Activate when a multi-agent orchestration goes wrong. Contains: recovery from `ValueError: Tool '' not found`, the full forbidden-tool reference for each specialist, retry…
Uses Agent SDK to deploy 3 parallel agents for client onboarding -- workflow auditor, tech stack mapper, and strategy drafter.
Universal multi-agent collaboration methodology for Claude Code. Model-tiered cowork + document-driven sync + self-evolution.
Decision frameworks and patterns for choosing and composing Claude Code components — skills, sub-agents, hooks, MCP servers, and slash commands — into effective multi-component…
Use when multiple Starlight agents need to collaborate on a related task — handles agent selection, task decomposition, dependency management, and result aggregation across the…
An advanced orchestration specialist that manages complex coordination of 100+ agents across distributed systems with hierarchical control, dynamic scaling, and intelligent…
Design the agent topology for a multi-agent feature and produce agent_topology.md. Use when eval_criteria.yaml declares multi_agent:true or when invoking /multi-agent-design.
|-. 面向需要multi agent dev v2相关能力的开发场景,提供结构化流程和配置指引. 该工具经过差异化增强,结合实际使用痛点进行了优化。Use。Use when 需要代码生成、编程辅助、调试测试、开发部署时使用。不适用于无明确技术栈的模糊需求。适用于独立开发者、企业团队和自动化工作流场景。
Generic Multi-Agent Dispatcher (English): Turns the main agent into a pure dispatcher that delegates all work to 5 persistent sub-agents via sessions_spawn.
Plan and document handoffs between specialized AI agents (foreman, workers, reviewers). Use for multi-agent workflows, subagent delegation, baton passes, or guild-style agent…
Run recoverable multi-agent long-task scheduling after the required launch review and authorization.
Используй когда Standard/Full задача затрагивает код, generated files, runtime sync, 2+ независимых tracks, долгие build/test ожидания или высокий риск scope drift.
Orchestrate tasks across multiple AI providers (Claude, OpenAI, Gemini, Cursor, OpenCode, Ollama). Use when delegating tasks to specialized providers, routing based on…
Conception de systèmes multi-agents avec patterns d'orchestration (supervisor, swarm, hierarchy, voting). Coordination entre agents spécialisés.
Multi-agent performance profiling for pipeline bottlenecks. TRIGGERS - performance profiling, bottleneck analysis, pipeline optimization.
Run multiple AI CLIs (Claude, Codex, Gemini) in parallel for code review, then aggregate, deduplicate, and reconcile results into a unified review.
Orchestrate a team of named subagents in shared threads. One orchestrator drives multiple peers with distinct identities; each subagent sees its own inbox and can cross-check…
Hierarchical multi-agent orchestration supervisor that decomposes tasks, delegates to specialized worker agents, tracks state, and employs triumvirate consensus for high-stakes…
Coordinate multi-agent tasks with visible group updates. Use when delegating work across multiple topic agents and the user needs transparent progress in-group (start update,…
Design and orchestrate multi-agent AI systems with knowledge harvesting, agent collaboration, and learning loops.
Route tasks to specialized AI agents with anti-duplication, quality gates, and 30-minute heartbeat monitoring
Run a gated multi-agent coding workflow for development requests. Use when the user asks Codex to use multiple agents, a team of agents, subagents,…
First principles of AI societal structures and multi-agent interaction paradigms.
Review or design multi-agent workflows with clear ownership, handoffs, evidence gates, conflict handling, and minimal coordination overhead.
Designs parallel agent workstreams for large feature sets by analyzing dependencies, assigning specialized agent types (Explore, Plan, Bash, Edit), maximizing parallelization, and…
Ollama-based multi-AI model orchestration with auto-profiling, smart routing, and ensemble execution — from general/automation
Ollama-based multi-AI model orchestration with auto-profiling, smart routing, and ensemble execution — from majiayu000/claude-skill-registry
Claude + Gemini CLI + Codex CLI multi-AI consensus engine. 3-Stage Pipeline (opinions → rebuttal → synthesis) drives consensus across domains: code review, market analysis,…
Re-render a subject or scene from multiple dramatic camera angles, such as fish-eye, bird's-eye, low-angle, and macro, while maintaining consistent identity and detail.
