Search

Single source of truth for AI coding agent configuration — skills, commands and rules shared across OpenCode and Pi.

A Claude skill that transforms documents, articles, brainstorms, and ideas into interactive mind maps — then connects them into a personal knowledge atlas. Contradiction detection, gap analysis, source attribution, 7 export formats, and adaptive layouts.

The ultimate cloud browser automation CLI purpose-built for AI agents.

Product Team Skills

Based on Anthropic's skill-creator — with bug fixes, working Cowork support, and official best practices baked in. Claude skill for creating, testing, and improving other Claude skills.

Blazing-fast WSL2 to Windows file search bridge for AI Agents via MCP

AI agent skills for startup founders — pitch decks, web conversion, and founder tooling by UniqueClub

Chinese expression compression skill for Codex-style agents

Cyber Threat Intelligence Skills for each stage of the CTI Lifecycle.

None

Semantic cache for LLM API calls — pay once, answer many paraphrases.

Dig Gmail emails and attachments into LLM-friendly markdown

Storage location movable for Tryton

Helper package for an ExteraGram Heroku Host Bridge plugin.

Advanced AI Shell Command Assistant

NXPU NeuroSymbolic Processing Unit SDK — AI that discovers rules from data, no LLM, no training

PQC-signed RAG pipeline chunks. Sign document chunks with ML-DSA at ingestion, verify at retrieval. Prevents vector database poisoning.

PQC-native per-tenant KV cache encryption for multi-tenant LLM inference. ML-KEM-768 derived session keys, AES-256-GCM per-entry encryption, automatic key rotation, tenant isolation enforcement.

PQC-native C2PA-compatible content provenance for AI-generated outputs. Sign every LLM/image/audio output with ML-DSA so its origin is verifiable for decades.

Python SDK for the TRON (Token Reduced Object Notation) format — compact, LLM-friendly JSON superset