh, nested hierarchies, coordinate transforms, and headless Node.js execution.
Complete pipeline for identifying anomalous product category spending patterns in e-commerce data using Prophet counterfactual forecasting, and explaining anomalies through demographic factors via Difference-in-Differences causal inference.
Detects filler words in video/audio interviews using ASR (faster-whisper) with word-level timestamps, saves annotations as JSON, and extracts filler clips into a compilation video.
A comprehensive skill for extracting chapter indices from tutorial videos using FFmpeg audio extraction, OpenAI Whisper ASR transcription with word-level timestamps, and semantic chapter alignment via fuzzy string matching.
Handles plan output formatting and end-to-end task orchestration. Reads problem.json, calls the solver for each task, formats plans in actionname(param1, param2, ...) syntax, and writes output files.
Core PDDL planning solver that parses domain/problem files, invokes pyperplan with optimal search configuration (GBFS + hFF), handles timeouts and fallbacks, and returns a plan as a list of action strings.
Solves PDDL airport ground traffic control planning problems from the IPC Airport domain. Uses unified-planning with pyperplan backend (GBFS + hFF for agile solving), with direct pyperplan fallback, robust timeout/memout handling, and correct plan output formatting.
Load existing workbooks with openpyxl, validate required sheets and ranges, write Excel formulas into existing cells, save safely, and trigger headless recalculation while preserving formatting.
Provides utility functions for loading, scanning, and saving Excel workbooks with openpyxl 3.1.5, including handling merged cells, detecting placeholder markers, and preserving formatting when writing numeric values back.
Recover missing values (marked as "???") in a multi-sheet NASA budget Excel workbook. Handles 4 interdependent sheets with cross-sheet constraint propagation, floating-point precision management, and robust Excel I/O via openpyxl.
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: