Skill UI

This skill enables AI agents to search, import, and analyze video content using Memories.ai's Large Visual Memory Model. It provides persistent video intelligence, allowing videos to be indexed once and queried repeatedly. Supports social media import from TikTok, YouTube, and Instagram, meeting summarization, knowledge base building, and cross-video Q&A via Memory Augmented Generation. Ideal for analyzing video URLs, researching social media trends, and summarizing recordings.

Tree Ring Memory is a local-first framework for managing AI agent memory lifecycles. It enables recall, evidence recording, auditing, and forgetting without dumping transcripts. Built with Rust and SQLite, it supports scoped memory, privacy, and durable project knowledge consolidation. Ideal for developers managing AI agent projects securely.

This skill humanizes natural-language memory files like CLAUDE.md, AGENTS.md, and docs by removing AI-isms and adding burstiness. It offers deterministic and LLM modes, preserves code blocks, URLs, paths, and headings, and creates backups. Ideal for cleaning up AI-generated content in configuration files and documentation.

This skill captures and persists critical user decisions, project constraints, and architectural choices across multiple sessions and agents. It saves this context into a structured memory database (`mdbase`), ensuring that future development steps or agents can retrieve the original intent without re-deriving it from scratch. Ideal for documenting project rules, tech stacks, and design rationale.

LWC is a durable memory system for coding agents that preserves project decisions, code structure, and verified context across sessions. It utilizes a physical Wiki document graph and a CodeGraph index to enable source-grounded recall. This tool helps agents search, update, and maintain knowledge without losing critical information during future coding-agent interactions.

Detects data exfiltration via URL path encoding and chained web_fetch navigation, covering fake trusted UI injection, indirect prompt injection, letter-level path exfiltration, and multi-hop navigation hijacking in agent memory/context scenarios.

Security hardening guidance for AI agent frameworks processing untrusted content, invoking tools, writing files, managing identifiers, or handling credentials. Use when building or reviewing agent runtimes, autonomous workers, tool gateways, memory services, or multi-tenant deployments.

A public-safe preliminary screen for challenges to the impartiality of an AI evaluator, LLM-as-a-judge, or decision-support agent based on prior outputs, suspected bias, unstable reasoning, or self-reinforcing memory. Classifies evidence and recommends proportionate remedies.

Answer questions about a past agent run from its recorded transcript instead of memory. Find sessions, build a step timeline with recorded vs inferred causality, and verify summaries with typed claim checks.