发现 AI Agent 技能

Treffer-Workflow zum Sanktionslisten-Screening nach EU-Sanktions-VOen (konsolidierte EU-Liste auf Basis VO (EU) 269/2014, 2580/2001, 881/2002, 833/2014, 2017/1509 u.a.) – Bereitstellungsverbot Art. 2, False-positive-Bewertung, Frostung von Geldern und wirtschaftlichen Ressourcen, Meldung an BMWK/Bundesbank/Zoll, Schnittstelle GwG-KYC (§§ 10 ff. GwG). Use when ein Geschäftspartner-Screening oder ein laufendes Re-Screening einen möglichen Treffer auf einer EU- oder nationalen Sanktionsliste ergibt.

4-Stufen-Prüfung der Ausfuhrgenehmigungspflicht nach VO (EU) 2021/821 – Güterklassifikation Anhang I, Einzelgenehmigung bzw. EU-Allgemeine Genehmigungen IIa–IIg, Catch-all Art. 4 (militärische Endverwendung) und Art. 5 (Cyber-Surveillance), BAFA-Antrag ELAN-K2 mit Endverbleibsdokumentation. Use when ein deutscher Exporteur Güter in ein Drittland liefern will und Listung, Genehmigungspflicht oder Catch-all-Risiko prüfen muss; berücksichtigt Vorrang länderspezifischer Sanktions-VOen (Russland VO 833/2014, Iran VO 267/2012, DVRK VO 2017/1509 u.a.).

Rechtliche Vollprüfung einer ordentlichen oder außerordentlichen Kündigung im deutschen Arbeitsrecht – KSchG (allgemeiner und besonderer Kündigungsschutz), § 102 BetrVG (BR-Anhörung), §§ 622 und 626 BGB (Fristen und wichtiger Grund), Sozialauswahl § 1 Abs. 3 KSchG, Sonderkündigungsschutz (MuSchG, BEEG, SGB IX, § 15 KSchG). Use when ein Arbeitgeber eine Kündigung plant oder ein Arbeitnehmervertretender eine empfangene Kündigung auf Klagewert prüft.

Erstellung und Prüfung eines Aufhebungsvertrags inkl. Sperrzeit § 159 SGB III, Schriftform § 623 BGB und steuerlicher Behandlung der Abfindung § 34 EStG. Use when ein Arbeitsverhältnis einvernehmlich beendet wird oder eine Sperrzeit-Risikobewertung benötigt wird.

Entwurf einer BAG-konformen Abmahnung im Arbeitsrecht – konkrete Schilderung der Pflichtverletzung, klare Verhaltenserwartung, ausdrückliche Sanktionsandrohung. Use when AG eine verhaltensbedingte Sanktion vor einer Kündigung dokumentieren muss oder AN die Wirksamkeit einer empfangenen Abmahnung prüft.

Prüfung und Durchsetzung von Auseinandersetzungsansprüchen ehemaliger LPG-Mitglieder bzw. ihrer Erben gegen die LPG-Nachfolgegesellschaft nach §§ 44 ff. LwAnpG vor dem Landwirtschaftsgericht – Anspruchsgrundlagen, Ermittlung des Auseinandersetzungsguthabens, Verjährung § 51a LwAnpG, Klagebefugnis, Verfahren nach LwVG/FamFG. Use when ein Mandant (Mitglied oder Erbe) Ansprüche gegen die LPG-Nachfolgegesellschaft (e.G., GmbH, GbR) geltend macht, ein Bescheid der Nachfolgegesellschaft angefochten werden soll oder die Verjährung zu prüfen ist.

systemd service 诊断 workflow：read-first 地查看 status、journal 与最近故障。

天气查询 workflow：通过 weather CLI 获取当前天气、指定日期天气或小时级预报。用户提到 weather、forecast、温度、降雨、体感或天气趋势时使用。

Python project workflow：dependency sync、targeted tests 与 lint。

日志与历史诊断 workflow：检查 recent logs、tool history、session transcript 与 error summary。

Hypo-Agent 运维 workflow：默认走 test-mode smoke，并对 service action 保持 guardrails。

只读 host inspection workflow：查看 CPU、memory、disk、port 与 process 状态。

GitHub CLI workflow：查看 pull request、issue、Actions run 与远程仓库状态。用户提到 GitHub、PR、issue、Actions、workflow run 或 gh CLI 时使用。

