Nutze diesen Skill für Phaser Input: Pointer, Maus, Touch, Tastatur, Drag-and-Drop, Hit Areas und Interaktionszustand.
GPT Pro(웹 전용·API 없음 — 현 시점 최신 플래그십 모델의 Pro 추론)를 Claude Code 안에서 활용한다. 사용자가 검토/수정/문제/리뷰/의견을 요청하면, 의도를 파악해 repomix로 관련 코드만 정밀 패킹한 뒤 구독 ChatGPT Pro에 투입하고 분석을 회수해 반영한다.
InsForge API for backend and cloud infrastructure. Use when the user mentions InsForge, agent-native backends, cloud infrastructure APIs, or InsForge projects.
Agents Checking Agents — multi-agent orchestration with cross-validation using Claude Code Agent Teams and a cross-provider Codex/GPT-5 judge for bias-free final verdicts — from…
Checkliste Eroeffnungsantrag § 13 InsO: zustaendiges Gericht, Glaeubigerliste, Vermoegensverzeichnis, Erklaerung Geschaeftsleitung.
Belegpaket gegen negative Auskunfteieinträge: Beschlüsse, Registerauszüge, Erledigungsnachweise, Löschfristen, Auskunft und Versandnachweis im Insolvenzrecht.
§ 13a InsO (Antrag zur Begründung eines Gruppen-Gerichtsstands) im Mandat prüfen: Normzweck, Tatbestand, Belege, Rechtsfolge, Fristen, Schnittstellen und sichere Quellenprüfung: §…
§ 14 InsO (Antrag eines Gläubigers) im Mandat prüfen: Normzweck, Tatbestand, Belege, Rechtsfolge, Fristen, Schnittstellen und sichere Quellenprüfung: § 14 InsO (Antrag eines…
§ 75 InsO (Antrag auf Einberufung) im Mandat prüfen: Normzweck, Tatbestand, Belege, Rechtsfolge, Fristen, Schnittstellen und sichere Quellenprüfung: § 75 InsO (Antrag auf…
§ 270a InsO (Antrag: Eigenverwaltungsplanung) im Mandat prüfen: Normzweck, Tatbestand, Belege, Rechtsfolge, Fristen, Schnittstellen und sichere Quellenprüfung.
§ 287 InsO (Antrag des Schuldners) im Mandat prüfen: Normzweck, Tatbestand, Belege, Rechtsfolge, Fristen, Schnittstellen und sichere Quellenprüfung: § 287 InsO (Antrag des…
§ 305 InsO (Eröffnungsantrag des Schuldners) im Mandat prüfen: Normzweck, Tatbestand, Belege, Rechtsfolge, Fristen, Schnittstellen und sichere Quellenprüfung: § 305 InsO…
§ 336 InsO (Vertrag über einen unbeweglichen Gegenstand) im Mandat prüfen: Normzweck, Tatbestand, Belege, Rechtsfolge, Fristen, Schnittstellen und sichere Quellenprüfung: § 336…
Vorab-Pruefung der Verrechnungsreihenfolge nach Paragraph 3a Absatz 3 EStG vor Insolvenzantrag oder StaRUG-Anzeige.
Insolvenzantrag-Maßnahmen durch Staatsanwaltschaft im Wirtschaftsstrafrecht: Anwendungsfall Staatsanwaltschaft hat Insolvenzantrag gestellt oder Vermögenswerte beschlagnahmt und…
Proxy OpenAI-compatible model traffic so operators can inspect prompts, detect risks, and enforce budget or policy controls.
Use Bull Board to add a protected dashboard for Bull and BullMQ queues so operators can inspect, retry, pause, clean, and debug background agent jobs.
Connect PDF Reader MCP when an agent needs source-backed PDF extraction with page evidence, visual crops, OCR provenance, tables, trust reports, and reviewable citations.
Use claude-code-system-prompts when you need the current extracted Claude Code system prompts, built-in tool prompts, or subagent prompts before building a compatible plugin,…
One-line install for dragoon. Detects supported coding agents (claude-code, codex, cursor, opencode, factory, kiro) and installs the skill pack into each. Multi-host on day one.
Add a Claude Code team scaffold with defined roles, stage gates, mandatory skills, blocking hooks, and Definition of Done checklists for app delivery.
Scaffold the full multi-agent workflow for a new project — AGENTIC.md, agent definitions, docs/context/ files, and hooks — in a single guided pass.
Use one manifest to reproduce agent setup across repositories so skills, prompts, plugins, and config stop drifting from machine to machine.
Load a Claude Code workflow plugin that adds project-oriented commands, specialist agents, skills, and hooks for planning, review, verification, commits, and pull requests.
Review and install only the Claude Night Market plugins needed for a specific Claude Code workflow, such as PR prep, code review, TDD gates, or spec-driven development.
Use when installing skills from a shared ai-agent-skills library repo. Inspect with `--list` first, prefer `--collection`, and preview with `--dry-run` before installing.
Use add-mcp when an agent needs to roll out, list, remove, or synchronize MCP server configs across multiple coding clients instead of hand-editing each config file separately.
Install and adapt Agency Agents' curated specialist role files so coding agents can switch into focused engineering, product, marketing, support, or operations workflows.
