劳动用工回复草稿工作流，用于把劳动法律与用工管理问题整理成可复核、可追溯、可转发的简短答复文本。Use when：律师、法务、HRBP 或合规同学需要回复业务、管理层或客户的劳动用工问题，并希望输出“结论 + 依据 + 风险提示 + 待复核点”。NOT…
北大法宝原生 MCP 的法规/精准法条检索 Skill。当前本机已配置 `law-keyword`（检索法律法规-关键词）和 `fatiao`（精准查找法条-关键词），不得假定 `law-semantic`、`law-recognition` 等旧 MCP 可用。Use…
使用 `semantic-nlsql` 做跨库语义检索与综合法律资料召回。Use when：用户问题同时跨法规、案例、法条或多类材料，希望先用一次自然语言检索拿到综合候选结果。NOT for：只查单一法规、只查单一案例、已知法规名加条号的精准查询，以及未完成 `serverPaths.semantic-nlsql`…
Plandex is an open-source terminal-based AI coding agent designed for large projects and complex tasks.
Skip agent-declared MCP servers when strict plugin-only mode is active unless the agent is admin-trusted, keeping the session secure.
Gestion de pools de sous-agents pré-instanciés pour performance et réutilisation. Se déclenche avec "pool agent", "agent pool", "pool de sous-agents", "pre-allocated agen — from…
Adversarial, Multi-Agent Career Knowledge Base & Resume Pipeline. Usage: /praxis (ingest), /praxis (add knowledge), /praxis (generate tailored resume)
Describe an agent in `agent_spec.yaml`, run deterministic prompt-injection analysis, generate mitigations, and validate defenses before rollout.
Capture coding-agent sessions, compress the useful decisions and context, and inject relevant memory into future runs so long-running repository work does not restart cold.
Use Claude Mem to capture Claude Code sessions, compress the useful context, and re-inject relevant memory so future coding-agent runs start with project-specific continuity.
Use Context Mode when a coding agent keeps burning context on large tool outputs or loses its place after compaction.
Render an AI coding agent's plan as an interactive flowchart so a human can inspect dependencies, attach context, choose branches, and approve execution before code changes begin.
Unified proactive UX: Interactive Decision Options + Guardian QA Gate + Post-Task Suggestions. Giúp agent đưa options khi cần user input, double-check kết quả trước khi trả, và…
Orchestrator for all 7 Laws of AI Agent Discipline. Walks an agent-emitted recommendation list top-to-bottom under the 7 Laws — restate, route per item, verify before advancing,…
Give coding agents one promptable workflow surface for OCR, extraction, redaction, form filling, conversion, and signing across document-heavy tasks.
Govern Cursor SDK local, cloud, self-hosted, and subagent coding runs before they create branches or PRs.
claude-plugin 프로젝트 개발 가이드라인, 레퍼런스 패턴, 프로젝트 구조 조회. Use when Claude needs to (1) Look up development principles (P1-P4, DRY, KISS, YAGNI, SOLID), (2) Find reference patterns for…
Entwerfe einen Projekt-basierten Lern (PBL) Auftrag mit einer Fragestellung, Meilensteinen und Beurteilungs-Kriterien.
Comprehensive framework for analyzing, creating, and refining prompts for AI systems. Use when creating prompts for Claude, ChatGPT, or other language models, improving e — from…
Transformiert Anforderungen in Best-Practice Prompts nach Claude 4.x Standards (Dezember 2025). Basiert auf: - Nate B.
Transformiert Anforderungen in Best-Practice Prompts nach Claude 4.x Standards (Dezember 2025). Basiert auf: - Nate B.
Package prompt, identity, and runtime constraints into one explicit handoff so child agents start with the right context and no accidental leakage.
Transforms user prompts into optimized prompts using frameworks (RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE, RISE, STAR, SOAP, CLEAR, GROW)
Expert in designing, optimizing, and evaluating prompts for Large Language Models. Specializes in Chain-of-Thought, ReAct, few-shot learning, and production prompt management.
Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, or debug age — from…
Use when managing prompts in production at scale: versioning prompts, running A/B tests on prompts, building prompt registries, preventing prompt regressions, or creating eval…
Оценка и оптимизация промптов по методологии PQS и экономике API-вызовов LLM. Рассчитывает токены, стоимость вызова, вероятность retry и выдаёт переписанный промпт с…
Prompt-engineering expertise for designing test cases, edge cases, adversarial inputs, and iterating on prompts based on eval results
Expert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who collaboratively crafts high-quality prompts through flexible dialogue.
Analyse et améliore un prompt existant pour obtenir de meilleurs résultats avec un LLM. À utiliser quand l'utilisateur a un prompt qui ne donne pas les résultats voulus o — from…
Comprehensive reference for prompt engineering patterns and techniques. 提示工程模式與技術全覽。 Use when: selecting prompting strategy, applying zero/few-shot or CoT patterns, structuring…
Flags prompt-engineering bugs in user-supplied prompts without rewriting them. Use when the user says "lint my prompt", "review this prompt", "improve this prompt", "what's wrong…
Conçoit des system prompts robustes pour applications, agents IA ou chatbots personnalisés. À utiliser quand l'utilisateur développe un chatbot, un agent ou une app utili — from…
Optimisation systématique des prompts d'agents pour améliorer performance et fiabilité. Se déclenche avec "optimiser prompt agent", "agent prompt", "améliorer mon agent" — from…
prompting_skill — Best Practices für Prompt-Engineering mit aktuellen Claude-Modellen. Trigger: Prompt schreiben/optimieren.
Agent governance skill for MCP tool calls — Cedar policy authoring, shadow-to-enforce rollout, and Ed25519 receipt verification.
Audita, clasifica y elimina selectivamente memorias almacenadas. Cubre la enumeración y clasificación de memorias por tipo/antigüedad/frecuencia de acceso, detección de…
High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, o — from…
High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, o — from…
Create PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents, creating chat systems, or integrating LLMs with…
企查查官方 CLI — 企业工商、风险、知识产权、经营信息一站式查询。输入企业名称即可调用 67 个 API 获取注册信息、股东、高管、失信、行政处罚、专利、招投标、融资、舆情等全维度企业数据。触发场景：查企业、背调、尽调、风险排查、企业画像、商机分析、企业信用评估、供应商审查。使用 agent-browser 补充高管履历和地方互动等互联网信息。
An official Qdrant MCP server implementation that provides semantic memory capabilities for AI agents.
Qdrant Operations — управление коллекциями Qdrant, sparse vectors, snapshots. ИСПОЛЬЗУЙ когда создаёшь/настраиваешь коллекции Qdrant, мигрируешь с ChromaDB, настраиваешь named…
AI agents as force multipliers for quality work. Core skill for all 19 QE agents using PACT principles. — from proffesor-for-testing/agentic-qe
Use Fabric RTI MCP when an agent needs tool-callable access to Microsoft Fabric Real-Time Intelligence services such as Eventhouse, Eventstreams, Activator, and Map instead of…
Connect MCP-compatible agents to Neo4j so they can inspect graph schemas, run Cypher queries, manage graph memory, and operate Aura instances from chat.
Fast single-pass writing review against Ben Church's writing standards. Use when the user asks to "quickcheck", "quick review", "fast check", "quick edit", "scan my writing", or…
Use when the user asks to design RAG pipelines, optimize retrieval strategies, choose embedding models, implement vector search, or build knowledge retrieval systems.
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API.
RAG-grounded code generation with source citations. Triggers on: grounded code, ground this, cite sources, show me with sources, how do I with attune, reference attune docs,…
Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.
Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this…
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HN — from…
Hybrid search combining semantic and keyword retrieval for RAG pipelines. Implement BM25 + dense vector search with fusion strategies.
Design and implement Retrieval-Augmented Generation systems — chunking strategy, embedding selection, vector store setup, retrieval pipeline, re-ranking, and evaluation
RAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval optimization.
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search.
Интеграция RAG (Retrieval Augmented Generation) с xAI Grok Collections и Google Gemini. Используй этот skill когда нужно добавить AI-чат с базой знаний, настроить RAG систему,…
Build RAG (Retrieval-Augmented Generation) knowledge bases for businesses — turn documents, SOPs, policies, product manuals into AI assistants that answer questions accurately.
Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config.