agent-md-setup
Use when a repository needs one canonical instruction file shared by coding agents, when AGENTS.md or CLAUDE.md is missing, or when their guidance has diverged.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-31 00:15
Agents & models
25,338 results
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…
forge-prompt
Turns a short, unclear ask into one paste-ready prompt block — targets, boundaries, evidence, open questions, and a done signal — for a fresh session to pick…
langchain-hello-world
Create a minimal working LangChain example with LCEL chains. Use when starting a new LangChain integration, testing your setup, or learning LCEL pipe syntax…
arch-init
Identifica el punto de partida de un proyecto (sin código / con código base / con implementación) e inicializa lo que falte de su harness multi-agente: repo…
integrating-jupiter
Comprehensive guidance for integrating Jupiter APIs (Swap, Lend, Perps, Trigger, Recurring, Tokens, Price, Portfolio, Prediction Markets, Send, Studio, Lock,…
write-a-skill
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
analyze-team-session
Use when reviewing an agent team session export for quality, when asked to "analyze this team session", "review my agent team run", "what went wrong with this…
retrospective
Use when ending a working session to capture lessons learned, when the user corrects Claude or asks to redo work, when the user expresses frustration with…
view-team-session
Generate a self-contained HTML viewer for any Claude Code session, including agent team sessions with full inter-agent DM timelines. Use whenever the user asks…
delegation
Turn delegation mode on or off — you orchestrate, subagents execute — for this session, this project, or your user account.
codex-mcp
Connect Codex CLI as an MCP server — giving you codex_run and codex_review as native tool calls instead of black-box bash commands. codex_run covers six modes:…
langchain
Build agents with a prebuilt architecture and integrations for any model or tool. Use when creating tool-calling agents, switching model providers, or adding…
ecosystem-primer
INVOKE FIRST for any LangChain / LangGraph / Deep Agents agent building project before consulting other skills or writing any agent code. Required starting…
agent-sdk-streaming
Stream agent output correctly — text deltas, tool-use events, thinking deltas, progress indicators — without dropping events or blocking on long tool calls.…
extended-thinking
Use Claude's extended thinking (reasoning) mode effectively — budget tokens, interleaved thinking with tool use, when it helps, when it wastes tokens, and how…
mcp-client-integration
Connect MCP servers to AI clients — Claude Desktop, Claude Code, Cursor, the Claude Agent SDK, and custom apps — including config file locations, auth, and…
mcp-server-authoring
Build production-quality MCP (Model Context Protocol) servers that expose tools, resources, and prompts to AI clients like Claude Desktop, Claude Code, Cursor,…
memory-tool
Use Claude's Memory tool to give agents persistent cross-session memory stored in a client-side file directory. Covers setup, directory layout, reading/writing…
prompt-caching-ttl
Use Claude's prompt caching with 5-minute and 1-hour TTLs to slash costs on repeated context — codebases, system prompts, long documents. Covers cache…
ai-brain
Adaptive AI memory system. Triggers on: session start, 'remember', 'learn', 'what do you know about'. Combines episodic (sessions), semantic…
paypay-securities
CLI & agent skill for a PayPay Securities (PayPay証券, ペイペイ証券) account: check portfolio, holdings, balance, investment trusts, US stocks, transaction history (取引履歴), fees &…
mcp-oauth-setup
Implement MCP server authentication with OAuth Dynamic Client Registration (RFC 7591), Authorization Server Metadata Discovery (RFC 8414), and per-agent…
skill-evaluator
Evaluate Claude Code SKILL.md quality across 6 weighted dimensions: frontmatter quality, trigger coverage, structural completeness, content depth, consistency…