Detects and scaffolds a project's AI memory layer (layered docs/, two-phase workflow, main-rules-file hookup) — tool-neutral, for Claude Code / Cursor / Codex / Antigravity and others.
npx add-skill meow-Kat/agent-memory-scaffoldDetects and scaffolds a project's AI memory layer (layered docs/, two-phase workflow, main-rules-file hookup) — tool-neutral, for Claude Code / Cursor / Codex / Antigravity and others.
Source: https://github.com/meow-Kat/agent-memory-scaffold
Discovered during the daily awesomeskills.dev agent-skill hunt.
Share agent skills with a link. Publish and install SKILL.md artifacts across Claude Code, Codex, Cursor, OpenCode, and more.
AI text humanizer for prose, code & academic writing. 100+ patterns, two-pass audit, three-tier scoring, voice injection. Claude Code skill. No API calls — pure local pattern matching. The humanizer that studies how AI actually writes instead of swapping synonyms.
SharkonAI is a fully autonomous, self-recovering AI agent that lives in Telegram. It combines a powerful LLM brain (NVIDIA-hosted models) with 51+ executable tools to perform virtually anything — from running system commands and writing code, to controlling your desktop GUI with pixel-perfect precision, to creating its own new skills at runtime.
OpenCode port of academic-research-skills: 4 skills, 13 slash commands, 38-agent pipeline for academic research, writing, peer review, and revision
面向长篇小说创作的 AI Native 开源系统，用 Agent、世界观、写法引擎、RAG 和整本生产工作流，帮助新手从一句灵感走到完整小说。AI-native engine for end-to-end novel creation — from idea to full chapters, with structured planning, worldbuilding, and agent-driven workflows.
"ULTRASHIP" Claude Code plugin — 39 skills, 33 tools, 11 agents for ship-ready workflows: planning, review, pentesting, safety guardrails, canary monitoring, SEO/AI-readiness check, penetration testing, code review, competitive analysis, incident response. 1 dependency. 180 tests. MIT.