openai-agents
Build multi-agent systems with the OpenAI Agents SDK, including tool definitions, handoffs, context management, and webhook validation. Use when creating…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-28 00:17
Agents & models
24,965 results
temporal-python
Build Temporal applications in Python using the temporalio SDK. Use when creating workflows, activities, workers, clients, signals, queries, updates, child…
haos-cloud-backup
Ship Home Assistant OS (HAOS) backups off the SD card to cloud storage (Google Drive or any rclone remote) with an upload bandwidth cap and a GFS-style…
agent-device
Automates interactions for Apple-platform apps (iOS, tvOS, macOS) and Android devices. Use when navigating apps, taking snapshots/screenshots, tapping, typing,…
model-selector
Based on the user's video needs (scene, duration, audio, language, platform restrictions, budget, whether local deployment/character consistency is required, etc.), recommend the 1-3 best-matching from 16 mainstream AI video models (12 commercial + 4 open-source), and explain why. Covers commercial: Seedance 2.0, HappyHorse 1.0, Kling 3.0, Sora 2, Veo…
agent-collaboration
Routes explicitly requested agent collaboration across direct work, focused headless Grok delegation, Pi subagents, and Herdr. Use when the user asks to…
hyperagent
Run a self-referential self-improving agent loop where a meta-agent iteratively modifies a task-agent's code to optimize for any measurable target. Based on…
google-pubsub
Google Cloud Pub/Sub messaging service. Covers topics, subscriptions, push/pull delivery, and dead-letter handling. Use for GCP-native event-driven…
ligandmpnn
Design protein sequences around ligand or small-molecule contexts with LigandMPNN-style workflows. Use when a task asks for ligand-aware protein design,…
cy-create-tasks
Create or refine a task graph from an existing CompozyOS spec, with outcome, dependency, and test ownership.
multi
Parallel subagent orchestration kernel — spawn invariants, model routing, generic prompts and synthesis. Entry skills supply job recipes. Use when a task…
skill-creator
Creates new Agent Skills following the Agent Skills specification. Use when the user asks to create a new skill, add a skill, define a skill, or build a skill…
goap-agent
Invoke for complex multi-step tasks requiring intelligent planning and multi-agent coordination. Use when tasks need decomposition, dependency mapping,…
discover-tools
Discover available tools and resources in Databricks workspace. Use when: (1) User asks 'what tools are available', (2) Before writing agent code, (3) Looking…
autoresearch-hooks
Author pre/post-iteration hooks for an autoresearch session. Use when the user asks to add research fetching, Slack/webhook notifications, persistent…
phantom-wallet-mcp
Execute wallet operations through the Phantom MCP server. Use when the user wants to interact with their Phantom wallet directly — get addresses, transfer SOL…
idea-mcp
IntelliJ IDEA MCP for Java code analysis, testing, refactoring, and project navigation. Use when: (1) Checking Java compilation errors (get_file_problems is…
orca-automations
Only use when the user explicitly invokes /orca-automations (or $orca-automations in Codex). Never auto-invoke. Orca's Automations with the orca CLI…
game-quest
Designs a single quest end-to-end — coherence check, objective tree, quest brief, and registry entry. Extract the quest name from the user's message. Requires…
knowledge-distillation
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance,…
voice-skill
Voice conversations with Claude Opus 4.5 about your code projects. Receive calls from Claude or call Claude to discuss problems, brainstorm, and get code…
arcanea-architect
Expert guidance for building the Arcanea creative agent ecosystem with attention to detail, design excellence, and systematic implementation.
stitch-mcp-delete-project
Permanently deletes a Stitch project and all its screens. Destructive — requires explicit user confirmation before calling.
authoring-verifiable-skills
Write, split, rename, or repair an agent skill so it activates when it should and can be proved rather than believed: a new skill, a description that never…