安全的 Git workflow：inspect status / diff / branch / history，并在用户明确要求时执行 commit 或 push。

浏览器自动化 workflow：打开网页、获取可交互 snapshot、点击、填写表单、截图与读取 JS 渲染内容。用户需要真实 browser interaction、DOM refs、页面操作或截图时使用。

持久 terminal session 管理。仅在需要跨多次调用保留 shell state 的场景使用，普通 one-shot command 优先 exec。

Reminder CRUD 与 scheduler integration：创建、列出、更新、删除与 snooze 定时提醒。

L2 structured memory：持久化并读取稳定的用户记忆、偏好与长期上下文。

受权限控制的文件读写与目录索引 backend。适合 document-oriented file read/write、目录扫描与 workspace 导航。

核心 shell execution backend。所有 CLI-based skill 的底层一次性 subprocess primitive。

多账号 IMAP 邮件扫描、分类、搜索与详情读取。适合 inbox refresh、mail search、detail inspect 与 proactive email workflows。

一次性临时脚本执行（Python / shell），可用时优先走 bwrap sandbox。适合多行代码、快速数据处理与临时计算。

远程设备 inspection：列出 device、抓取 screenshot、查看 process list。用户要监控或排查远程机器时使用。

读取与写入普通 Notion page / database。用户要在 Notion workspace 中 search、query、create 或 update 非计划通内容时使用。

读取和编辑 HYX 的 Notion Plan / 计划通；当用户要查看、添加或插入计划通日期事项时使用。

TrendRadar 主动资讯 workflow：结构化 query、summary 与 subscription push。用户要订阅、推送、跨多日检索或管理主题关注时使用。

查询 Hypo-Info 的今日资讯、topic search、AI benchmark 与 section browse。用户询问 news、trends 或 model leaderboard 时使用。

将 coding task 委托给 Hypo-Coder。用户请求 code change、feature implementation、bug fix 或 code review，且任务适合异步委托时使用。

通过 Tavily 执行 Web search 与 page reading。用户需要在线检索、事实核验或读取公开网页时使用。

Begleitung und Verteidigung des Sammelantrags GAP 2023–2027 – Direktzahlungen (Einkommensgrundstützung, Umverteilung, Junglandwirteprämie, gekoppelte Stützung), Öko-Regelungen, Konditionalität (GLÖZ 1–9, GAB), Sanktionsbemessung, Widerspruch und Klage. Statutory anchors: VO (EU) 2021/2115, 2021/2116; GAP-DZG; GAPInVeKoSG; GAP-KondV; GAP-IntegrV. Use when ein Betriebsinhaber den Sammelantrag vorbereitet, eine Bewilligung erhält, eine Kürzung/Sanktion verteidigt oder Widerspruch/Klage erwägt.

Prüfung der Genehmigungspflicht eines Verkaufs landwirtschaftlicher Flächen nach GrdstVG, der Versagungsgründe nach § 9 GrdstVG, des siedlungsrechtlichen Vorkaufsrechts nach § 4 RSG und der Anzeige- und Beanstandungspflicht bei Landpachtverträgen nach LPachtVG. Statutory anchors: §§ 2, 6, 9, 22 GrdstVG; §§ 4, 6 RSG; §§ 2, 4 LPachtVG; §§ 463 ff., 581 ff. BGB; LwVG. Use when ein Kaufvertrag über landwirtschaftliche Flächen genehmigt werden soll, das Vorkaufsrecht ausgeübt wurde, ein Landpachtvertrag anzuzeigen ist oder eine Beschwerde gegen einen LwG-Beschluss erwogen wird.

Capture useful learnings from the current Codex session and propose concise updates to AGENTS.md files. Use near the end of a session, or when the user asks to revise AGENTS.md, capture project instructions, record missing context, update Codex project memory, or save recurring commands, workflows, gotchas, testing approaches, environment quirks, or codebase conventions discovered while working.

