spellbook

Automatically diagnose excessive Codex local SQLite diagnostic log writes and give a concrete fix plan. Use when a user asks whether Codex is writing too much to disk, mentions logs_2.sqlite, logs_2.sqlite-wal, block_log_inserts, SSD/TBW wear from Codex logs, or wants Codex log write issues checked, explained, stopped, cleaned up, verified, or restored.

Use when you want Codex to review its own recent history (last N days or specific period) and improve its behavior. Produces minimal, high-signal updates to AGENTS.md and tiny reusable skills. The goal is long-term fluency — Codex gradually becomes better at your specific style, constraints, and workflows.

Use when coordinating complex tasks across multiple AI agents with a centralized handoff document for planning, execution tracking, and feedback fusion.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Guard long, ambiguous, or stateful AI-agent work from drift. Use when the user asks to run or continue a multi-step task, autonomous loop, bug fix, repo change, PR readiness check, compaction handoff, resume from previous context, cost-control checkpoint, or any task likely to span many tool calls, files, sessions, agents, or verification gates.

Audit and standardize a repository's agent-readable context, including AGENTS.md, CLAUDE.md, WARP.md, CONTRIBUTING.md, .agents/skills, and specs/ PRODUCT.md and TECH.md contracts. Use when asked to review, design, create, scaffold, or improve repo instructions, agent onboarding, spec workflows, or cross-repo agent-context conventions.

Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. Requires Codex CLI to be installed and authenticated.

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing

Use when the user explicitly asks for $threads, Codex-native subagents, 开几个子 agent, or a GitHub issue/PR queue needing parallel lanes, worktrees, review/merge gates, and closure audit. Do not use for OS/language threads, chat/email/forum threads, or Assistants product threads unless Codex workflow orchestration is explicit.

Use when Codex feels slow, bloated, or heavy after heavy use. Provides safe session hygiene, archive strategy, and handoff discipline to keep daily Codex usage responsive and low-friction. Always pairs with comprehensive handoffs before archiving active work.

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。 典型触发语句： - “Claude写小红书翻译腔太重”“英文思考输出灾难” - “帮我把这个笔记改成纯中文网感”“去除Claude翻译腔” - “公众号文章中途变英文了”“50 Skills内容生成翻车” - “强制Claude用中文思考写笔记”“小红书情绪化表达润色” 始终保护用户原有的 CLAUDE.md / AGENTS.md 中的人设与语气要求，只做最小必要干预。优先与 xiaohongshu 技能组合使用。

Generate web assets including favicons, app icons (PWA), and social media meta images (Open Graph) for Facebook, Twitter, WhatsApp, and LinkedIn. Use when users need icons, favicons, social sharing images, or Open Graph images from logos or text slogans. Handles image resizing, text-to-image generation, and provides proper HTML meta tags.

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

Safely diagnose and improve local network speed, latency, jitter, DNS, Wi-Fi, Ethernet, macOS network services, and bufferbloat. Use this skill whenever the user asks to optimize internet/network speed, make the network faster, diagnose slow Wi-Fi, latency, packet loss, DNS delay, unstable Codex/AI tool connectivity, or asks about the viral Codex network optimization workflow. Always protect VPN/proxy tools such as Clash Verge, Mihomo, Shadowrocket, Tailscale, V2Ray, Surge, and corporate VPNs; do not modify or disable them unless the user explicitly asks for that specific change.

全面代码库审计 — 自适应并行深度分析（前后端契约、数据完整性、异常处理/安全、架构/技术债、配置/缓存），输出按严重程度排序的统一报告和修复路线图。Use when user asks to audit, analyze, or review an entire codebase for design issues, find hidden bugs, check architecture health, or asks '全面审查', '代码库审计', '分析设计问题', 'audit codebase', 'health check', '有哪些问题'. Also trigger when user asks to find silent degradation, data flow breakpoints, type mismatches between frontend and backend, or wants to understand technical debt across a project.

Clash Verge 诊断与配置管理。网络诊断、配置 AI 工具路由规则（Claude/Codex/Cursor/Warp）、查看/克隆订阅配置、切换配置文件。当用户遇到网络问题、要配置代理规则、切换订阅、查看 Clash 配置时使用

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Browser automation and testing with Playwright. Use when testing web applications, automating browser tasks, taking screenshots, or validating UI behavior.

服务器安全审计与加固。扫描 SSH、防火墙、端口暴露、文件权限、暴力破解等安全问题，生成报告并提供一键修复。当用户说服务器安全、安全审计、安全检查、安全加固时使用

Logging system design guide covering centralized architecture, field standards, and distributed tracing. Use when designing log systems, establishing standards, or debugging production issues.

Use when planning, building, designing, code review, refactor, fixing, improving, optimizing, enhancing, or checking UI/UX work. Covers product patterns, landing pages, chart choices, visual styles, palettes, typography, UX rules, and 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.

