Run extended multi-agent reconnaissance sessions. Use when asked to brainstorm deeply, explore ideas from multiple angles, or generate a structured recon document.
Triage-cache hygiene and "what's next?" queue selection -- the agent-facing playbook for syncing the triage cache, classifying candidates, presenting a ranked queue, walking…
Prüft das Verhältnis von vertraglicher und deliktischer Haftung: Konkurrenz, Anspruchskumulation und Verjährungsunterschiede im BGB BT.
Prüft das Verhältnis von vertraglicher und deliktischer Haftung: Konkurrenz, Anspruchskumulation und Verjährungsunterschiede. — from Klotzkette/claude-fuer-deutsches-recht
Agent responsibilities and hard boundaries. Load when determining which agent should act or checking role violations.
Eine A2A-Agentenkarte (.well-known/agent.json) als Manifest entwerfen, das Agentenfaehigkeiten, Skills, Authentifizierungsanforderungen und unterstuetzte Inhaltstypen beschreibt.
Design framework-neutral agent and automation workflows before implementation. Use when choosing between Codex app automations, codex exec, Codex subagents, OpenAI Agents SDK…
Design evaluation workflows for agent, skill, prompt, and automation behavior before implementation. Use when choosing eval cases, graders, thresholds, regression runs, full-auto…
Expert photography prompt engineer specializing in crafting detailed, evocative prompts for AI image generation.
Design a Zoom MCP workflow for Claude. Use when deciding whether Zoom MCP fits a task, when planning tool-based AI workflows, or when separating MCP responsibilities from REST API…
Converge on a single recommended solution after brainstorming options. Use when you have multiple candidate approaches and need to analyze trade-offs, select one, and def — from…
Designlizenzvertrag prüfen oder entwerfen: Territory, Produkte, Exklusivität, Qualitätskontrolle, Unterlizenz, Royalty, Audit, Laufzeit, Kündigung und Insolvenz im Designrecht…
Desktop Commander is an MCP server that gives AI assistants terminal command execution, file system search, diff-based file editing, and process management capabilities.
Utilities and patterns for detecting execution environment (CI/CD vs local, network access, available ports, timeouts).
Prüft englische Vertragssprache bei deutschem Recht, Gerichtssprache, Commercial Courts, Übersetzungsregeln, Auslegung und False Friends im Gesellschaftsrecht Legal English.
One-command dev loop boot. Spins up portless (named HTTPS subdomain), emulate (stateful API mocks), the project's dev server, and an agent-browser session — all using the current…
Conception et implémentation d'agents IA autonomes avec outils et mémoire. Se déclenche avec "agent IA", "AI agent", "autonomous agent", "tool use", "function calling", "agent…
Phân tích task/issue và đề xuất 2-3 phương án implement với trade-off. Dùng multi-agent để giữ context sạch.
Code review wykonanej fazy/etapu przez multi-agent analysis.
Use when a reviewed plan is ready to implement — orchestrates subagent-driven execution with per-task review and a crash-safe progress ledger, or falls back to inline execution…
Multi-agent generowanie i filtrowanie pomyslow na ulepszenia projektu.
Conception de pipelines RAG (Retrieval-Augmented Generation). Se déclenche avec "RAG", "retrieval augmented", "vector database", "embeddings", "knowledge base", "Pinecone — from…
Create or update agent skills following the agent skill specification. Use when user asks to create a new skill or update an existing skill.
Install and configure Flutter SDK. Use when setting up a Flutter development environment.
Perform git partial merges (checkout specific folders from another branch) and squash merges (clean single-commit integration) to selectively integrate changes across branches.
Install AI code agent CLI tools including claude-code, gemini-cli, codex, and github copilot-cli. Use when setting up AI coding assistants or when the user asks to install an AI…
Add and manage Model Context Protocol (MCP) servers for AI agents, including transports, scopes, and config files.
Install and configure Node.js, npm, and pnpm using nvm. Use when setting up a Node.js environment.
Restore a project from 99-archive, a remote git repo, or a local codebase back to the workspace root, including reconstructing missing docs, stages, and sprints.
Review and refine MCP skill descriptions to follow the agent skill specification, and record approved overrides in dev-swarm/mcp_descriptions.yaml.
