cathrynlavery — 7 Open-Source AI Agent Skills
cathrynlavery is the author of 7 open-source AI agent skills and MCP servers spanning claude-skill, codex-skill, with a combined 43,553+ GitHub stars. On AgentSkillsHub each is quality-scored (avg 59/100) and security-graded where a README exists (5 of 7) — 5 verified safe.
Top skills by cathrynlavery
- diagram-design — Editorial diagram design for Claude Code, Codex, GitHub Copilot, Factory Droid, and Pi. 42 diagram types. Self-contained HTML + SVG. No shad (43.3k★ · quality 68/100 · security: safe)
- openclaw-ops — OpenClaw operations skill with health checks, repair scripts, watchdogs, update triage, and security scans. (224★ · quality 69/100 · security: safe)
- repo-atlas — A Claude Code skill that builds a persistent context system (atlas) for any git repository — directory trees, entrypoints, architecture docs (51★ · quality 63/100 · security: safe)
- voice-memo-organizer — Claude Code skill that organizes hundreds of Apple Voice Memos into a searchable archive with transcriptions, summaries, and key quotes. No (15★ · quality 65/100 · security: safe)
- problem-solver-skill — Claude Code skill for systematic problem diagnosis using progressive disclosure — 55-line router + 7 on-demand framework references (4★ · quality 40/100 · security: safe)
- proof-skill — Claude Code skill for working with Proof documents over HTTP (0★ · quality 45/100)
- agent-improvement-loop — Self-improvement for you and your AI agents: a safe daily loop that mines your Claude Code and Codex sessions and stages setup improvements (0★ · quality 60/100)
View cathrynlavery on GitHub · Explore audited agent skills