Generate a complete set of multi-angle product shots — front, side, back, top-down, and 45-degree perspective — for comprehensive product visualization.
Use when you have independent LC-MS assays (e.g., positive and negative ionization modes, different lipid profiling assays, or different chromatographic methods) analyzed on the…
Takes a draft written by two or more contributors and rewrites it as a single, consistent voice — smoothing over clashing tones, register shifts, and stylistic inconsistencies…
Reviews a text written or assembled by multiple authors and produces a detailed inconsistency report — flagging voice shifts, terminology mismatches, tonal clashes, and formatting…
Design and deploy multi-canister dapps. Covers inter-canister calls, canister factory pattern, async messaging pitfalls, bounded vs unbounded wait, and 2MB payload limits.
Coordinate across push, email, in-app, and SMS so a user gets one message rather than the same thing four times. Use when several channels exist and users receive duplicates.
Skill: multi-channel-reminder. See SKILL.md body for details. Use when this domain is relevant.
Mehrere Mandanten in einer Sache: steuert Joint Defense, gleichlaufende Interessen, Kostenteilung, Konfliktumschlag und Information zwischen Kanzlei, Mandant und Rechtsabteilung…
Stratégie multi-cloud et cloud hybride couvrant la portabilité, le vendor lock-in et le networking inter-cloud.
Orchestrate multiple standalone Codex workers for parallel repository tasks. Use when the user wants task decomposition, isolated worktrees, structured worker outputs, patch…
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control. — from satoshistackalotto/skills
Use when you have generated hypothetical links (e.g., GCF–MF pairs) and computed multiple independent scoring functions on them (e.g., strain co-occurrence, IOKR structural…
Multi-database Rails 8 — primary + replica for read scaling, separate databases per concern (auth DB, analytics DB), automatic role switching via connected_to + connects_to,…
Track completion status of all required deliverables and ensure ALL outputs are completed before stopping
Systematic tracking and completion of all required deliverables before task termination
When the user wants to solve Multi-Depot VRP (MDVRP), optimize routes from multiple warehouses/depots, or handle multi-facility distribution.
Use when you have raw or processed mass spectrometry data in HDF5 (.h5) or mzML format and need to ingest it into DEIMoS for multi-dimensional analysis.
Use when you have a parsed sample list with metadata (sample IDs, classification
当需要对多份相关文档进行综合分析、提取共同观点、识别冲突并生成统一概览时触发此技能。 典型触发场景包括但不限于： - 用户上传多份判决书、裁定书，要求总结类案裁判要旨 - 用户提供多个合同文本，要求归纳条款异同和关键差异 - 用户提供多份法律法规、司法解释，要求梳理规范演变和适用要点 - 用户提供多个证据材料、调查笔录，要求整合事实脉络 -…
Use when you have executed batch searches of MS/MS spectra against multiple domain-specific MASST tools and need to synthesize results across domains (e.
Use when the user wants an 8-expert or multi-expert roundtable, multi-perspective strategic analysis, consulting-style decision report, expert challenge session, pyramid-principle…
Guide users to create multi-factor stock selection strategies and generate independent YAML configuration files
Use when when building a transformer-based model to process mass spectrometry data (MS/MS spectra or fingerprints) where you need the model to learn multiple independent attention…
Answer questions that need several linked lookups by decomposing the query and retrieving in sequence.
Use when when you need to support multiple plotting library backends (static or interactive) for the same data visualization domain (e.
Guides building a multi-jurisdiction privacy compliance matrix for organisations operating across multiple countries.
Use when when converting tabular data to JSON via the matrix directive, you need to exclude records that fail domain-specific validation (e.g., only retain records where a 'test'…
Create multilingual README files by translating an existing README into target languages. Use when users ask for bilingual or multilingual README output, such as "create bilingual…
创建多语言 README。用于用户要求“中英 README”“多语言 README”“把 README 翻译成某语言”等场景。支持英文、德语、日语、韩语、中文，并保持 Markdown 结构与链接一致。
Best practices for multi-language static websites with proper i18n and l10n support
Use when facing complex problems, making decisions, seeking creative solutions, or when single-perspective thinking feels limiting.