Run behavioral benchmarks against the agent, detect failure patterns, generate guidance patches, apply them with auto-revert safety net. Implements the closed-loop self-improvement cycle from Hermes PR.
πͺ½ Write code, see it live, instantly. Claude-style artifacts with persistent history, live reload, inline editor, screenshots, and 'Save as New'. v4.3 β one-line install! π₯.
Multi-lens research engine β one question, 9 angles, synthesized analysis. Uses /research-skill-graph/ as the knowledge base. Load this skill when given a research question and use it to produce deep, structured analysis. Invoke by saying "do deep research on [question]".
GitHub Copilot CLI plugin β 23 Hermes development skills wired into gh copilot. Use /skill or gh copilot -- -i 'use ' to invoke any skill. Covers code review, TDD, debugging, GitHub workflows, AI agents, MLOps, and MCP.