Create custom slash commands for popular AI agents (Claude Code, Codex, Gemini CLI). Use when user asks to create slash commands, custom commands, or reusable prompts for AI agent…
IMPLEMENT VueUse composables for browser APIs, event handling, and performance optimization. Add keyboard shortcuts, local storage, clipboard functionality, drag-and-drop — from…
IMPLEMENT VueUse composables for browser APIs, event handling, and performance optimization. Add keyboard shortcuts, local storage, clipboard functionality, drag-and-drop — from…
MUST be loaded before working with any Skill. Covers creating, building, reviewing, assessing, checking, auditing, evaluating, updating, modifying, and improving skills.
Explain and activate anti-hall's optional DevSwarm integration — the hivecontrol reference KB, the workspace-tier orchestration doctrine (a Primary's top fan-out tier is a child…
Comprehensive diagnostic tool for troubleshooting OADP/Velero backup and restore problems with automated checks and recommendations. — from majiayu000/claude-skill-registry
Diagnoses RAG system failures by classifying queries as factual-lookup-safe vs. relational-temporal (where RAG breaks).
Prüft Dienstvertrag, freie Dienste, Geschäftsbesorgung, Behandlungsvertrag, Dokumentation und Aufklärung.
Prüft, wie Dienst- oder Werkvertragskonstruktionen statusrechtlich wirken und wo sie täuschen im Sozialversicherungsstatus Prüfer.
Methodology for categorizing changes, assessing risks, and creating summaries from any changeset.
GKV-Leistungsanspruch auf DiGA (§ 33a SGB V): Verzeichnis, Verordnung, Freischaltung, Erprobungsphase und Nutzenbewertung durch BfArM im Krankenkassen-/Krankenversicherungsrecht:…
A strict binary communication protocol for high-density, agent-to-agent interactions.
Proof-based orchestration discipline for spec-compliant multi-agent systems. Five layers: DECOMPOSITION, COMPREHENSION, VERIFICATION, ENFORCEMENT, ACCOUNTABILITY.
Expert in combinatorics, graph theory, discrete probability, and algorithms with applications to computer science — from majiayu000/claude-skill-registry
Create screenshots, images, and visual tests for documentation. Use when you need to capture UI screenshots, generate visual assets, create test captures, or update documentation…
Render a PR-review film — a pull request reviewed the way a principal engineer would, with the load-bearing 5% surfaced, the trade-off named, and a verdict.
Generate a markdown report documenting codebase changes from the current session — files added, modified, deleted, and a summary of what was done.
Dokumente in ueberlappende Token-Chunks aufteilen fuer RAG-Pipelines und LLM-Kontextfenster. Zero Dependencies.
Use when creating or editing documents (DOCX, PDF, XLSX, PPTX) that need professional output. Adds visual verification, typography hygiene, and formula patterns to the do — from…
Build complete document knowledge bases with PDF text extraction, OCR for scanned documents, vector embeddings, and semantic search.
One-off repository documentation reseed for backing up existing docs, configuring agent discoverability, rebuilding Agent-first docs from old docs and current code, and pruning…
Hierarchical machine-readable documentation - root CLAUDE.md with module index, per-module CLAUDE.md for significant modules
Apply Domain-Driven Design patterns. Use when modeling complex business domains, defining bounded contexts, or designing aggregates.
Foundational layer beneath PDE. Governs eight-strata substrate (ontology, lineage, constellation, gap-map, agent-fleet, production-stack, internal-magnet, external-contribution)…
Price a proposed multi-agent fan-out before launching workers. Use when a packet, goal fleet, or hand-written plan would run several agents over declared file trees and you need…
Validation gate for freshly written code — run two independent reviews (codex CLI + a Claude review subagent) over the same scoped diff, then empirically vet every finding against…
Retrieve past closed/archived DPD subgraphs whose FTS5 index matches a query, then distill selected results into graph-candidate proposals.
Externally verify a DPD edge that claims a logically-necessary implication (layer='necessary'), using a context-stripped prompt so an independent verifier judges the implication…
Use when queuing, reviewing, editing, opening, or sending email drafts requested by organization teammates, including Slack @agent-native intake.
Unterscheidet Drag-along, Tag-along und Piggyback Rights mit Triggern, Mehrheiten, Minderheitenschutz, Vollzug und deutscher Dokumentenlogik.