assistant
claudecodex个人 AI 助手 3.0 - 11 个命令 + 14 个 skills + SessionStart 上下文注入 + 活动/健康脚本;CODE 循环与记忆消融
14 skills · 11 commands · hooks
智能通知插件 - Claude Code 完成任务或需要权限时发送 macOS 通知,支持点击跳转(Claude 桌面版 Code 标签页、iTerm2 和 Cursor)。桌面版精确跳回具体会话,默认让路给 App 自己的原生通知,只在用户关掉它时接管。
Plugin claude-notify from marketplace build-your-system in haoliucha/build-your-system. Commands read from the repo's manifest — 8 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
/claude-notify:setup[一键] 扫描环境、安装依赖、配置权限、验证通知
bash ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/notify-smart.sh
bash ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/notify-smart.sh
个人 AI 助手 3.0 - 11 个命令 + 14 个 skills + SessionStart 上下文注入 + 活动/健康脚本;CODE 循环与记忆消融
14 skills · 11 commands · hooks
To-B 投标/交付物项目方法论 - 单一真源生成器纪律、口径级联同步、可辩护成本测算、PERT 排期、对抗审校、去AI味、图表与中文PDF管线、调研取证、售前谈判、原型交接。10 个 skills + 6 个流程节点命令(/bid:init·meeting·sync·handoff·review·status),提炼自真实投标项目全周期实战(318 条经验,已全脱敏)。
16 skills · 6 commands
短视频创作助手 - 共享选题、Hook、结构、逐字稿、标题与发布工作流;Claude 命令为薄入口。
12 skills · 8 commands
X (Twitter) 工具集:Claude 与 Codex 共享 x-follow 精准关注、x-unfollow 关注卫生,以及 x-image `/x:image` 封面和 article illustrations。关注需明确授权;评论默认关闭并要求独立双授权。图片任务经 Codex Rescue 交给原生 Codex,以 one-call ImageGen 完整生成且无后处理。
3 skills · 3 commands
随时随地远程开发栈 - 一键搭建 mosh + tmux + SSH 中继方案,iPhone/iPad/任何笔记本都能从山顶、咖啡馆、高铁连回家中 Mac。含 dropfile 终端传文件能力(截图或选文件→快捷键→路径进 Claude Code 输入框,支持任意文件类型,默认 15MB 上限,可在线一键安装)。1 个 skill + 6 个配置模板 + 6 个可执行脚本,覆盖 ECS Relay 和 DDNS 直连两种架构。
1 skill
/goal 命令提示词工程辅助 - 通过引导式 brainstorm 把模糊需求转成可验证的 /goal 命令,自动写决策 log 并在当前 session 触发。基于 superpowers TDD 方法论 (6 RED 场景 + 6 GREEN 验证 + 50 Tier 1 内容契约测试 全绿)。
1 skill
Code cleanup, refactoring automation, and technical debt management with context restoration
3 commands · 2 agents
Knowledge base compiled from OpenAI's Spinning Up in Deep RL (MIT, Joshua Achiam) by engineering/book-to-skill. A resident core carries the RL optimization problem, the model-free taxonomy, the policy-gradient template with its five valid weights, the safe-step family (VPG to TRPO to PPO) and the overestimation family (DDPG to TD3 and SAC); 20 on-demand chapters cover key concepts and MDPs, the algorithm taxonomy and model bias, the policy gradient derivation with the log-derivative trick and EGLP lemma, Achiam's researcher essay, the key-papers topic map, the exercises including the silent DDPG broadcasting bug, the benchmark parity disclosure, one chapter per algorithm, and the logger/MPI/ExperimentGrid utilities. Ships a glossary, a patterns file with 16 techniques, a decision cheatsheet with thresholds, a cs-spinning-up-deep-rl agent and /cs-spinning-up-deep-rl. Structured study notes, not a reproduction of the source.
1 skill · 1 command · 1 agent
PM utility skills: resume review, NDA drafting, privacy policy generation, and grammar/flow checking. Essential tools for product managers beyond core product work.
4 skills · 5 commands
Content generation, AI backends, and utility tools for daily work efficiency
22 skills
Official GSAP skills for Cursor, Claude and other AI agents, covering tweens, timelines, ScrollTrigger, plugins, utilities, React hooks, and performance optimization
8 skills
es-toolkit best practices: function recommendation, lodash migration, and compat guidance
3 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.