
harrey401 skills on Remote OpenClaw
7 skills published by harrey401. Each listing includes a one-command install for Claude Code, OpenClaw, Codex, and Hermes, plus a link to the upstream source.
lofy-career
Manages job searches end-to-end using a local JSON file to track applications. Tailors resume bullets to job descriptions by comparing requirements against a user career profile, generates interview prep from live web research, and drafts follow-up emails based on application timeline rules.
lofy-fitness
Fitness accountability layer for the Lofy AI assistant. Logs workouts and meals from natural language, detects personal records using the Epley formula, and generates weekly progress summaries. Tracks consistency through conversation without requiring a separate app.
lofy-life-coach
Personal accountability layer for the Lofy AI assistant. Tracks fitness, career, and daily habits with streak counting, and delivers scheduled morning briefings and evening reviews. Parses conversational updates to keep a local goals.json file current.
lofy-home
Controls smart home devices through a Home Assistant instance using natural language commands. Supports preset scene modes for different activities, individual device control for lights, music, and thermostat, and wake-on-LAN for PCs. Device mappings and scenes are defined in a local config file.
lofy
A modular life management system that runs as a single AI agent inside OpenClaw. Handles morning briefings, evening reviews, fitness logging, job application tracking, project management, and smart home control. Uses a five-layer memory architecture to persist context across sessions.
lofy-projects
Manages projects and coursework inside the Lofy AI assistant using a local JSON data file. A weighted priority formula scores each project on urgency, job relevance, momentum, and energy level to recommend what to work on next. Also automates meeting prep, tracks time logs, and flags projects that have gone stale.
brain-cms
Replaces flat MEMORY.md files with a multi-layer memory architecture for OpenClaw agents. Uses a hippocampal router, LanceDB vector store, and automated NREM/REM sleep cycles to load only relevant context per session. Modeled on neuroscience concepts like long-term potentiation and spreading activation.