Skills 目录 · 第 41 页

Next.js 16+ 和 Turbopack：增量打包、文件系统缓存、开发速度，以及何时选择 Turbopack 或 webpack。

Next.js 16+ 和 Turbopack 指导：增量 Rust 打包、文件系统缓存、更快的开发启动与 HMR、Turbopack/webpack 取舍，以及 middleware.ts 改名为 proxy.ts。用于开发或调试 Next.js 16+ 应用、诊断开发启动或热更新缓慢、选择打包器，或审查 middleware/proxy 文件命名。

Next.js 16+とTurbopack — インクリメンタルバンドリング、FSキャッシング、開発速度、Turbopackとwebpackをいつどちらかどうかを選ぶか。

用于依赖更新：升级npm/pnpm/yarn/bun包、检查过时依赖，或运行taze。

使用现代框架、架构模式和最佳实践构建可扩展、可维护且可用于生产的 Node.js 后端应用的全面指南。

Node.js 开发原则与决策。框架选择、异步模式、安全性和架构。传授思维方式，而非照搬。

防止 JavaScript 和 TypeScript 中的 Ethereum 哈希错误。Node 的 sha3-256 是 NIST SHA3，而非 Ethereum Keccak-256，会静默破坏选择器、签名、存储槽和地址派生。适用于在 JavaScript 或 TypeScript 中为 Ethereum 进行哈希计算，或当选择器、签名、存储槽或派生地址出错时使用。

JavaScriptとTypeScriptにおけるEthereumハッシュバグを防ぐ。NodeのSHA3-256はNIST SHA3であり、Ethereum Keccak-256ではなく、セレクター、署名、ストレージスロット、アドレス導出を静かに破壊する。

防止 JavaScript 和 TypeScript 中的以太坊哈希错误。Node 的 sha3-256 是 NIST SHA3，而非以太坊 Keccak-256，会静默破坏选择器、签名、存储槽和地址推导。

定义一个北极星指标和 3-5 个支撑性输入指标，构成指标星座。对业务类型（注意力、交易、生产力）进行分类，并依据有效北极星的 7 项标准进行验证。适用于选择北极星指标、搭建指标框架、了解北极星框架，或决定衡量什么。

分布式NoSQL数据库（Cassandra、DynamoDB）的专业指导。侧重于心智模型、查询优先建模、单表设计，以及在高规模系统中避免热分区。

Save a to-do to the briefing notes, tagged with the current project. Use when the user types "/note" followed by the text.

适用于Google NotebookLM中的任何操作：查询笔记本、添加来源、生成音频或视频概览、报告、闪卡或幻灯片。驱动浏览器；需要浏览器自动化。

使用此技能可直接从 Claude Code 查询你的 Google NotebookLM 笔记本，获得由 Gemini 提供的基于来源、附有引用的回答。支持浏览器自动化、库管理、持久认证。通过仅基于文档的响应大幅减少幻觉。

将对话和决策整理为结构化 Notion 页面。适用于将聊天或笔记转为带有恰当链接的 Wiki 条目、操作指南、决策记录或常见问题。

借助Notion上下文和Codex调研准备会议材料；适用于收集背景信息、起草议程/预读材料，以及为参会者定制材料。

跨 Notion 来源开展研究，并整理为结构化文档。适用于从多个 Notion 来源收集信息，生成附引用的简报、对比或报告。

将 Notion 规格转化为实施计划、任务和进度跟踪；在实施 PRD/功能规格并据此创建 Notion 计划和任务时使用。

作为业务构建和销售Notion模板的专家——不仅是制作模板，而是构建可持续的数字产品业务。涵盖模板设计、定价、市场平台、营销以及扩展到真实收入。使用场景：notion模板、销售模板、数字产品、notion业务、gumroad。

实现 NOWAIT 技术，用于 R1-style 大语言模型的高效推理。适用于优化推理模型（QwQ、DeepSeek-R1、Phi4-Reasoning、Qwen3、Kimi-VL、QvQ）的推理，在保持准确率的同时将思维链词元用量降低 27-51%。触发条件包括“优化推理”“减少思考词元”“高效推理”“抑制反思词元”，或处理冗长的 CoT 输出时。

Manage NuGet packages in .NET projects/solutions. Use this skill when adding, removing, or updating NuGet package versions. It enforces using `dotnet` CLI for package management and provides strict procedures for direct file edits only when updating versions.

Process, convert, OCR, extract, redact, sign, and fill documents using the Nutrient DWS API. Works with PDFs, DOCX, XLSX, PPTX, HTML, and images. Use when converting, OCRing, extracting from, redacting, signing, or filling documents via the Nutrient DWS API.

使用Nutrient DWS API处理、转换、OCR识别、提取、编辑、签名和填写文档。支持PDF、DOCX、XLSX、PPTX、HTML和图像格式。

Nutrient DWS API を使用してドキュメントの処理、変換、OCR、抽出、編集、署名、フォーム入力を行います。PDF、DOCX、XLSX、PPTX、HTML、画像に対応しています。

Nuxt 4 应用模式，涵盖水合安全、性能优化、路由规则、懒加载，以及使用 useFetch 和 useAsyncData 进行 SSR 安全的数据获取。

Nuxt 4 app patterns for hydration safety, performance, route rules, lazy loading, and SSR-safe data fetching with useFetch and useAsyncData. Use when building or reviewing a Nuxt 4 app, or debugging hydration mismatches and SSR-safe data fetching.

