Search
majiayu000/spellbook
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 49 | Parallel multi-AI cross-validation research workflow (大版本). An agent skill from majiayu000/spellbook. | majiayu000/ | 287 | — | ~2k | Automated safety check: Pass | MIT | 3 days ago |
| 50 | Observability and SRE expert. An agent skill from majiayu000/spellbook. | majiayu000/ | 287 | — | ~3.3k | Automated safety check: Pass | MIT | 3 days ago |
| 51 | Plan, diagnose, and verify performance budgets, latency targets, load tests, capacity estimates, bottleneck analysis, caching strategy, query efficiency, queue throughput, and regression gates. | majiayu000/ | 287 | — | ~501 | Automated safety check: Pass | MIT | 3 days ago |
| 52 | 52.Prd Master PRD writing and product definition expert. An agent skill from majiayu000/spellbook. | majiayu000/ | 287 | — | ~3.4k | Automated safety check: Pass | MIT | 3 days ago |
| 53 | Product analytics and growth expert. An agent skill from majiayu000/spellbook. | majiayu000/ | 287 | — | ~2.7k | Automated safety check: Pass | MIT | 3 days ago |
| 54 | Product discovery and market research expert. An agent skill from majiayu000/spellbook. | majiayu000/ | 287 | — | ~3.3k | Automated safety check: Pass | MIT | 3 days ago |
| 55 | Product interaction and UX expert. An agent skill from majiayu000/spellbook. | majiayu000/ | 287 | — | ~3.1k | Automated safety check: Pass | MIT | 3 days ago |
| 56 | Comprehensive codebase health analysis. An agent skill from majiayu000/spellbook. | majiayu000/ | 287 | — | ~1.7k | Automated safety check: Notes | MIT | 3 days ago |
| 57 | Modern Python project architecture guide for 2025. An agent skill from majiayu000/spellbook. | majiayu000/ | 287 | — | ~2.7k | Automated safety check: Notes | MIT | 3 days ago |
| 58 | Provides React patterns for hooks, effects, refs, and component design. | majiayu000/ | 287 | — | ~2.7k | Automated safety check: Pass | MIT | 3 days ago |
| 59 | Plan and verify software releases with versioning, changelogs, release branches, feature flags, canaries, migration gates, rollback, deployment checks, and release readiness. | majiayu000/ | 287 | — | ~511 | Automated safety check: Pass | MIT | 3 days ago |
| 60 | Scaffold or standardize a production-ready repository structure with specs, source layout, tests, CI, agent context, config examples, release notes, and operational docs. | majiayu000/ | 287 | — | ~651 | Automated safety check: Pass | MIT | 3 days ago |
| 61 | 61.Rust Project Modern Rust project architecture guide for 2025. An agent skill from majiayu000/spellbook. | majiayu000/ | 287 | — | ~2.9k | Automated safety check: Pass | MIT | 3 days ago |
| 62 | Threat-model product features, APIs, data flows, secrets, permissions, supply-chain changes, auth boundaries, and risky code paths before or during implementation. | majiayu000/ | 287 | — | ~561 | Automated safety check: Pass | MIT | 3 days ago |
| 63 | 63.Skill Audit Audit, design, categorize, distribute, and measure agent skills using lessons from Anthropic's Lessons from building Claude Code: How we use skills. | majiayu000/ | 287 | — | ~1.6k | Automated safety check: Pass | MIT | 3 days ago |
| 64 | Technical specification and design document expert. An agent skill from majiayu000/spellbook. | majiayu000/ | 287 | — | ~3.3k | Automated safety check: Pass | MIT | 3 days ago |