Install and activate specialized AI agent personas from Agency Agents when a coding or operations session needs a focused role, workflow, and deliverable standard instead of a…
Use Everything Claude Code to install curated skills, rules, hooks, and MCP configuration into Claude Code, Codex, Cursor, OpenCode, and related coding-agent harnesses without…
Install skills from github.com/oaustegard/claude-skills into /mnt/skills/user. Use when user mentions "install skills", "load skills", "add skills", "update skills", "ref — from…
Submit structured feedback about instar bugs, feature requests, improvements, or innovations worth sharing.
Structured outputs with Instructor. Extract typed data from LLMs using Pydantic models and validation. Use for data extraction, structured generation, and type-safe LLM responses.
Activate when: an insurance agent/agency must not skip licensing, disclosure, suitability, and replacement steps on a sale; 'am I compliant on this policy', selling/replacing a…
Use when you need to send a message to another Claude Code agent, broadcast to all agents, or when you receive a message prefixed with [@agentName].
Use when designing or implementing communication protocols between two or more agents in a workflow
Use when targeting International Conference on Autonomous Agents and Multiagent Systems (AAMAS) or deciding whether a computer-science manuscript fits this venue.
Entry point for Internet Court — the trust layer for agent-to-agent commerce. Use whenever an agent needs to transact with another agent or a paid service, or a user mentions…
Gather structured user input via web form. Use when you need multiple clarifying questions answered, collecting design mockups/images, or getting user decisions on implementation…
Formuliert Untersuchungsauftrag, Scope, Ausschlüsse, Governance und Eskalation so eng wie moeglich und so belastbar wie noetig. — from Klotzkette/claude-fuer-deutsches-recht
Connect agents to Monoscope so they can query logs, traces, metrics, monitors, and issues through stable JSON CLI output or MCP tools for incident triage.
Install and drive Google's Antigravity CLI (`agy`) as a non-interactive sub-agent. Use when orchestrating agy, running Antigravity agents from a script or sandbox, delegating a…
Use when you have 512-dimensional representation vectors output from ResNet18 encoders processing paired augmented ion images, and you need to prevent trivial solutions…
IPv6 is THE first-class citizen. All code, tests, documentation, and configurations MUST be IPv6-first. IPv4 MAY be added only for legacy support as a second-class citizen.
Datenschutz-Due-Diligence fuer Cloud-Vertraege. Sieben-Fragen-Diagnose: Cloud-Typ IaaS PaaS SaaS Anbietersitz Datenstandort Schlusselverwaltung Subprozessoren Zertifizierung…
SaaS-Vertrag mit AVV nach Art. 28 DSGVO und Transfer Impact Assessment als Bundle. Sieben-Fragen-Diagnose: Anbietersitz Datenstandort Datenkategorien Konzernverflechtung…
IT-Vertragsverhandlung SaaS Cloud Lizenz mit Schlichtungsklauseln und EU-ODR-Optionen: Anwendungsfall IT-Vertrag soll verhandelt werden und Streitbeilegungsklauseln muess...
Git-backed issue tracker for multi-agent coordination. Use when working with itack issues to: (1) View the project board and list issues (2) Create new issues with titles and…
Turn an agent's own failure — a premature stop, a false "done", a reward- hacked check, a missed file, a broken handoff — into a durable improvement to the harness (skills, rules,…
Use reflective search to improve prompts or text-configured agent components against a real eval set instead of manual prompt tweaking.
Bauleiter SaaS-Vertrag: Service Level Agreement, Datenverarbeitung Auftragsverarbeitungsvertrag, Mitwirkungspflichten, Verfuegbarkeit, Bonus-Malus.
Driving a Jardis workspace headless through `jardis mcp` — Tools as actions vs Resources as read-only, the Workspace to Schema to Aggregate to Process to Build to Code-read…
Advise on USING Jira well, not operating it: make the structural call — is this an epic, a story, a task, or a sub-task? — and diagnose why a Jira is a dread, then recommend the…
统一的 Jira 问题处理中心。提供：ensureConnected() 确保连接可用（MCP/curl 双通道 + 多源凭证 + 缓存）、getIssue() 获取完整 ticket 上下文（含图片分析）、writeBack() 回写结果到 Jira。被 autopilot/hotfix/feature 调用，所有 Jira 相关逻辑集中在此。
Defines how to write GitHub issues (tasks) for jiriki-labs/agentic-wallet: Polish body structure matching issues #1 and #2, epic-level granularity (roughly 3–5 issues unless the…
Genera le istruzioni passo-passo per impostare gli alert di lavoro su LinkedIn e Indeed a partire dagli intenti di ricerca del sistema Job Hunter (cartella searches/ nel repo).
Design and write any creative surface Suede ships — landing pages, brand surfaces, product and app UI, Apple iOS and App Store surfaces, dashboards, components, and creative…
Guide for creating CLAUDE.md files. Use when: user asks to create CLAUDE.md, document project, add project instructions, or mentions CLAUDE.md.
Install Gmail MCP for email operations. Use when user needs Gmail read/send capabilities.
Install Jina AI MCP for web scraping. Use when user needs Jina Reader for URL content extraction.