Актуализация CLAUDE.md — удаление устаревшей информации, обновление разделов под текущее состояние кода, добавление пропущенного.
Update the repo-local review-pr-local and review-spec-local companion skills using human feedback left on pull request conversations.
核心 HRIS Repo Wiki 的派生同步能力。由 submit-knowledge 在源知识 commit 后自动调用，也可在用户明确要求“更新 Repo Wiki”“同步 Wiki”“刷新知识卡片”时单独使用；通过公开 Git 与文件协议增量维护 .qoder/repowiki 和 .agent-wiki，不调用 Qoder 私有…
Synchronizacja KFG między urządzeniami (Windows/Android). Triggers: sync KFG, updatekfg, zaktualizuj — from general/ai-tooling
Use when a learning, new skill, rule improvement, or bug fix from a consumer project should be contributed back to the shared agent-config package.
Bauleiter Urhebervertrag: Einraeumung von Nutzungsrechten §§ 31 ff. UrhG, Bestimmtheitsgrundsatz, angemessene Verguetung § 32 UrhG, Auskunftsrecht § 32d UrhG.
Track and analyze US government shutdown liquidity impacts by monitoring TGA (Treasury General Account), bank reserves, EFFR, and SOFR data from FRED API.
Expose agent capabilities and route tasks across independent agent runtimes with the Agent2Agent protocol.
Provides knowledge about acpx CLI for agent-to-agent communication. Use when user asks about acpx commands, ACP protocol, agent sessions, prompt queueing, or scriptable agent…
Start with cheap static fetches, escalate to a browser only when needed, validate findings, and turn the result into a production-ready scraping approach.
Use the Apify MCP server to let MCP-compatible agents run Apify Actors for structured extraction from search, maps, ecommerce, social platforms, and arbitrary websites.
Compose, test, and hand off visual AI-agent flows in Flowise when the work needs inspectable orchestration instead of ad hoc prompting.
【大型代码库分析专用】当需要分析整个项目架构、识别代码模式、追踪功能实现、梳理模块关系时必须使用本技能。触发关键词：分析整个项目/代码库、架构梳理、模块划分、代码模式识别、功能追踪、全局扫描。本技能通过 Gemini CLI 快速扫描完整代码库，提供 AI 驱动的架构洞察和代码分析，大幅节省手动探索时间。仅返回原始分析结果，不做二次解读。
Put a governed gateway in front of MCP, A2A, REST, and gRPC tools so agent calls can be discovered, routed, observed, and controlled.
Run ACP-compatible agents such as Claude Code, Codex, Gemini CLI, OpenCode, and custom agents from inside Obsidian notes and vault context.
. Optional: To view different results, adjust the prompt, model, or parameters, and click Submit. Learn more about prompting strategies.
Build and run repeatable AI agent workflows in Sim by composing agents, tools, triggers, and integrations on a visual canvas.
Parses a user agent string and returns structured information about the browser, OS, device, and bot status.
Routes repository-memory work through the layered agent-ready model when working with AGENTS.md, CLAUDE.md, monorepos, docs, skills, agents, hooks, CLI/MCP decisions,…
Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task.
Routes dev tasks into the forge planning workflow. Checks whether brainstorm, writing-plans, executing-plans, or subagent-execution should run before any code is touched.
Use when legacy prompts or old framework sessions refer to the pre-rebrand Galyarder Agent Framework operating guide and need the modern equivalent behavior.
Run the `gemini` CLI in headless mode for one-off prompts, model-directed Gemini tasks, structured output capture, and follow-up messages against prior Gemini sessions.
Use when starting feature work that needs isolation, before executing implementation plans, or before dispatching sub-agents in a jj (jujutsu) repository.
OpenAI SDK development with GPT-5 family, Chat Completions, Responses API, embeddings, and tool calling. Use for AI-powered applications, chatbots, agents, and semantic search.
Use when user has complex multi-agent workflows, needs to coordinate sequential or parallel agent execution, wants workflow visualization and control, or mentions automating…
Dispatch and validate background OpenCode work through taskferry's AXI CLI inside subagent-driven-development.
