opencode-acp-control
Control OpenCode directly via the Agent Client Protocol (ACP). Start sessions, send prompts, resume conversations, and manage OpenCode updates.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-07 00:13
Agents & models
25,853 results
reasoning-personas
Activate different high-agency thinking modes to unlock better reasoning. Use when brainstorming, reviewing plans, making decisions, or when user says 'put on…
ltx23-comfyui-ti2v-audio
Use when you need to run, configure, explain, or adapt Isi-dev style LTX 2.3 ComfyUI workflows for text-to-video or image-to-video with audio, including remote…
supermemory-forget
Remove outdated or incorrect information from memory. Use when user says something is no longer true, wants to delete a memory, or information has changed.
supermemory-login
Log in to Supermemory. Use when the user needs to authenticate, set up their API key, or when memory features report a missing key.
liang-xiangrun
From the perspective of Liang Xiangrun (1930-2014). Spokesperson for the disciplinaryization of the Ziping school in Hong Kong and Taiwan, advocate of the "Ziping Mother Method," and founder of the three-stage teaching method. Lead author of the Xingmao Publishing House book series, and made a disciplinary-historical rebuttal to the Republican-era collation school (Xu Lewu) — "Shen's profound essence is obscured by Xu's annotations, and he often misunderstands Shen's meaning through his own habits." Pushed the study of fortune-telling from "master-to-disciple transmission" toward a "disciplinary teaching system," making him one of the rare figures within the Ziping school with an "academic air +…
kyro-pi-sprint-flow
Orchestrates the Kyro sprint flow on Pi by directing specialized workers. The orchestrator never executes the sprint or runs QA itself. Trigger: When the user…
agent-relay
Cross-product Agent task relay, delegation, and collaboration. Quota switching, compaction and continuation, sub-agent invocation (Claude Code / Grok Build / Kimi Code / Codex, etc.). Trigger: relay, handoff, handoff, delegate, delegate, resume, continue doing, out of quota, switch environment to continue, cross...
mimo-skill-creator
Create, test, and optimize skills for MiMo Code. Use when creating a skill, editing one, testing if a skill works, optimizing skill triggering, or packaging a…
agent-social
Smart AI agent social matching. Analyze your profile, register to NextMarket platform, and find matched agents based on skills, interests, and goals.
telegram-bot-agent
Comprehensive Telegram Bot management for Claude agents. Use when the user needs to: (1) Create or configure Telegram bots, (2) Send messages to users or…
build-custom-agent
Build a bounded .NET 10 local agent prototype from a short Purpose. For requests requiring live access, real effects, or complex orchestration, offer an…
build-template-agent
Copy, build, smoke-test, and run a finished .NET 10 agent template: Release Evidence Reviewer, Docs Q&A, Operations Data Analyst, or Ticket Triage. Use for…
yolo-master-agent
Use when the user wants to run a YOLO-Master task (train/val/predict/track/export/benchmark) or use the Agent Skill dispatcher.
ag-ui
AG-UI (Agent-User Interaction Protocol) is an open, event-based protocol that streams an AI agent's text, tool calls, state and lifecycle events to a frontend…
agent-workflow-packager
Converts repeated AI coding-agent workflows into reusable skill packages with triggers, guardrails, examples, and verification checks. Use when a user wants to…
huggingface
Work with Hugging Face's ecosystem for machine learning — transformers library, model hub, tokenizers, inference pipelines, and fine-tuning. Covers downloading…
ios-debugger-agent
AI agent for building, running, and debugging iOS apps on simulator via XcodeBuildMCP. Use when: running iOS apps, inspecting simulator UI, capturing logs, or…
openclaw
Deploy and manage OpenClaw, a self-hosted gateway bridging messaging platforms to AI coding agents. Use when a user asks to set up OpenClaw, connect WhatsApp…
prompt-tester
Design, test, and iterate on AI prompts systematically using structured evaluation criteria. Use when building AI features, optimizing agent instructions,…
qdrant
You are an expert in Qdrant, the high-performance vector search engine written in Rust. You help developers build semantic search, RAG retrieval,…
ray
Framework for scaling Python applications from a laptop to a cluster. Includes Ray Core for distributed computing, Ray Serve for model serving, Ray Tune for…
senior-computer-vision
Object detection, image segmentation, and visual AI. Use when a user asks to detect objects in images, segment images, run YOLO inference, build a computer…
terragrunt
You are an expert in Terragrunt, the thin wrapper for Terraform and OpenTofu that provides extra tools for keeping configurations DRY, managing remote state,…