创建、编辑、诊断并验收说明对象组成、连接、流程、状态、时序、接口或因果机制的技术图解与工程文档。用于说明/培训图、系统与网络拓扑、流程与 SFC、电气/仪控图、机械剖面、科学机制图及其可编辑原生源；按用途与 assurance 区分说明、培训、维护和受控工程声明，不用于以数值规律为主的数据图、保留真实地理位置的地图、产品工作台或参数仿真。

海岚旅行线上咨询与预订服务标准作业程序（HL-CS-SOP-01 V3.4）：全程约束，接入分流、需求采集与确认、产品匹配、报价、确认与占位、方案 PPT 制作质检与交付、后续告知七个阶段，以及投诉、超范围、团队三个分支。在线顾问每次接待都按此执行。

Assess a produced spec or spec bundle as black-box evidence of outcome orientation and PDLC readiness. Use when a CTO, VPE, or AI adoption leader wants to improve a spec-driven harness from its outputs, separating current-spec repairs from reusable workflow changes. For white-box inspection of a harness repository or agent configuration, use pdlc-harness-readiness.

Adopt a workflow that already exists — GitHub Spec Kit, Kiro, a bespoke prompt/script/cron harness, Claude Code or Codex skill libraries, a Jira/Linear tracker, or an n8n/Temporal automation — and map it into a definition of workflow without rewriting what works. Use when an organisation already has agentic or process machinery and wants it made flow-driven, when documented and actual process have drifted apart, or when deciding whether to wrap, extend, or retire an existing harness. Produces the mapped workflow plus a delta report. Part of the flow-driven family.

Identify the value streams an organisation actually runs — operational (a request stream with someone waiting) and development (building something that did not exist) — and choose which one to make agentic first, with a scored, reversible recommendation. Use before defining any workflow, when an org asks "where should we apply AI/agents", when an agentic programme has produced demos but no change in outcomes, or when picking the next stream after the first one is running. Part of the flow-driven family.

Search and inspect external sources for product, design, technical, or comparative research; verify provenance and turn findings into decisions. Use for requests to investigate online, research X posts or demos, compare approaches, or deepen a research task. Complements a research orchestrator without taking over its state or stop conditions.

Deep code review of the branch you are standing on, before it becomes a PR. Scope is merge-base..working-tree, so it covers commits, staged and unstaged changes together. Runs the same review lanes as review-pr — implementation, verification, approach, security — against the local checkout through the sandbox CLI, and saves a draft to ~/.nx-branch-reviews/<branch>.md. Use when asked to review "this branch", "my changes", or work that is not yet on GitHub.

Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also triggers for Next.js apps needing memory-augmented AI. DO NOT TRIGGER when: user asks about direct Python/TS SDK calls without Vercel (use mem0 skill), or CLI terminal commands (use mem0-cli skill).

VS Code theming, color tokens, widget styles, focus indicators, and high-contrast theme support. Use when registering colors, styling widgets with theme tokens, or ensuring HC/focus compliance.

VS Code CSS conventions, file organization, class naming, standard sizes, SplitView/Grid layout, scrollable content, responsive layout, and text overflow/ellipsis patterns. Use when writing CSS, building layouts, or fixing text truncation issues.

How to give the person a small interactive page in the drive: a board, checklist, queue, form, table or dashboard. Read it when the ask is for something to look at and touch rather than a reply. Covers picking a starter with create_app, the app folder layout, and the window.agenta bridge for hand-written apps.

当用户询问《纳瓦尔宝典》(The Almanack of Naval Ravikant) 相关内容，或在以下领域寻求建议时调用: 财富构建(怎么赚钱/股权期权/杠杆/副业与职业定位/时薪与外包决策)、判断与决策(重大选择纠结/心智模型/打工vs创业)、 幸福与心智(欲望与焦虑/接受与内耗/冥想/刷手机上瘾/愤怒与期望/攀比妒忌)、人生哲学(生命意义/该不该信玄学/诚实沟通/选朋友圈子/怎么读书学习)。 不适用于: 具体投资标的与选股、临床心理治疗、急性危机(先求助专业人士)。 Triggers: 纳瓦尔/Naval/纳瓦尔宝典/致富/财富/幸福/判断力/冥想/读书/人生意义

Track validated Codex Security findings in Linear, Jira, GitHub issues, or draft GitHub security advisories. Supports issue batches, duplicate checks, and reviewed writes. Do not use for scans or fixes.

Triage and archive accumulated Codex conversations without losing wanted work. Use when cleaning up old Codex threads, deciding which conversations still need attention, or resuming a large conversation cleanup. Do not use for ordinary backlog capture, feature implementation, or issue-tracker cleanup.

Audit a test file or suite; produce a severity-ranked diagnostic report. ALWAYS USE for tests that verify nothing, missing/tautological assertions, swallowed/broad exceptions, flaky/order-dependent tests, duplication, or magic values. Polyglot. DO NOT USE for direct edits: writing-mstest-tests owns supplied MSTest assertions/attributes/lifecycle; code-testing owns new tests. Exclude running tests, migration, assertion metrics (assertion-quality), raw .NET coverage collection (run-tests), non-.NET coverage collection/analysis (native tooling), project-wide .NET coverage/CRAP (coverage-analysis), named-target .NET CRAP (crap-score), behavioral/pseudo-mutation gaps (test-gap-analysis), test-mix/ happy-vs-error classification and trait distributions (test-tagging), or the testsmells.org catalog (test-smell-detection).

Diagnose and fix concrete MSBuild property defects in projects and existing shared-file hierarchies. USE FOR: conditions, defaults, append versus overwrite, last-write-wins values, OS/TFM checks, portable paths, normalization, and reviews centered on those property defects. Property defects in Directory.Build.* remain in scope, including overwritten values across parent/child imports and conditions that run before TargetFramework is set, even when the fix changes import order or moves a property group to .targets. DO NOT USE FOR: placement-only or import-only requests with no concrete property defect, such as discovering shared files or choosing which file owns a target or customization (use directory-build-organization); item operations; target structure; broad reviews without a concrete property defect; non-MSBuild work.

Rapidly triage an incoming NDA and classify it as GREEN (standard approval), YELLOW (counsel review), or RED (full legal review). Use when a new NDA arrives from sales or business development, when screening for embedded non-solicits, non-competes, or missing carveouts, or when deciding whether an NDA can be signed under standard delegation.

Trigger: update skills, skill registry, actualizar skills, after skill changes. Index available skills by trigger and path.

Use this skill when the user asks to create, modify, debug, validate, or scaffold a MoviePilot local plugin. Covers version-aware V3/V2 plugin development, _PluginBase implementations, package.v3.json/package.v2.json/package.json metadata, plugins.v3/plugins.v2/plugins source layout, PLUGIN_LOCAL_REPO_PATHS local plugin sources, plugin APIs, Vuetify JSON forms/pages/dashboards, Vue module federation remote components, get_render_mode, get_sidebar_nav, plugin sidebar pages, get_agent_pets assistant avatars, commands, services, workflow actions, agent tools, and local install/reload flows. Also use for Chinese requests mentioning 编写插件、本地插件源, 插件开发, V3插件, V2插件, 插件市场, 本地安装插件, 插件热加载, 前端联邦, 侧栏入口, Vue插件页面, 助手形象.

Use when the user asks to push the current branch — confirms a first-time upstream and a diverged main, and refuses force pushes without explicit authorization. Not for committing or reviewing. Self-contained — execute the inlined steps directly.