Agents
AI agents and automation
fluxa-agent-wallet
by FluxA-Agent-Payment
FluxA Agent Wallet integration via CLI. Enables agents to make x402 payments for paid APIs, send USDC payouts to any wallet, and create payment links to receive payments. Use when the user asks about crypto payments, x402, USDC transfers, payment links, or interacting with the FluxA Agent Wallet.
dispatching-parallel-agents
by Cygnusfear
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
horizon-golden-demo
by sfc-gh-tquinones
"Run the Horizon Catalog Golden Demo end-to-end. Two modes: (1) SETUP — provisions all Snowflake objects, AWS IAM config, sample data, policies, views, semantic view, and agent from scratch; (2) WALK-THROUGH — guides the presenter through each of the 5 acts live. Triggers: horizon demo, golden demo, run horizon demo, setup horizon demo, horizon walkthrough, governance demo, catalog demo, teardown horizon demo."
marketplace-earning
by coopergwrenn
Earn money autonomously via Clawlancer bounties and digital product creation on external marketplaces. Use when the user asks how to earn money, create products, sell services, find gigs, or generate passive income.
AI Engineer
by anorbert-cmyk
AI Engineer building LLM features with focus on reliability, evals, cost control, latency, and user trust.
devdocs-onboard
by ab300819
Generate project context summary for AI tool handover. Use when switching AI tools, starting new sessions, or onboarding team members. Triggers on keywords like "project context", "handover", "onboard", "项目上下文", "交接", "接手项目".
Code to Paper
by midhunxavier
Meta workflow skill for transforming code to paper. Provides interactive guidance for the complete workflow from code implementation to published paper.
agents-md
by CacaoRick
引導 AI Agent 閱讀並遵守專案的 AGENTS.md 規範。AGENTS.md 是給 AI 看的專案說明文件，定義了技術棧、資料夾架構、專案架構、開發流程等約束。Use when：任何任務開始前、需要了解技術棧、資料夾架構、專案架構、開發流程時。AI Agent 不可做出違抗 AGENTS.md 的行為。
review
by pmco23
Use after /design to adversarially review the design document. Dispatches strategic-critic (Opus) and code-critic (Sonnet) in parallel — Opus for strategic critique grounded in Context7, Sonnet for code-grounded critique against the existing codebase. Lead deduplicates, runs cost/benefit analysis, loops until all MUST FIX findings resolve. Writes .pipeline/design.approved on loop exit.
Agent Design 2
by hhopkins95
This skill should be used when the user asks to "configure agent profile", "add skills to agent", "set up MCP servers", "configure agent tools", "write system prompt", "create agent workflow", "define agent commands", "add subagents", or needs to define what capabilities an agent has and how to orchestrate complex workflows in the runtime.
onboarding-ux
by moderndegree
First-time user experience, tooltips, guided tours, and feature discovery. Use when creating onboarding flows, tours, or user education.
proactive-amcp
by fcavalcantirj
Agent Memory Continuity Protocol - encrypted checkpoints of your agent's soul, memories, and secrets to IPFS. Never lose your agent again.
research
by keenranger
Research topics via codebase exploration or external documentation. Use when user asks to research, explore, investigate, or says /research.
fund-wallet
by agnicpay
Get instructions for funding your AgnicPay wallet with USDC. Use when you or the user want to add funds, deposit USDC, top up the wallet, or need more balance. Covers phrases like "add funds", "deposit", "top up", "fund my wallet", "how do I get USDC", "need more balance".
eval-core-scorecard
by whitespectre
Runs the core evaluation dimensions (clarity, relevance, accuracy, tone/empathy, guidance/actionability, conversation flow, boundary adherence) and returns a single strict JSON scorecard for continuous monitoring/logging.
dewey-docs
by arach
Generate AI-agent-ready documentation and static doc sites using Dewey. Use when asked to "set up docs", "create documentation", "make docs agent-friendly", "generate AGENTS.md", "add llms.txt", or "create a doc site".
clawlancer
by coopergwrenn
"Earn USDC autonomously. Clawlancer is where AI agents find paid work\u2014research, coding, writing, analysis\u2014complete it in seconds, and get paid automatically. Fastest setup: npx clawlancer-mcp (one command, full access). Bounties are pre-funded (free to claim), payments go to trustless escrow, and your reputation builds on-chain (ERC-8004). First 100 agents get free gas. 16 agents already earning, 13 transactions completed, 100% success rate so far. All payments in USDC on Base mainnet."
base-account
by hk-vk
Base Account is a passkey-secured, ERC-4337 smart wallet with one‑tap payments, spend permissions, and sub‑accounts—built for seamless multi‑chain apps.
codebase-context
by alexandephilia
Automatically discovers and indexes project structure, component signatures, types, and dependencies. Use this skill when you need comprehensive context about the current codebase before making changes. Activates via /context command or when deep codebase understanding is required.
codex-autoresearch
by luizgustavo22
"Autonomous long-running iteration for Codex CLI. Use when the user wants Codex to plan or run an unattended improve-verify loop toward a measurable or verifiable outcome, especially for overnight runs; it also covers repeated debugging, fixing, security auditing, and ship-readiness workflows. Do not use for ordinary one-shot coding help or casual Q&A."
atm-detection
by jefrnc
Use when determining whether a company has an active At-The-Market (ATM) offering, controlled equity offering, or equity line (ELOC). Defines the multi-signal inference required to distinguish ACTIVE dilution from dormant shelf capacity, and disambiguates ATM from ELOC.
github
by yousufjoyian
Clone, pull, and manage GitHub repositories using SSH authentication. Handles yousufjoyian repos and third-party repos.
news-intel
by chess99
科技资讯日报生成入口。每天 09:00 CST 由 cron 触发。 当用户提到"发资讯"、"今日日报"、"科技新闻"、"资讯群"、"日报"时触发。 三阶段流程：orchestrator 选文章 → analyst 并行分析 → reporter 生成日报。
deep-plan
by idrevnii
Structured clarification before decisions. Use when user is in PLANNING mode, explicitly asks to plan or discuss, or when agent faces choices requiring user input. Ensures agent asks questions instead of making autonomous decisions when multiple valid approaches exist or context is missing.