Phoenixrr2113/agent-harness
A file-first agent operating system. Build AI agents by editing markdown files, not writing code. Self-managing, self-improving, durable. Agent Skills compatible.
A file-first agent operating system. Build AI agents by editing markdown files, not writing code. Self-managing, self-improving, durable. Agent Skills compatible.
npx add-skill Phoenixrr2113/agent-harnessA file-first agent operating system. Build AI agents by editing markdown files, not writing code. Self-managing, self-improving, durable. Agent Skills compatible.
Read-only closeout triage for worktrees and branches across sessions, with artifact summaries and follow-up prompts.
Best static AI text humanizer. Two research-grounded skills that work in any LLM (Claude, ChatGPT, Gemini, Codex): humanize beats perplexity-based detectors, ai-check produces forensic scoring with evidence-quoted flags. Nine levers, 50+ peer-reviewed sources, 2024-2026 detection literature.
Manage multiple Gmail accounts with an MCP server for AI agents to read, search, label, archive, and unsubscribe from email
An automated AI research-paper writer based off Google's PaperOrchestra paper's implementation through a skills - benchmark + autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider). No API keys, no LLM SDKs.
Prepare open-source repositories for launch by verifying key documentation, usability, and trust signals to improve user adoption.
Personal skill library for the OpenClaw browser-automation assistant — content publishing + workflow trigger skills, powered by Claude Max.