| 65 | 65.Trip Planner A skill your agent uses when the user wants detailed travel itineraries with activities, logistics, day-by-day schedules, vacation planning, trip organization, or travel documentation. | majiayu000/ | 287 | — | ~873 | Automated safety check: Pass | MIT | 3 days ago |
| 66 | Modern TypeScript project architecture guide for 2025. An agent skill from majiayu000/spellbook. | majiayu000/ | 287 | — | ~3.3k | Automated safety check: Pass | MIT | 3 days ago |
| 67 | 67.Zig Project Modern Zig project architecture guide. An agent skill from majiayu000/spellbook. | majiayu000/ | 287 | — | ~2.6k | Automated safety check: Pass | MIT | 3 days ago |
| 68 | GitHub Trending 探索与分析。用于发现热门开源项目、技术趋势、开发者偏好，帮助理解技术社区的兴趣走向。使用场景包括“看看今天 GitHub 什么火了”、“Rust 最近热门项目”、“AI 领域趋势日报”、“这个方向有没有值得关注的开源项目”、“帮我做个 GitHub trending 分析”。 | majiayu000/ | 287 | — | ~647 | Automated safety check: Pass | MIT | 3 days ago |
| 69 | 只读统计 Claude/Codex 的 Skill 使用证据并检查 agent 配置健康。仅用于明确的健康检查、配置诊断、使用排行或低使用候选请求；会识别 enabled 插件并单列批量审计读取。不要用于规范源、触发、全局/项目/profile/冷存储、投影或退役治理，改用 skill-ecosystem-doctor。忽略引用日志和相邻任务。 | majiayu000/ | 287 | — | ~2.1k | Automated safety check: Pass | MIT | 3 days ago |
| 70 | Four-phase debugging framework for any technical issue. An agent skill from majiayu000/spellbook. | majiayu000/ | 287 | — | ~981 | Automated safety check: Pass | MIT | 3 days ago |
| 71 | 71.Xiaohongshu 生成小红书文案和配图。当用户需要写小红书、生成社交媒体文案、小红书运营内容时使用. An agent skill from majiayu000/spellbook. | majiayu000/ | 287 | — | ~2k | Automated safety check: Notes | MIT | 3 days ago |
| 72 | Audit and organize AI coding-agent instructions, including AGENTS.md, CLAUDE.md, skills, and agent definitions. | majiayu000/ | 287 | — | ~4k | Automated safety check: Pass | MIT | 3 days ago |
| 73 | Evidence-driven architecture research for understanding real systems and making technical decisions. | majiayu000/ | 287 | — | ~2.8k | Automated safety check: Pass | MIT | 3 days ago |
| 74 | A skill your agent uses when you want Codex to review its own recent history (last N days or specific period) and improve its behavior. | majiayu000/ | 287 | — | ~1.6k | Automated safety check: Pass | MIT | 3 days ago |
| 75 | 在本机 Mac 或 Apple Silicon 上部署 Gemma 4 12B。本地安装/升级 llama.cpp，下载 GGUF 量化模型，用 llama-server 暴露 OpenAI-compatible API，或用 Ollama 暴露本地模型服务；按用户需求在默认 Q4KM、64K/128K 长上下文、QAT Q40 @ 256K、左右对比演示之间选择，配置 tmux… | majiayu000/ | 287 | — | ~875 | Automated safety check: Notes | MIT | 3 days ago |
| 76 | Art-direct complete illustrated websites and write project-specific image-generation prompts. | majiayu000/ | 287 | — | ~1.6k | Automated safety check: Pass | MIT | 3 days ago |
| 77 | 77.Vibeguard Lightweight anti-hallucination workflow for task kickoff, review prioritization, and regression retrospectives. | majiayu000/ | 287 | — | ~723 | Automated safety check: Pass | MIT | 3 days ago |
| 78 | 想法群聊室 — 调研员角色。被 idea-team 主编排器调用，或用户单独说"调研一下 X"、"X 的现状/竞品/数据"、"找 2026 数据"、"事实底"时触发。用 WebSearch 拉真实 2026 数据、列竞品、引来源——只给事实，不评判，不建议。Do NOT use when 用户要评价想法好坏（那是反方）、或要跨界启示（那是类比者）、或已有 PRD 在跑（不需要这种调研）。插件内… | majiayu000/ | 287 | — | ~385 | Automated safety check: Pass | MIT | 3 days ago |
| 79 | Create or audit SLOs, SLIs, alert rules, incident response steps, escalation paths, postmortems, operational runbooks, and customer-impact communication. | majiayu000/ | 287 | — | ~460 | Automated safety check: Pass | MIT | 3 days ago |
| 80 | A skill your agent uses when creating or maintaining UI design systems, design tokens, component documentation, responsive calculations, quality checks, or design-dev handoff materials. | majiayu000/ | 287 | — | ~328 | Automated safety check: Pass | MIT | 3 days ago |
