Mechaharness is an agentic harness for raw LLM inference. It wraps local or remote model calls with context engineering, tool use, rules, skills, AGENTS.md instructions, and agentic execution loops, turning a model endpoint into a capable, extensible agent runtime.
mechaharness is a Antigravity agent skill that mechaharness is an agentic harness for raw LLM inference. It wraps local or remote model calls with context engineering, tool use, rules, skills, AGENTS.md instructions, and agentic execution loops, turning a model endpoint into a capable, extensible agent runtime.
npx skills add rl337/mechaharnessMechaharness is an agentic harness for raw LLM inference. It wraps local or remote model calls with context engineering, tool use, rules, skills, AGENTS.md instructions, and agentic execution loops, turning a model endpoint into a capable, extensible agent runtime.
Extract frames or short clips from videos using ffmpeg.
Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.
Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.
Obra superpowers agent skills.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work
Use when you have a spec or requirements for a multi-step task, before touching code