content-analysis
Analyze text content using both traditional NLP and LLM-enhanced methods. Extract sentiment, topics, keywords, and insights from various content types…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,666 results
ltv-predictor
A customer lifetime value (LTV) predictive analysis tool based on the RFM model and regression algorithms, supporting customer value prediction for e-commerce and retail businesses. When used, it requires customer transaction data, order history, or consumption records, and automatically performs RFM feature engineering, regression modeling, and value prediction.
research-teams
Coordinate multiple agents working together as a team, with shared tasks, inter-agent messaging, and centralized management. Agent teams are most effective…
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…
llmquant-setup
Connect LLMQuant Data to this Hermes instance, confirm the DeepSeek baseline, smoke-test auth for zero credits, install the playbooks, and schedule the first…
dsh-search-or-create-plugin
Search the plugin gateway, analyze which DSH plugin best fits a goal, then use it or design a new plugin from the closest open source. Trigger: choose a plugin or create a new one / are the plugins sufficient /…
lov-integrate-lovstudio-llm-skill
Use LovStudio.AI's OpenAI-compatible API to complete text chat, speech-to-text, speech translation, speech synthesis, and Realtime audio sessions; triggered when the user says "接入 Lovstudio LLM", "调用语音转文字", or "use LovStudio API".
lov-read-codex-session
Read turn summaries, status, tool activity and completion results of a local Codex task/thread; suitable for "view Codex session", "read task progress" or read Codex session.
lov-skill-distiller
Use when the user wants to distill project experience, incident retrospectives, and validated processes into a creatable Agent Skill blueprint, clarifying the user outcome, trigger boundary, private-information boundary, and acceptance method; trigger phrases include "把经验蒸馏成 skill" and "distill experience into a skill".
lov-skill-visualizer
Parse a local Agent Skill directory or SKILL.md into a scenario-first, one-page trust review, internal run graph, and JSON model; first explain when it is indispensable, then continuously present inputs, internal transformations, delivered results, source-code evidence, and unproven gaps. Use when the user wants to understand, review, or trust a Skill.
lov-yolo-mode
Enable YOLO mode: first check the current session and prepare the necessary permissions through interfaces allowed by the host, then complete the task autonomously according to presets and preferences without asking questions. Use /lov-yolo-mode for unattended work with session permission preflight.
lov-xbti-creator
Create a complete custom BTI personality test (like LBTI, FBTI, etc.) based on the XBTI architecture. User provides a theme name and preferences, AI generates…
consulting-librarian
Emulates repository-librarian research in hosts without a native Librarian. Use in non-Amp agents when tracing dependency internals, comparing remote…
jiangju-perspective
The thinking framework and expression style of Warring States Era_Ginger Ale. Based on in-depth research of 186 Bilibili video transcripts (about 2 million characters), distilling 7 core mental models, 8 decision heuristics, and a complete expression DNA. Purpose: To serve as a geopolitical and financial thinking consultant, analyzing international situations, macroeconomics, and asset allocation issues from the perspective of Ginger Ale. When the user mentions "from Ginger Ale's perspective," "what would Soda think," "Soda mode," "jiangju...
skill-index-updater
Add GitHub skill repos to the ASM index: clone, audit, eval, regenerate index, rebuild catalog, open PR. Use when given GitHub URLs to onboard. Don't use for…
claude-md
Create or update CLAUDE.md files following best practices for optimal AI agent onboarding
codex-usage-status
Check OpenAI Codex (openai-codex) account usage/quota windows using local OpenClaw configuration (OAuth). Report clean, readable usage stats and compute a…
herdr-agent-comms
Manage AI agent fleets in Herdr: split root + sub-agents into one tab as a tiled grid, message/wait/read via herdr CLI, steer any pane. Use for Herdr…
whatsapp-macos
Control WhatsApp desktop (macOS Catalyst app) via native MCP tools. Send messages, read chats, search contacts, verify delivery, start/quit app. Use when:…
template-constructor
Construct and scaffold Machina agent-templates and connectors with correct YAML structure, then install them via MCP. Use when users ask to "create a…
mirage-private-transfer
Use when the user wants to build, sign, and send a transaction for ANY Solana program that has an Anchor IDL (either published on-chain or supplied locally),…
agent development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent…
agentobservability
Real-time observability dashboard for multi-agent Claude Code sessions. Visualize agent interactions, tool usage, and session flows in real-time through a web…
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…