В каталоге 183 730 навыков в 14 категориях.
When the user wants to combine machine learning with optimization, use ML predictions in optimization models, or integra...
Analyze an OpenClaw agent's browser usage and recommend browsy migration
Build a retrieval-optimized knowledge layer over agent documentation in dotfiles (.claude, .codex, .cursor, .aider). Use...
Optimize AGENTS.md and rules for token efficiency. Auto-invoked when user asks about improving agent instructions, compr...
GPU-accelerate Python code using CuPy, Numba CUDA, Warp, cuDF, cuML, cuGraph, KvikIO, cuCIM, cuxfilter, cuVS, cuSpatial,...
Optimizes prompts for goal effectiveness - ensures instructions serve the stated goal, prevents missteps, improves effic...
Iteratively optimizes prompts for precision - eliminates ambiguities, resolves conflicts, adds missing definitions. Use...
Use when creating or refining SKILL.md-based skills, or diagnosing weak triggering (under/over-triggering, vague descrip...
Use when CLAUDE.md is bloated or ineffective. Use when Claude ignores instructions, file exceeds 150 lines, response for...
Use when instruction files (skills, prompts, CLAUDE.md) are too long or need token reduction while preserving capability...
Execute this skill optimizes prompts for large language models (llms) to reduce token usage, lower costs, and improve pe...
options foundations, Greeks analysis, volatility surface, put call parity, options pricing, delta gamma theta vega rho,...
When the user wants to tune metaheuristic or solver parameters with Optuna, including search-space definition, TPE sampl...
Optuna Study Creator - Auto-activating skill for ML Training. Triggers on: optuna study creator, optuna study creator Pa...
Create optuna study creator operations. Auto-activating skill for ML Training. Triggers on: optuna study creator, optuna...
Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update...
Leverage Claude Opus 4.5's extended thinking capabilities for deep reasoning, complex analysis, and multi-step synthesis...
Generate a voiceover, narration or text-to-speech, a music track or soundtrack, or short AI video clips with OpusClip MC...
GPT-5 Pro second opinion. Use when user says "consult the oracle", "ask the oracle", "oracle this". Run DETACHED with no...
Build production agentic applications on OCI using Oracle Agent Development Kit with multi-agent orchestration, function...
Design framework-agnostic AI agents using Oracle's Open Agent Specification for portable, interoperable agentic systems...
This skill should be used when the user asks to "use Codex", "ask Codex", "consult Codex", "use GPT for planning", "ask...
This skill should be used when the user asks to "use Codex", "ask Codex", "consult Codex", "Codex review", "use GPT for...
This skill should be used when the user asks to "use Gemini", "ask Gemini", "consult Gemini", "Gemini review", "use Gemi...
Build Oracle memory surfaces: session logs, durable notes, local context, and retrieval. Use when the task touches histo...
Prepare a lawyer for an adversarial proceeding the way Neal Katyal's "Harvey" prepared him for the SCOTUS tariffs argume...
WordPress plugin coding standards review. Use when reviewing WP plugin code for standards compliance — naming convention...
Set up LLM-as-judge evaluation for ORC workflows
Set up GEPA prompt optimization for an ORC workflow
Generate visualizations from OrcaFlex simulations including model views, time series plots, range graphs, and interactiv...
Use when a task spans multiple files or workstreams and benefits from parallel implementation by an agent team.
Skill for configuring AI integrations in Orchard Core. Covers AI service registration, MCP enablement, prompt configurat...
Skill for configuring the CrestApps A2A Client feature in Orchard Core. Covers adding remote A2A hosts, authentication,...
Skill for configuring the CrestApps A2A Host feature in Orchard Core. Covers exposing Agent AI Profiles as A2A agents, h...
Skill for configuring AI Chat in Orchard Core using the CrestApps AI Chat module. Covers chat profiles, admin chat UI, f...
Skill for configuring AI Chat Interactions in Orchard Core using the CrestApps module. Covers ad-hoc chat sessions, prom...
Skill for configuring Model Context Protocol (MCP) in Orchard Core using the CrestApps MCP module. Covers MCP client con...
Skill for configuring CrestApps MCP client connections in Orchard Core. Covers SSE and Stdio transports, authentication,...
Skill for configuring the CrestApps MCP Server feature in Orchard Core. Covers server authentication, exposing tools, ad...
Skill for implementing custom Chat Response Handlers in Orchard Core. Covers IChatResponseHandler, deferred and streamin...
Skill for creating and managing AI Templates in Orchard Core. Covers template creation via admin UI, markdown files, rec...
Coordinate focused subagents on substantial work, keep their ownership non-overlapping, and integrate verified results....
Activate multi-agent orchestration mode
Multi-agent task orchestration for complex features. Use when: - User has a complex, multi-step task - Task requires mul...
- Running the full Conductor workflow
Orchestrate tasks from a 0N_TASKS.md file with enforced memory-first pre-hooks, quality-gate post-hooks, and session arc...
Delegation manual for the five agents (Operator, Researcher, Builder, Specialist, Reviewer). Use for any search, change,...
Task Decomposition Engine - Breaks down complex tasks into phases, creates Native Tasks with dependencies, and generates...
Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning...
Leader가 직접 스펙을 작성하고 Executor 세션으로 실행합니다. Tester는 Executor가 필요 시 on-demand로 생성합니다.
Plan and execute large refactors with dependency-aware work packets and parallel analysis.