Store and retrieve durable facts from the Mem0 vector-memory MCP. Use at session start to recall task-relevant memories, and whenever you learn a durable user- or domain- — from…
Browser automation via webctl CLI in Claude.ai containers with authenticated proxy support. Use when users mention webctl, browser automation, Playwright browsing, web sc — from…
Draft CHANGELOG entries from git log via the pm-changelog-curator sub-agent. Dispatches natively on Claude Code with the pm-skills plugin (invokes @agent-pm-changelog-curator); on…
Run adversarial review on a PM artifact via the pm-critic sub-agent. Dispatches natively on Claude Code with the pm-skills plugin (invokes @agent-pm-critic); on non-Claude clients…
Walk the guided release runbook (6 gates G0/G1/G2/G2.5/G3/G4) via the pm-release-conductor sub-agent.
MCP server optimization and transport layer enhancement for claude-flow v3. Implements connection pooling, load balancing, tool registry optimization, and performance monitoring…
Aiuta a vendere tutte le notti disponibili di una casa vacanze a Roma. Genera annunci ottimizzati per Airbnb/Booking, strategie di pricing dinamico, contenuti marketing — from…
Aiuta a vendere tutte le notti disponibili di una casa vacanze a Roma. Genera annunci ottimizzati per Airbnb/Booking, strategie di pricing dinamico, contenuti marketing — from…
Übernimmt Daten aus einem alten Vertrag in eine neue Vorlage, erkennt Altlasten, veraltete Klauseln und abweichende Parteien- oder Objektangaben.
Spezialfall Rahmenvertrag im Konzern anpassen ohne Aenderung der Substanz: typische Stellen wie Vergueng, Laufzeit, Liefermenge.
Validation agent that validates plan tech choices against current best practices — from majiayu000/claude-skill-registry
Validation agent that validates plan tech choices against current best practices — from majiayu000/claude-skill-registry
Validation agent that validates plan tech choices against current best practices — from majiayu000/claude-skill-registry
Turn YAML runbooks into auditable agent actions with validation, dry-runs, destructive-step approval, and optional MCP exposure.
Use when you have multiple open PRs and want to validate them all (CI, reviews, code quality) and plan a safe merge order.
\"Validate MCP tool JSON schemas and optionally test input against schemas. 驗MCP工具JSON綱要，可測輸入合規。 Use when: validate mcp schema, check tool schema, test schema input, mcp json…
Use when reviewing OpenAI API usage, answering questions about OpenAI endpoints, or validating implementations against the official API specification.
Lean value stream mapping for identifying waste and optimization opportunities. Creates current/future state maps with cycle time analysis and improvement recommendations.
Install all Vanguard Frontier Agentic Codex agents and companion skills into the current user's ~/.codex home after adding or installing the plugin marketplace.
Git-based persistent memory system for AI agents. Agents inherit full context across sessions via markdown brain files in models/public/.
Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits — from wrsmith108/varlock-claude-skill
Start a multi-agent coding team for a hard challenge. Use when a problem is too large for a single agent.
Vector database selection, embedding storage, approximate nearest neighbor (ANN) algorithms, and vector search optimization.
Create your RAG skill in one prompt, then learn to improve it throughout the chapter — from majiayu000/claude-skill-registry
Vector database expert for embeddings, similarity search, RAG patterns, and indexing strategies
Handles vector databases for efficient storage and querying of high-dimensional vectors in AI/ML applications.
Audit Vector DB coverage -- compares the live filesystem manifest against the ChromaDB index to identify coverage gaps.
Removes stale and orphaned chunks from the ChromaDB vector store for files that have been deleted or renamed.
Ingests repository files into the ChromaDB vector store. Builds or updates the vector index from a manifest or directory scan using ingest.py.
Interactively initializes the Vector DB plugin. Guided discovery asks which folders to index, confirms the manifest, then scaffolds vector_profiles.json for high-performance…
Vector database operations — Pinecone, Weaviate, Qdrant, ChromaDB. Indexing, querying, filtering, and managing
Embedding strategies, ANN algorithms, hybrid search, RAG chunking strategies, and reranking for semantic search and retrieval.
Semantic search skill for retrieving code and documentation from the ChromaDB vector store. Use when you need concept-based search across the repository (Phase 2 of the 3-phase…