ハイドレーション安全性、パフォーマンス、ルートルール、遅延ロード、useFetchとuseAsyncDataを使ったSSR安全なデータフェッチングのためのNuxt 4アプリパターン。

当为服务添加指标、日志和追踪，修复嘈杂告警或设计仪表盘时使用。用 slo_designer.py 设计 SLI，用 alert_optimizer.py 调整告警，用 dashboard_generator.py 生成仪表盘。

构建生产就绪的监控、日志和追踪系统。实施全面的可观测性策略、SLI/SLO 管理和事件响应工作流。

用于追踪、评估和监控的LLM可观测性平台。适用于调试LLM应用、基于数据集评估模型输出、监控生产系统，或为AI应用构建系统化测试流水线。

用于 LLM 追踪、评估和监控的开源 AI 可观测性平台。在使用详细追踪调试 LLM 应用、对数据集运行评估，或通过实时洞察监控生产 AI 系统时使用。

创建和编辑Obsidian Bases（.base文件），包含视图、筛选器、公式和汇总。适用于处理.base文件、创建类似数据库的笔记视图，或用户提到Obsidian中的Bases、表格视图、卡片视图、筛选器或公式时。

用于创建 Obsidian Web Clipper 模板的指南。适用于需要新建剪藏模板、了解可用变量或格式化剪藏内容时。

创建和编辑 Obsidian 风格 Markdown，支持 wikilinks、嵌入、标注块、属性及其他 Obsidian 专有语法。适用于在 Obsidian 中处理 .md 文件，或用户提及 wikilinks、标注块、frontmatter、标签、嵌入或 Obsidian 笔记时。

Claude Agent SDK build harness with a Planner/Builder/Evaluator loop. Owns subagent topology, tool-budget design, harness loop shapes, and agent evaluation. Use for /oc-agent, "Claude Agent SDK", "build an agent", "subagent", "tool budget", "agent loop", "harness", "multi-agent", "agent eval", "orchestrator-worker". Model routing comes from oc-claude-api; agent-forge owns topology + harness shape.

First-party API design and build harness with Designer/Builder/Conformance loop. Owns OpenAPI/GraphQL authoring, schema↔code parity, versioning + sunset strategy, pagination/error/idempotency conventions, typed handler scaffolding, and SDK generation for the API your own clients consume. Use for /oc-api, /oc-api design, /oc-api spec, /oc-api scaffold, /oc-api version, /oc-api lint, /oc-api sdk, "design our API", "OpenAPI", "GraphQL schema", "versioning strategy", "deprecate endpoint", "generate SDK", "API schema drift" (spec↔code; warehouse/data schema drift is oc-data-ops). For consuming someone else's API (Stripe, Slack, OAuth) use oc-integrations-engineer instead.

Unified app development: idea → spec → design → build with Generator/Evaluator QA loop → launch. Use for /oc-app, /oc-discover, /oc-spec, /oc-design, /oc-roadmap, /oc-scaffold, /oc-build, /oc-launch, "build me an app", "I have an app idea", or any software project. Chains to (when you invoke it): oc-stack-forge and oc-ux-engineer.

Pre-commit QA gate that runs on every commit. Fast, opinionated checks: type safety, lint, tests, anti-pattern scan, secret detection, build verification, and dependency vulnerability scan. Blocks commits on failures, warns on cautions, passes silently on clean code. Invoked by oc-git-ops before every /oc-commit and /oc-git-sync. Use for /oc-bugcheck, "check this before I commit", "run the checks", "is this safe to commit", "pre-commit", "quick audit", "lint and test", "any bugs in this?", "sanity check".

Cross-skill protocol for session persistence. Not invoked directly — every other opchain skill implements this JSON checkpoint contract so state survives across conversations.

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill include prompt caching by default. Also migrates existing Claude API code between model versions (4.6 → 4.7 → 4.8, Mythos Preview → Fable 5, retired-model replacements). Use for /oc-claude-api, "Anthropic SDK", "prompt caching", "cache hit rate", "tool use", "model migration", "extended thinking", "batch API", "files API", "memory", "citations".

Code quality auditor with Auditor/Fixer/Verifier loop. Use for /oc-audit, "audit this", "find bugs", "code review", "pre-deploy check", "what's wrong with this code", or any code-level quality question. For fast pre-commit checks, escalate to oc-bug-check. For architecture- or infra-level security, escalate to oc-security-auditor.