Audit, design, categorize, distribute, and measure agent skills using lessons from Anthropic's Lessons from building Claude Code: How we use skills. Use when reviewing an existing skill, deciding whether a workflow deserves a skill, planning a skill library, turning team knowledge into skills, choosing skill categories, writing trigger descriptions, designing progressive disclosure, or planning skill marketplace and usage measurement.

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 Q4_K_M、64K/128K 长上下文、QAT Q4_0 @ 256K、左右对比演示之间选择，配置 tmux 后台运行，验证健康检查、问答接口、资源占用和常见故障。当用户说部署 Gemma 4、Gemma 4 12B、本地大模型、长上下文、QAT、量化、llama-server、Ollama、GGUF、Mac 本地模型服务时使用。

Use when writing, modifying, or reviewing Rust code. ALWAYS invoke before Rust edits; covers Microsoft Pragmatic Rust guidance for error handling, API design, performance, and idiomatic patterns.

REST/GraphQL/gRPC API design best practices. Use when designing APIs, defining contracts, handling versioning. Covers OpenAPI 3.2, GraphQL Federation, gRPC streaming.

Design architecture foundations before implementation. Use when asked to design or refactor architecture, choose Rust/Go crate, package, module, runtime, workflow, or service boundaries, compare mature project architecture, prevent stacked one-off PRs, audit migration debt in existing repos, or produce a spec before coding.

OAuth 2.1 + JWT authentication security best practices. Use when implementing auth, API authorization, token management. Follows RFC 9700 (2025).

在 Linux VPS 上部署 CLIProxyAPI + NewAPI 组合栈，把 Codex/Claude/Gemini/Qwen 等订阅账号包装成可计费的 OpenAI 兼容 API。负责 NewAPI Docker 部署、容器→宿主桥接、模型计费倍率（ModelRatio/CacheRatio/CompletionRatio）、SQLite 直写额度、CLIProxyAPI 408 冷却补丁、多账号 OAuth 凭据热加载、双路径验证。当用户说"部署 cliproxy + newapi"、"加 OpenAI 计费层"、"配置 newapi 渠道接 cliproxy"、"newapi 价格不对"、"加新的 codex/claude 账号到现有部署"、"172.17.0.1 容器网络"、"408 冷却放大故障"时触发。

Use when a contributor wants to move beyond simple bug fixes into architectural improvements, technical debt discovery, design proposals, or module ownership opportunities.

Use when designing PostgreSQL + Redis data models, indexes, caching strategies, JSONB usage, tiered storage, or cache consistency contracts.

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。

Guides clean architecture design with strict 200-line file limits. Use when starting new features, refactoring large files, or planning module structure. Enforces modular design and real testing.

Use when the user wants to extract Figma designs into production-ready React or Next.js components with TypeScript, Tailwind CSS, and pixel-perfect accuracy.

Use when executing coding tasks with a strict delivery workflow: build a full plan, implement one step at a time, run tests continuously, and commit by default after each step (`per_step`). Support explicit commit policy overrides (`final_only`, `milestone`) and optional BDD (Given/When/Then) when users ask for behavior-driven delivery or requirements are unclear.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Generates meaningful, conventional commit messages automatically. Use when committing code changes. Analyzes diff to create descriptive commits following best practices.

Use when the user asks to discover and deliver repository optimization work end to end: identify performance/reliability/maintainability/security/dx/cost optimization points, prioritize by impact-effort-risk, then execute fixes step by step with continuous testing and explicit commit policy (`final_only`, `per_step`, `milestone`). Default to `per_step` for implementation work so each feature is tested then committed before the next feature. Supports optional BDD (Given/When/Then).

扫描并诊断你个人 ~/.claude/skills 里的技能健康状态。当用户说以下任意内容时使用： - “我的技能失效了”“升级后老技能不认了” - “技能腐烂了”“外部依赖坏了”“我的个人 Arsenal 乱了” - “帮我检查技能健康”“技能生命周期”“长期维护技能” - “我 1-2 年前超好用的 Skill 现在 Claude 完全不认了” - “我的部署类技能现在执行不了了，外部项目下线了” 特别适合维护 1 年以上个人技能集合（Arsenal + 自定义 + 社区拷贝混合）的重度用户。 Always protect 用户现有的 CLAUDE.md / AGENTS.md / 自定义配置，只读优先，任何修改必须用户明确确认后才执行。 发现问题时优先给出最小变更 + 备份建议，绝不擅自大规模修改。

Use when deep architecture review or convergence planning requires analyzing repository-level duplicate/redundant design first, then building and executing a strict step-test-update plan in docs/plan.

Use when the user needs product management workflows such as RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, go-to-market strategy, feature prioritization, research synthesis, or requirements documentation.