| 81 | 能力蒸馏工作流——从用户批准的强模型访谈或真实任务轨迹中提取非显然的判断规则，形成可审计的 judgment packet，再交给 skill-audit 和 skill-creator 决定是否落成可加载 skill。当用户说“蒸馏这个模型的判断力”“把这次任务的关键决策固化下来”“模型窗口要关了，保留它在某类场景的判断”时使用。普通流程文档、直接写… | majiayu000/ | 287 | — | ~1.3k | Automated safety check: Pass | MIT | 3 days ago |
| 82 | 82.Clash Routes 查看本机进程的 Mihomo 实时代理链。当用户问 Claude、Codex、Gemini、ChatGPT、 浏览器或其他进程走哪个代理时使用。只读。Profile 拓扑和写入使用 clash-doctor， 出口 IP 质量使用 ip-check。 | majiayu000/ | 287 | — | ~1.1k | Automated safety check: Notes | MIT | 3 days ago |
| 83 | 83.Disk Cleaner 当用户要扫描磁盘空间、找出可安全删除的缓存/编译产物/安装包、或交互式释放空间时使用. An agent skill from majiayu000/spellbook. | majiayu000/ | 287 | — | ~1.5k | Automated safety check: Notes | MIT | 3 days ago |
| 84 | Create distinctive, production-grade web frontend interfaces with high design quality. | majiayu000/ | 287 | — | ~1.4k | Automated safety check: Pass | MIT | 3 days ago |
| 85 | 85.GPU Use 查看远程服务器 GPU 使用情况。SSH 连接服务器，展示每张卡的显存占用、运行进程、所属容器。当用户说查看 GPU、显卡占用、显存使用时使用 | majiayu000/ | 287 | — | ~761 | Automated safety check: Notes | MIT | 3 days ago |
| 86 | Browser automation and testing with Playwright. An agent skill from majiayu000/spellbook. | majiayu000/ | 287 | — | ~335 | Automated safety check: Notes | MIT | 3 days ago |
| 87 | React and Next.js performance playbook distilled from Vercel Engineering guidance. | majiayu000/ | 287 | — | ~1.1k | Automated safety check: Pass | MIT | 3 days ago |
| 88 | 系统性能诊断。当用户说电脑卡、系统慢、查看进程、CPU占用高、内存不够等性能问题时使用. An agent skill from majiayu000/spellbook. | majiayu000/ | 287 | — | ~941 | Automated safety check: Notes | MIT | 3 days ago |
| 89 | A skill your agent uses when planning, building, designing, code review, refactor, fixing, improving, optimizing, enhancing, or checking UI/UX work. | majiayu000/ | 287 | — | ~442 | Automated safety check: Pass | MIT | 3 days ago |
| 90 | 90.Slides 生成口播视频背景 PPT 幻灯片（16:9 横版 PNG 序列）。当用户需要做 PPT、生成幻灯片、做演示背景图时使用. An agent skill from majiayu000/spellbook. | majiayu000/ | 287 | — | ~2k | Automated safety check: Notes | MIT | 3 days ago |
| 91 | 根据参考图、带尺寸的设计图或文字概念，在 Blender 中制作由独立命名零件组成的可编辑 3D 模型，再按用户要求修改尺寸、部件和配色，交付 .blend、GLB 和多角度渲染。用于图纸转三维、产品概念建模和风格化硬表面道具，以及“做一个同样的案例，换成坦克或其他物体”等请求；不用于人物角色、头发或脸部建模，这些请求使用… | majiayu000/ | 287 | — | ~593 | Automated safety check: Pass | MIT | 3 days ago |
| 92 | 根据人物参考图在 Blender 制作、修整和配色可编辑角色，尤其适用于二次元头部与头发、静态多角度展示。覆盖输入拆解、轮廓与五官标注、九视图参考、模板选型、几何实现、材质配色、视觉检查和工程交付；当用户要求图转三维头像、按参考建模、修复相似度、完善配色或运行完整人物制作流程时使用。仅分析、写流程或封装技能时不修改模型。 | majiayu000/ | 287 | — | ~944 | Automated safety check: Pass | MIT | 3 days ago |
| 93 | 93.Clash Doctor Clash Verge 与 mihomo 诊断和 profile 管理。当用户遇到代理失败、需要配置 AI 工具路由、本地 Hub 拓扑、多机对齐、TUN 绕过、克隆或切换订阅，或同步后 配置未生效时使用。进程线路使用 clash-routes，出口 IP 质量使用 ip-check。 | majiayu000/ | 287 | — | ~648 | Automated safety check: Notes | MIT | 3 days ago |
| 94 | 当用户用 Claude 写小红书、公众号、视频脚本等内容时，输出出现翻译腔、英文思考、西式框架，导致“像外国人假装写中文”时使用。 | majiayu000/ | 287 | — | ~802 | Automated safety check: Pass | MIT | 3 days ago |
| 95 | 优化实际模型推理链路，将正确性对齐、分段 profiling、显存与数据搬运、TensorRT/ONNX/PyTorch 后端、attention/kernel、FP8/compile、缓存与少步采样、质量回归、GPU 成本和服务验收串成同一实验闭环。当用户要求推理提速、降低显存或 GPU 成本、复现模型效果、定位 GPU 利用率低、优化图像/视频/扩散模型或自托管 LLM 时使用，提供… | majiayu000/ | 287 | — | ~1.1k | Automated safety check: Pass | MIT | 3 days ago |
| 96 | 在已经过独立验证的 CLIProxyAPI upstream 之上部署 NewAPI 计费层，把 Codex/Claude/Gemini/Qwen 等订阅账号包装成可计费的 OpenAI 兼容 API。本 Skill 不负责新建裸 CLIProxyAPI；负责 NewAPI Docker 部署、容器到宿主桥接、模型计费倍率、参数化额度修正、多账号 OAuth… | majiayu000/ | 287 | — | ~1.7k | Automated safety check: Warn | MIT | 3 days ago |