Standing compliance operator: maps SOC 2 / HIPAA / GDPR controls to concrete repo and infra artifacts in a maintained control register, generates audit-ready evidence bundles at deploy and release time, and scaffolds the policy docs auditors ask for. Use for /oc-comply, /oc-compliance, "make us SOC 2 compliant", "get compliant", "SOC 2 evidence", "compliance checklist", "audit-ready", "control mapping", "GDPR", "HIPAA", "BAA", "data retention policy", "access review", "what would an auditor ask for", "compliance delta since last release". Consumes oc-security-auditor's readiness gaps (the point-in-time assessor); this skill is the standing register and evidence pipeline. Activated by `.opchain/compliance.yaml` (adds oc-deploy-ops' evidence gate row); absent profile, inert. Readiness and evidence, not certification and not legal advice. Technical control execution belongs to oc-security-hardening.

Cost operations harness — attribute LLM spend to the skill phase that incurred it, set per-phase and per-suite budgets that gate in the checkpoint, and recommend model-tier routing (Haiku for cheap repetitive phases, Opus for spec/audit/migration). Use for /oc-cost, "what did this cost", "cost attribution", "token cost", "budget gate", "model tier routing", "cost regression", "cheaper model", "spend per feature". Pairs with oc-prompt-ops (cost-regression gate alongside the score gate) and oc-telemetry-ops (feeds the public /dashboard cost stats).

Specialized dashboard and dense-information UI designer. Produces design specs AND working React prototypes with mock data for three archetypes: executive (KPI-driven, low density), operations (real-time, monitoring-dense), and analyst (exploratory, drill-heavy). ALWAYS trigger on /oc-data-forge, /oc-dash-forge, /dashboard, /dataviz-design. Also trigger on: "design a dashboard", "dashboard mockup", "BI design", "data visualization design", "KPI dashboard", "analytics UI", "monitoring dashboard", "dense information display", "what should the dashboard look like", "design a report view". Invoked by oc-ux-engineer when the UI is data-heavy and by oc-app-architect when the design phase encounters a dashboard surface.

Data-pipeline harness with a Designer/Builder/Contract-Verifier loop. Owns the data estate: ingestion patterns (batch, stream, CDC), transformation layering (staging → intermediate → marts), dbt project design, and observable data contracts with freshness/volume/schema SLAs. Use for /oc-data-ops, "data pipeline", "ingestion", "ELT", "dbt", "data warehouse modeling", "data contract", "warehouse schema drift", "stale data", "data quality checks", "volume anomaly", "sync SaaS data into the warehouse", "medallion architecture", "backfill strategy". Invoked by oc-app-architect Phase 2 when discovery surfaces a data-heavy backend. Warehouse/queue choice comes from oc-stack-forge. NOT single-metric analytics (oc-signal-forge), NOT dashboards (oc-dash-forge), NOT live-pipeline engine swaps (oc-migration-ops), NOT API contract / schema-to-code drift (oc-api-dev), NOT the SaaS connector mechanics (OAuth/webhooks — oc-integrations-engineer builds the connector; this skill owns the pipeline + cont

Deployment pipeline: audit gate → staging → production → monitoring. Use for /oc-deploy, "deploy this", "ship it", "push to production", "staging", "rollback", "health check", or any deployment task. Single-app managed deploys only: multi-container, self-managed or IaC deploys are oc-fleet-ops.

Documentation creation, standardization, and upkeep for every PR. Invoked by oc-git-ops before PR creation and by release flows before release PRs. Use for /oc-docs, /oc-docs pr, "generate the PR docs", "update README", "standardize docs", "refresh product documentation", "write PR body docs", "post a PR docs comment", "docs upkeep", changelog/ADR/readme drift, or any request where implementation changes need reader-facing documentation. Catalog drift (generated catalogs out of sync with source) is oc-repo-ops.

Governed behavior improvement: reflect on recurring failures, propose rules, evaluate task outcomes and review adoption. Use for /oc-evolve, what keeps going wrong, propose a workflow improvement, or evaluate a learned rule.

Multi-container / orchestration deployment operator for self-managed infrastructure. Declares topology (containers/services × target environment), provisions infra with the right IaC tool (Terraform/OpenTofu when it fits, else Ansible/cloud-init/k8s-manifests/ Helm/Nomad/Compose), rolls the fleet with a rollout strategy, verifies fleet-wide health, and operates day-2 (scale/drain/replace/rollback). Specifically lands the modules oc-modularize-ops carves out of a monolith. Use for /oc-fleet, "deploy multiple containers", "kubernetes", "terraform", "orchestrate containers", "on-prem deployment", "deploy to VMs", "self-managed infra", "container fleet". Complements oc-deploy-ops (single-app managed PaaS): managed app → deploy-ops; multi-container/self-managed/IaC → fleet-ops. Trigger on multi-container / IaC / self-managed deployment.

Git workflow: branch, commit, PR, merge, sync, release tag. Chains to (when you invoke it): oc-bug-check before every commit and the oc-docs-forge → oc-repo-ops pre-PR gate before every PR. Owns the release tag that oc-release-ops hands off. Use for /oc-git, /oc-commit, /oc-pr, /oc-push, /oc-git-sync, /oc-merge, /oc-git-release, "commit this", "push to git", "create a PR", "merge PR 123", "tag the release", "sync to repo". "Commit and open a PR" is /oc-git-sync (branch → commit → push → PR); /oc-pr only drafts the PR description. Not the desktop app's Auto-fix or CI-monitoring settings.