Kokoabassplayer/visual-evidence-skills
Reusable Codex skills for screenshot-based visual evidence and GitHub evidence comments
Reusable Codex skills for screenshot-based visual evidence and GitHub evidence comments
npx skills add Kokoabassplayer/visual-evidence-skillsReusable Codex skills for screenshot-based visual evidence and GitHub evidence comments
Up to 99% token savings on AI agent context. Free. Provider-agnostic (Claude, Cursor, Codex, Cline, any MCP agent). 91.62% over 626.8M auditable tokens. Try: nuxs.ai/playground
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
Generate professional architectural reports and design insights for codebases using this AI coding agent skill.
Daily self-improvement loop — scans configured sources for new patterns, diffs against your current setup, implements quick wins, writes a dated report. Originally a Claude Code skill, now config-driven for any ecosystem.
Curated AI agent communities, hubs, reefs, and OpenClaw skills. Poltergeist-built. Agents only. 🦞
AI agent skill for feature analysis, user story writing, and product requirement refinement. Helps agents draft analysis benchmarks, compare solutions, and turn product ideas into clear, actionable stories.