dex
Use when tracking complex multi-step tasks, creating task hierarchies, maintaining persistent task state across sessions, building backlogs, or when the user…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-03 00:11
Agents & models
25,520 results
multi-ai-collab
Orchestrate multiple AI agents with specialized personas for cross-review and collaborative development
taxue-roundtable
Taxue multi-perspective collision. Multiple perspectives look at the same issue simultaneously, exposing blind spots you wouldn't think of alone. Trigger: /taxue-roundtable, help me analyze from multiple angles, how do different perspectives see it, roundtable, multiple perspectives, multiple angles, collide, multi-angle discussion, see from different angles, perspective collision. EN: "multiple perspectives", "devil's advocate",…
claude-code-setup
Deploy or audit the full 5-layer Claude Code stack (CLAUDE.md + skills + hooks + agents + memory) in a repository. Use this skill whenever the user runs…
arm-holdings
Expert skill for Arm Holdings
apm-package-author
Create, maintain, and troubleshoot APM (Agent Package Manager) manifests for distributing GitHub Copilot skills, agents, and MCP servers. USE FOR: creating…
dsh-plugin-dev
Develop plugins for DeepSeek Harness (dsh), a Cordis-based agent framework. Use when the user asks to create, modify, debug, or package a dsh plugin; write a…
slopshipper
Runs a structured, deterministic implementation workflow via the installed slopshipper CLI: clarifies intake, gates human release, runs build and verify,…
claude-handoff
Hand the current conversation off to a fresh background agent that picks up the work immediately.
agents-md
Audit and refactor a repository's AGENTS.md so an agent can act on it. Use when the user asks to audit AGENTS.md, fix AGENTS.md, set up agent docs, improve…
mainframe-modernization-and-data-offload
Guides agents through mainframe data modernization and offload workflows. Use when migrating or exposing data from COBOL, JCL, VSAM, IMS, DB2 for z/OS, or…
vp-agent-browser-session
Manage persistent, login-required agent-browser sessions and dedicated Chrome profiles. Use to select installed or CLI-bundled agent-browser guidance, create,…
fiftyone-zoo-remote-model
Use when integrating a model into FiftyOne's remote model zoo — detection, classification, segmentation, embedding, keypoint, or vision-language (VLM) models…
skill_evaluator
Evaluates agent skills against Anthropic's best practices. Use when asked to review, evaluate, assess, or audit a skill for quality. Analyzes SKILL.md…
claude-chatgpt-skill
Via Claude Code and the claude-in-chrome MCP, reuse the user's existing, already-logged-in ChatGPT web session, delegate tasks to any ChatGPT model, and manage conversations/projects/Memory/library, etc., and also save conversations/Artifacts/images to local disk. Suitable when the user says "ask ChatGPT / have GPT Pro think about it for me..."
binance-agentic-wallet-100-questions
100 Questions on Binance Agentic Wallet. Use Chinese Q&A to guide agents in understanding the Binance on-chain wallet, selecting the official baw route, verifying transaction authorization and risk boundaries, and designing constrained automation extensions. Covers meme coin risks and honeypot identification, rug pull prevention, and distinguishing genuine from fake smart money signals. Suitable for product Q&A, operational troubleshooting, trading strategy constraints, meme...
rag-search
Semantic search using embeddings and vector storage. Search documents semantically using similarity matching.
xquik-mcp
Connect, verify, and troubleshoot Xquik's remote MCP server. Use when a user needs MCP setup, OAuth recovery, tool discovery, endpoint execution, or a…
alternative-agent-frameworks
Multi-agent frameworks beyond LangGraph. CrewAI crews, Microsoft Agent Framework, OpenAI Agents SDK, GPT-5.2-Codex. Use when building multi-agent systems,…
fine-tuning-customization
LLM fine-tuning with LoRA, QLoRA, DPO alignment, and synthetic data generation. Efficient training, preference learning, data creation. Use when customizing…
prompt-caching
Provider-native prompt caching for Claude and OpenAI. Use when optimizing LLM costs with cache breakpoints, caching system prompts, or reducing token costs for…
seedance-2-prompts
Search Seedance 2.0 video generation prompts curated from the community. ByteDance AI video model — find cinematic, realistic, animated, and creative video…
zapier-status
Check the health of your Zapier MCP setup. Three modes — health check (dashboard view), audit (find waste and duplicates), diagnose (systematic…
ezbot-agent-id-feed
Read and subscribe to the Binance Agent ID / Agentic Wallet ecosystem project directory from the EZbot signal panel, and show brief project cards and contract initial-screening updates in chat. Supports official entry categorization, low-priority and risk filtering. Does not involve wallet login, trading, or proactive research data collection.