Audit and improve AGENTS.md files in repositories. Use when user asks to check, audit, update, improve, or fix AGENTS.md files. Scans for all AGENTS.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "AGENTS.md maintenance" or "Codex project instructions".

Guides day-to-day work in Tuist-generated Xcode workspaces, including generation, build and test commands, and buildable folders. Use when working in a Tuist-generated project or when users mention `tuist generate`, `xcodebuild test`, or generated workspaces.

Debugs issues users encounter with Tuist-generated projects by reproducing the scenario locally, building Tuist from source when needed, and triaging whether it is a bug, misconfiguration, or something that needs team input. Use when users report generation failures, build errors after generation, or unexpected project behavior.

Use when writing, reviewing, or refactoring SwiftUI code for iOS or macOS, including state management, view composition, performance, Liquid Glass adoption, or Instruments `.trace` capture/analysis for hangs, hitches, CPU hotspots, or excessive view updates.

Scan Apple's SwiftUI documentation for deprecated APIs and update the SwiftUI skill with modern replacements. Use when asked to "update latest APIs", "refresh deprecated SwiftUI APIs", "check for new SwiftUI deprecations", "scan for API changes", or after a new iOS/Xcode release. Requires the Sosumi MCP to be available.

Expert guidance for Swift Testing: test structure, #expect/#require macros, traits and tags, parameterized tests, test plans, parallel execution, async waiting patterns, and XCTest migration. Use when writing new Swift tests, modernizing XCTest suites, debugging flaky tests, or improving test quality and maintainability in Apple-platform or Swift server projects.

Diagnose Swift Concurrency issues, refactor callback-based code to async/await, and guide Swift 6 migration when working with tasks, actors, @MainActor, Sendable, data races, thread safety, or concurrency-related compiler and linter warnings.

Use when you have a spec or requirements for a multi-step task, before touching code

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

Use when implementing any feature or bugfix, before writing implementation code

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when executing implementation plans with independent tasks in the current session

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector).

Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Compact the current conversation into a handoff document for another agent to pick up.

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

Prompt and workflow for generating conventional commit messages using a structured XML format. Guides users to create standardized, descriptive commit messages in line with the Conventional Commits specification, including instructions, examples, and validation.

Draft repository-compliant GitHub pull requests with the `gh` CLI. Use when Codex needs to inspect the current repository's PR template and lint rules, derive a PR from local changes, find related issues or precedent PRs, and create or update a PR with labels discovered from GitHub.

Randy's basic context - tools, projects, and setup. Use when Randy asks about his environment, projects, or technical setup.

Draft repository-compliant GitHub issues with the `gh` CLI. Use when Codex needs to inspect the current repository's issue templates and title rules, classify a request into the repository's supported issue types, and create or update an issue with labels discovered from GitHub.

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples.

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", or "switch to --preset".

Guides and best practices for working with Neon Serverless Postgres. Covers setup, connection methods, branching, autoscaling, scale-to-zero, read replicas, connection pooling, Neon Auth, and the Neon CLI, MCP server, REST API, TypeScript SDK, and Python SDK. Use when users ask about "Neon setup", "connect to Neon", "Neon project", "DATABASE_URL", "serverless Postgres", "Neon CLI", "neonctl", "Neon MCP", "Neon Auth", "@neondatabase/serverless", "@neondatabase/neon-js", "scale to zero", "Neon autoscaling", "Neon read replica", or "Neon connection pooling".

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user says "write copy for," "improve this copy," "rewrite this page," "marketing copy," "headline help," "CTA copy," "value proposition," "tagline," "subheadline," "hero section copy," "above the fold," "this copy is weak," "make this more compelling," or "help me describe my product." Use this whenever someone is working on website text that needs to persuade or convert. For email copy, see emails. For popup copy, see popups. For editing existing copy, see copy-editing.

Configure Better Auth server and client, set up database adapters, manage sessions, add plugins, and handle environment variables. Use when users mention Better Auth, betterauth, auth.ts, or need to set up TypeScript authentication with email/password, OAuth, or plugin configuration.

