Loading...
Loading...
Found 25 Skills
Execute multiple independent tasks simultaneously using parallel agent coordination to maximize throughput. Use when tasks have no dependencies, results can be aggregated, and agents are available for concurrent work.
Parallel execution engine for high-throughput task completion
Based on the Recursive Language Models (RLM) research by Zhang, Kraska, and Khattab (2025), this skill provides strategies for handling tasks that exceed comfortable context limits through programmatic decomposition and recursive self-invocation. Triggers on phrases like "analyze all files", "process this large document", "aggregate information from", "search across the codebase", or tasks involving 10+ files or 50k+ tokens.
Code context using Exa. Finds real snippets and docs from GitHub, StackOverflow, and technical docs. Use when searching for code examples, API syntax, library documentation, or debugging help.
Manage work in Vibe Kanban (VK), the shared source of truth for agent tasks. Use when checking assigned work, creating/updating tasks, running heartbeat checks, scanning @mentions, or producing daily standup summaries. Triggers: "check the board", "what's on my plate", "create/update task", "heartbeat", "standup summary".
Use when an agent needs to write user stories for a project
Coordinate a research task by choosing the right workflow and dispatching to specialized agents. Use when the user has a broad or complex research request that may involve multiple steps.
Review applications and verify task submissions on OpenAnt. Use when the agent (as task creator) needs to review applicants, accept or reject applications, approve or reject submitted work, or give feedback on deliverables. Covers "review applications", "approve submission", "reject work", "check applicants", "verify task".
Orchestrate multiple code-writing agents in parallel when the work contains 3 or more genuinely independent build tasks. Use for execution lanes with disjoint write scope, clear task boundaries, and no dependency edges that would force sequencing.
Create, query, update, assign, and discuss Multica issues. Also covers comments, subscribers, and viewing execution runs for an issue. Use when the user wants to file a task for an agent, triage the board, comment on an issue, or inspect what an agent actually did.
Goal-based workflow orchestration - routes tasks to specialist agents based on user goals
Maintain a structured ledger of decisions, discovered bugs and fixes, user preferences, constraints, current status, and failed approaches throughout multi-step agentic tasks. Auto-update after every significant step. Triggers on "where were we", "continue", "summarize status", "remember", or when a new agent instance takes over a task.