Loading...
Loading...
Found 409 Skills
Build AI agents with persistent threads, tool calling, and streaming on Convex. Use when implementing chat interfaces, AI assistants, multi-agent workflows, RAG systems, or any LLM-powered features with message history.
Coordinate complex work using a phase-gated, multi-agent engineering loop (audit → design → implement → review → validate → deliver). Use when you need to split a task into subsystems, run dual independent audits, reconcile findings into a confirmed issue list, delegate fixes in clusters, enforce dual-review PASS gates, and drive an end-to-end delivery. Prefer discovering and invoking other specialized skills when they can execute part of the work faster or more reliably.
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
Save current session state to Apple Notes at session end. Triggers on handoff, bye, done, wrap up, or Chinese equivalents. Multi-agent architecture with private (per-agent) and shared (cross-agent) notes. Three-tier memory: Active, Archive, Long-term. Use whenever the user wants to end a session, save progress, or says anything indicating they are done for now.
Run a multi-agent review of changed files for reuse, quality, efficiency, and clarity issues followed by automated fixes. Use when the user asks to "simplify code", "review changed code", "check for code reuse", "review code quality", "review efficiency", "simplify changes", "clean up code", "refactor changes", or "run simplify".
#1 on DeepResearch Bench (Feb 2026). Any-to-Any AI for agents. Combines deep reasoning with all modalities through sophisticated multi-agent orchestration. Research, videos, images, audio, dashboards, presentations, spreadsheets, and more.
Multi-agent pipeline orchestrator that plans and dispatches parallel development tasks to worktree agents. Reads project context, configures task directories with PRDs and jsonl context files, and launches isolated coding agents. Use when multiple independent features need parallel development, orchestrating worktree agents, or managing multi-agent coding pipelines.
Canonical ticket lifecycle engine for multi-agent orchestration. Two backends: (1) filesystem YAML bundles for project-level work management (roadmap → bundle → tickets → review), (2) DB-backed durable tickets for session-level claim/block/close lifecycle. This skill is the single source of truth for all ticket operations.
Task-based multi-agent coordination (includes Issue Remediation Loop)
Use when the user needs to build AI agents — tool use patterns, memory management, planning strategies, multi-agent coordination, evaluation, and safety guardrails. Triggers: user says "agent", "build an agent", "tool use", "agent loop", "multi-agent", "memory management", "guardrails", "agent evaluation".
Run structured multi-agent debates using argue CLI for cross-examined, high-confidence answers. Use when facing strategic decisions, ambiguous trade-offs, architecture debates, or questions where multiple perspectives improve the answer. Triggers on: argue, debate, cross-examine, second opinion, multi-agent, 'Should we X or Y?' with real stakes, consensus-building, risk analysis, or confirmation-bias mitigation.
C-suite orchestration layer that routes founder questions to the right advisor role(s), triggers multi-role board meetings for complex decisions, synthesizes outputs, tracks decisions, and manages cross-functional alignment. Every C-suite interaction starts here. Use when coordinating executive decisions, routing strategic questions, managing board meetings, synthesizing multi-perspective advice, tracking decision history, resolving inter-department conflicts, or when user mentions chief of staff, orchestrator, c-suite coordinator, executive routing, board coordination, decision synthesis, advisor routing, multi-agent coordination, or strategic orchestration.