Coordinate substantial multi-agent work through a fixed two-tier topology: a GPT-5.6-sol coordinator at max reasoning pl...
The canonical way to run agent-relay - self-bootstrap the local broker and autonomously spawn, monitor, and coordinate a...
Orchestrates parallel API instances, delegated sub-tasks, and multi-agent workflows with streaming and tool-enabled dele...
Skill-aware orchestration with context routing. Decomposes complex tasks into skill-typed subtasks, extracts targeted co...
Choose and compose the right building block — a skill, a subagent, an MCP server, a hook, a loop, or a workflow — and en...
Comprehensive inter-agent messaging and coordination system providing protocol-based communication, shared context manag...
Teams vs subagents decision framework, resource constraints, enforcement hooks awareness, and orchestrator rules for git...
Multi-agent orchestration patterns: delegation, context passing, workflow gates, and role-based coordination. Activate w...
Coordinate supervised Orca workers: threaded messages, blocking ask/reply, task dispatch, worker_done/escalation waits,...
Runnable driver for the deterministic campaign-execution protocol — the automaton that takes a validated campaign DAG to...
Production-scale multi-agent coordination, task orchestration, and workflow automation. Use for distributed system orche...
This skill should be used when the user asks about "orchestration patterns", "plan-then-execute", "hierarchical decompos...
Use when coordinating assignments, selected review boundaries, or blocked work across a rig.
Reference template for multi-agent orchestrated skills. Use as a pattern when creating complex skills that need parallel...
Master orchestrator routing to specialized agents - Australian-first
Claude as intelligent orchestrator for multi-agent workflows. Coordinates specialized agents (Gemini, local models, tool...
Multi-instance delegation: route to A-H instances, fanout/aggregation, sessions_send/spawn, health checks
Internal orchestrator for executing skills with phase-based subagent spawning. Parses SKILL.md frontmatter, manages depe...
Master coordinator for Unite-Hub workflows. Routes tasks to specialists, manages multi-agent pipelines, maintains contex...
DEPRECATED: Use dag-orchestrator instead. This skill has been merged into the more powerful dag-orchestrator skill.
Coordinate all assimilation phases to scan a repo and generate skills. Use when assimilating a repository, running the f...
Thin orchestrator for Task Decomposition Protocol v2. Supports two modes - /plan (decompose spec into tasks) and /execut...
Orchestrator for the complete talk preparation pipeline (REX or Concept mode). Runs all 6 stages in sequence with human-...
Plan and coordinate multi-agent bead execution. Use when starting a new epic, assigning tracks to agents, or monitoring...
Use when managing agent state transitions (START/INIT/IMPLEMENT/TEST/COMPLETE), triggering context compression at 80% ca...
Multi-omics query routing and pipeline orchestration across all OmicsClaw domains. Routes natural language queries to th...
Integrated orchestrator agent that manages and coordinates 25 specialized AI agents for Specification Driven Development...
多代理协作编排器,基于 Anthropic 工程团队架构,支持 Lead-Worker 模式、API Key 轮换、并行执行。触发词:创建团队、多代理协作、长任务、复杂任务、并行搜索。
The Orchestrator Agent - Master coordinator for the Nebuchadnezzar v4.0 Pipeline OS. Manages the Four Pillars: Expert CR...
多智能体编排的领域无关内核(A² Supervisor 层的方法论抽象)。把编排者的操作系统从领域里剥出来:萃取式主上下文 + 按『要不要主上下文』切分派工 + 契约化派发 + 分层合并 + 对抗式异构验证 + 降认知负载。领域皮(CTO...
Multi-agent orchestration for building software incrementally. Use when coordinating workers via native Agent Teams (Tea...
Shared orchestrator behavior for delegation-first agents. All specialized agents must follow this protocol when delegati...
Reference system prompt and tool schemas for Orchids.app. Use when imitating, comparing, or analyzing Orchids.app's prom...
Context-Aware Agentic Orchestrator that analyzes product context (budget, channel, maturity, timeline, team), recommends...
Ordered Locales (Heunen-van der Schaaf 2024): Point-free topology with direction. Frame + compatible preorder with open...
On-demand ORF news digest in German. Use when the user says 'orf', 'pull orf', or 'orf 10'. Focus on Austrian politics (...
Detect and quantify translated ORFs from Ribo-seq data including uORFs and novel ORFs using RiboCode and ORFquant. Use w...
Generate organizational hierarchy charts from CSV, JSON, or nested data. Supports multiple layouts, department coloring,...
Open the Claude Code Organizer dashboard — view and manage all memories, skills, MCP servers, hooks, and configs across...
Use when user invokes /orient with a topic keyword, entity type, project name, time qualifier, or combination. Also trig...
Use at the start of an orchestrator session to understand project state and find available work
Orients agents in new projects by scanning entry documents and discovering capabilities. Use at session start, when ente...
Use when you have just been primed into an EXISTING seat through a planned handover — a different agent retired and hand...
発信元の原典(一次資料)だけを根拠に web を調べ、主張ごとに出典URLを付けて答える。原典で確かめられなければ答えず「確認できなかった」と返す。「origin-search」「一次資料で調べて」「出典付きで調べて」「原典に当たって」と指...
Community resources, starter kits, tools, and libraries for oRPC.
Extend the body parser for larger payloads or additional data types.
Assess creative fatigue hypotheses from mature comparable trends, delivery age, and reach context; propose a bounded ref...
Find and install skills from the Orthogonal skill library. Use when you need capabilities you don't have, want to discov...