Loading...
Loading...
Found 20 Skills
Orchestrate work through a team of agents coordinating via chat. Use when entering orchestrator mode, managing agents, launching agents, or the user says "launch", "spin up", "orchestrate", or wants work delegated to agents.
Invoke MassGen's multi-agent system for general-purpose tasks, evaluation, planning, or spec writing. Use whenever you want multiple AI agents to tackle a problem, need outside perspective on your work, a thoroughly refined plan, or a well-specified set of requirements. Perfect for: writing, code generation, research, design, analysis, pre-PR review, complex project planning, feature specification, architecture decisions, or any task where multi-agent iteration produces better results than working alone.
(NS) Autonomous execution engine — plans depth, resolves doubts from docs/specs, multi-agent work in an isolated worktree. Use for a local/pasted plan or "run this autonomously" without GitLab. Also Phase 2 under ns-execution-gitlab-issue (do not run standalone then). Not for single-step edits (ns-coder) or GitLab issues directly (ns-execution-gitlab-issue).
Integration patterns and best practices for adding persistent memory to LLM agents using the Letta Learning SDK
Break down a one-sentence idea into a task plan that an AI agent can execute independently. Use this when the user says: "Help me write a goal for the agent", "Help me break down this goal in detail", "Write a task brief for the agent", "Write a goal prompt", "Let the agent run this project on its own", "Split the work among multiple agents for parallel execution". First conduct actual tests in the codebase, conduct online research if necessary, then ask a maximum of 5 questions in one go, and produce a task plan of ≤4000 characters that can be directly pasted into /goal to run, including actual test data, whitelist boundaries, anti-cheating acceptance criteria, and resumable progress. Automatically distinguish between execution-type and exploration-type (research/selection/solution-finding) tasks.
Unified team skill for deep collaborative analysis. All roles invoke this skill with --role arg for role-specific execution. Triggers on "team ultra-analyze", "team analyze".
One-click comprehensive analysis of a stock/company. Collect data from five dimensions - stock price, news sentiment, industry comparison, market environment, and official company website - simultaneously through parallel sub-agents, then conduct cross-analysis, causal attribution, and trend prediction in the main thread, and output a standardized analysis report. Trigger words: Analyze XX stock, analyze TICKER, How is XX, Is XX worth buying? Supports A-shares and U.S. stocks.
Interactive agent picker for composing and dispatching parallel teams
Auto-activates when working with implementation plans. Triggers on "continue the plan", "next task", "what's the plan status", "run task 2.1", or when user references plans/*.plan.md files. Not for creating plans - use /superplan command for that.
Sets up Claude Code agent teams with role-based composition. Use when creating dev teams, defining team roles, or organizing multi-agent collaboration. Do NOT use for single sub-agent creation (use agent-creator instead).
Project development lifecycle management with a strict three-phase workflow (investigate -> proposal -> implement), file-based plan tracking in docs/plan/, task tracking in docs/task/, and claim-before-work multi-agent coordination. Use when handling feature development, bug fixes, refactors, planning, progress tracking, or multi-agent execution in an existing codebase. Supports English and Chinese project templates.
AI Agent Orchestration Dashboard for managing AI agents, tasks, and multi-agent collaboration via OpenClaw Gateway