majiayu000/spellbook
51 skills · 10 total installs
$npx skills add majiayu000/spellbookSkillInstalls
app-ui-designMobile app UI design expert for iOS and Android. Use when designing app interfaces, creating design systems, ensuring accessibility, or following platform…optimize-networkSafely diagnose and improve local network speed, latency, jitter, DNS, Wi-Fi, Ethernet, macOS network services, and bufferbloat.agentsmd-optimizeAudit AND optimize a CLAUDE.md / AGENTS.md instruction file — score it against the five high-leverage patterns, flag anti-patterns, then apply approved fixes…agentsmd-scaffoldGenerate or update repository-specific AGENTS.md instruction files from real repo evidence.api-designREST/GraphQL/gRPC API design best practices. Use when designing APIs, defining contracts, handling versioning.app-user-story-qaEnd-to-end app feature inventory and user-story testing workflow with a canonical tracker.architecture-foundationDesign architecture foundations before implementation. Use when asked to design or refactor architecture, choose Rust/Go crate, package, module, runtime,…ask-opencliAsk Grok or Gemini via opencli (browser-session based, no API cost).auth-securityOAuth 2.1 + JWT authentication security best practices. Use when implementing auth, API authorization, token management. Follows RFC 9700 (2025).capability-distill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…clash-doctorClash 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clash-routes查看指定进程的代理线路。通过 Mihomo API 查询当前活跃连接，显示进程匹配的规则和代理链路。用于确认某个进程（如 claude、chrome）走的是哪条订阅线路cliproxy-newapi-stack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…codebase-audit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），结构化 findings + 对抗验证 + 基线对比，输出按严重程度排序的统一报告和修复路线图。支持 quick 快速体检模式。Use when user asks to audit, analyze, or…codexUse when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editingcodex-agentUse when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative…codex-fluentUse when Codex feels slow, bloated, or heavy after heavy use. Provides safe session hygiene, archive strategy, and handoff discipline to keep daily Codex usage…codex-log-guardDiagnose excessive Codex local SQLite diagnostic log writes with read-only evidence by default.codex-retrospectiveUse when you want Codex to review its own recent history (last N days or specific period) and improve its behavior.comprehensive-testingComplete testing strategy covering TDD workflow, test pyramid, unit/integration/E2E/property testing, framework best practices (Jest, Vitest, pytest), mock…config-secrets-environmentsDesign, audit, and verify configuration, environment separation, secrets, BYOK flows, key rotation, config schema validation, and drift checks across local,…contribution-architectUse when a contributor wants to move beyond simple bug fixes into architectural improvements, technical debt discovery, design proposals, or module ownership…contributorEnd-to-end open source contribution workflow: from scanning issues to submitting PRs.css-debugUse this skill to diagnose CSS and frontend layout issues such as positioning, overflow clipping, Tailwind class conflicts, z-index stacking, and React…data-contract-migrationsDesign and verify data contracts, schema changes, migrations, rollbacks, backfills, compatibility windows, tenant isolation, and API-to-database field mapping.database-patternsUse when designing PostgreSQL + Redis data models, indexes, caching strategies, JSONB usage, tiered storage, or cache consistency contracts.dev-architecture-playbookRoute full software-development architecture work from product intent through design, implementation, testing, release, and operations.devops-excellenceDevOps and CI/CD expert. Use when setting up pipelines, containerizing applications, deploying to Kubernetes, or implementing release strategies.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。elegant-architectureGuides clean architecture design with strict 200-line file limits. Use when starting new features, refactoring large files, or planning module structure.figma-to-codeExtract Figma designs and generate production-ready React/Next.js components with TypeScript, Tailwind CSS, and pixel-perfect accuracy.figma-to-reactUse when the user wants to extract Figma designs into production-ready React or Next.js components with TypeScript, Tailwind CSS, and pixel-perfect accuracy.flowguardGuard 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…frontend-designCreate distinctive, production-grade frontend interfaces with high design quality.gemma4-local-deploy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…git-commit-smartGenerates meaningful, conventional commit messages automatically. Use when committing code changes.github-trendingGitHub 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”。golang-webModern Go Web application architecture guide. Use when creating new Go web projects, APIs, or microservices.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harmonyos-appHarmonyOS application development expert. Use when building HarmonyOS apps with ArkTS, ArkUI, Stage model, and distributed capabilities.humanizerRemove signs of AI-generated writing from text. Use when editing orincident-slo-runbookCreate or audit SLOs, SLIs, alert rules, incident response steps, escalation paths, postmortems, operational runbooks, and customer-impact communication.ip-check检测一个 IP 或住宅/机房代理节点的质量——注册库、地理库一致性、ASN/org、风控信誉、黑名单、住宅真实性、BGP 宣告、目标服务(Grok/Claude/ChatGPT)解锁与延迟三角测量。判定该 IP 能否安全用于 AI 服务(避免被地理库误判到别国导致区域锁)。当用户说"查这个…multi-ai-researchParallel multi-AI cross-validation research workflow (大版本). Dispatch N internal sub-agents + grok + gemini in parallel, automatically cross-validate findings,…multi-model-orchestratorUse when coordinating complex tasks across multiple AI agents with a centralized handoff document for planning, execution tracking, and feedback fusion.observability-sreObservability and SRE expert. Use when setting up monitoring, logging, tracing, defining SLOs, or managing incidents.performance-capacityPlan, diagnose, and verify performance budgets, latency targets, load tests, capacity estimates, bottleneck analysis, caching strategy, query efficiency, queue…playwright-automationBrowser automation and testing with Playwright. Use when testing web applications, automating browser tasks, taking screenshots, or validating UI behavior.prd-masterPRD writing and product definition expert. Use when writing PRDs, user stories, acceptance criteria, or prioritizing features.product-analyticsProduct analytics and growth expert. Use when designing event tracking, defining metrics, running A/B tests, or analyzing retention.product-discoveryProduct discovery and market research expert. Use when validating product ideas, conducting market research, user interviews, competitive analysis, or…