Use this skill to analyze the module dependency tree of an Odoo instance and generate a migration-priority report. Triggers on: 'module dependencies', 'dependency tree', 'migration order', 'module priority', 'which modules to migrate first', 'dependency levels'.

Draft or revise pull request titles and bodies with a concise standard format: summary, risk assessment, testing summary, testing checklist, and technical changes. Use when preparing a new draft or ready-for-review PR, opening a PR from a branch, updating an existing draft/open PR, reopening a PR, or when the user provides a GitHub PR URL/branch and asks for PR summary, risk, testing, or description text. New PRs should be draft by default unless the user explicitly asks to open them ready for review.

Build hipDNN with providers via the repository superbuild. Faster than standalone since providers build alongside hipDNN in a single CMake invocation. On Windows, auto-runs the wheel-based ROCm setup if not already prepared.

Run tests against an existing hipDNN superbuild. Supports per-component selection (hipdnn, miopen-provider, hipblaslt-provider, hip-kernel-provider, integration-tests), unit/integration scope, and gtest filtering. Handles Windows DLL PATH automatically.

Review a hipDNN pull request, branch, or local diff for correctness, API compatibility, provider behavior, resource management, code reuse, and testing coverage/quality. Uses local source/worktrees for cross-reference by default. Use when asked to review hipDNN code, review a PR, or assess whether a change is ready to merge.

Generate hipDNN operation boilerplate from a YAML config. Use when the user wants to add a new operation type to hipDNN, or generate descriptor/packer/unpacker code.

Use this skill to query, create, update, delete, export, or import records in any Odoo instance via MCP tools. Triggers on: 'search records', 'create record', 'update partner', 'delete record', 'unlink record', 'export data', 'import records', 'execute method', 'list models', 'list fields', 'get version', 'list profiles', 'odoo mcp tools'.

Use this skill to manage Odoo profiles and run data operations directly from the terminal using the odoo-mcp CLI. Triggers on: 'add profile', 'list profiles', 'test connection', 'search records cli', 'export records', 'import records cli', 'run mcp server', 'odoo-mcp command', 'delete records cli', 'unlink records'.

Generate complete character sprite sheets for the Claude Office Visualizer agents. Creates all animation frames (idle, walking, typing, handoff, coffee) with consistent character design across all sheets. Uses iterative approval workflow and reference-based generation for consistency.

Build MCP (Model Context Protocol) servers that give Claude new capabilities. Use when user wants to create an MCP server, add tools to Claude, or integrate external services.

Use when executing implementation plans with independent tasks in the current session

Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.

Expert instructions for the Windows Operations MCP server, covering PowerShell best practices, diagnostic workflows, and error handling.

Complete fullstack development mastery covering modern web architectures, automation tools, AI integration, and production deployment practices

Comprehensive MCP server development guide covering FastMCP 2.14.3 features, Anthropic standards, ecosystem integration, and production deployment across all agentic IDEs

Run a standalone code review on lilnas changes — correctness, testing, maintainability, project standards — plus conditional reviewers (kieran- typescript, julik-frontend-races, security, performance, api-contract, reliability, equations-security, adversarial, code-simplicity, previous- comments). Writes a numbered, severity-sorted, emoji-rich report with code snippets, fix options, trade-offs, a selectable summary list, and a recommendation to `REVIEW.md` at the repo root (any prior `REVIEW.md` is deleted first); the chat shows only the picker and recommendation so you can reply with issue numbers inline. Use before pushing a lilnas PR or any time the user types /lilnas-code-review. Fully self-contained — no dependency on /ce-code-review or the compound-engineering plugin.

Perform a comprehensive multi-agent parallel code review on git changes, acting as a senior staff software engineer. Reviews staged files if any exist, otherwise reviews unstaged files. Reads project documentation (README, docs/, package.json) to understand the type of software being reviewed, then selects and launches specialized reviewer agents in parallel (Frontend, Backend, Architecture, Security, DevOps, Design/UX, Testing) tailored to the project context. Consolidates all findings into a structured report with a severity-sorted action items list. Use when the user types /review, asks for a code review, or wants to review git changes.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.