Agent skills for Claude Code, Codex, OpenCode & Cursor — autonomous orchestration, code quality, local LLMs (Harbor), and writing pipelines
#anthropic
1103 posts
Expert skills, agents, commands, rules, hooks & output styles for Claude Code — session continuity + modern CLI tooling for real-world dev w...
agentdots-sync: backup and sync local AI agent skills, AGENTS.md, CLAUDE.md, and rules to Git. 安全同步 Claude Code / Codex / OpenCode / Gro...
SEO checker skill for Claude Code — pre-commit SEO audit: /seo-check reviews your git diff for regressions (noindex, robots.txt, canonicals,...
Your agent reads the few skills a task needs, not forty. Picks none, one, or a small bounded set, and leaves the rest on disk.
Unofficial, safety-first QQ Mail CLI for scripts and AI agents. Read/search/triage/backup/gated-cleanup/allowlisted-send over a stable JSON...
Claude Fable 5.1 prompting guide as Claude Code skills (KO/EN/ZH). Output quality goes up on Opus 5 and Sonnet 5 too.
Kill AI slop in agent writing. Skill + hooks that make Claude, Codex, and Grok write like a person: direct, active voice, no filler, no fake...
Промпт для Claude Code и для Codex это два разных языка. Переписывает ваш под ту модель, где вы работаете, по официальным правилам вендора,...
Claude Design in Claude Code, Codex, Cursor, and 20+ agents. Designs come from your real components, tokens, and states; approved revisions...
Local control plane for Claude Code on Windows and macOS: switch LLM gateways in one click behind a fixed endpoint, SSE keepalive proxies, k...
本地运行的大模型聚合网关,GUI桌面端app,零代码部署,把Coding Plan、大模型 API 额度聚合成一个虚拟 Plan,一键接入 Claude Code、Claude Desktop...