Agent Workflow Skills

> Use this skill when a design or idea requires higher confidence, risk reduction, or formal review. This skill orchestrates a structured, sequential multi-agent design review where each agent has a strict, non-overlapping role. It prevents blind spots, false confidence, and premature convergence.

Master orchestrator, peer-to-peer, and hierarchical multi-agent architectures

Master on-call shift handoffs with context transfer, escalation procedures, and documentation. Use when transitioning on-call responsibilities, documenting shift summaries, or improving on-call processes.

Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.

Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache augmented.

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, or debug agent behavior.

Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks.

-Automatically convert documentation websites, GitHub repositories, and PDFs into Claude AI skills in minutes.

Opinionated, evolving constraints to guide agents when building interfaces

Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits

Use when creating, updating, or improving agent skills.

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

Quick reference for ponytail's modes, skills, and commands. One-shot display.

> Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

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 Codex's capabilities with specialized knowledge, workflows, or tool integrations.

Guides human users' AI agents to the NemoClaw docs MCP server and canonical Fern documentation in Markdown form. Use when users ask how to install, configure, operate, troubleshoot, secure, or learn NemoClaw with an AI coding assistant. Trigger keywords - nemoclaw docs, use nemoclaw with ai agent, nemoclaw mcp docs, nemoclaw install help, nemoclaw quickstart, nemoclaw markdown docs, llms.txt, agent skills.

Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.

Run evaluations for one, multiple, or all skills using the agent orchestration framework. Make sure to use this skill whenever the user asks to run evals, test a skill's performance, run benchmarks, or compare baseline versus with-skill execution.

Agent Context Isolation

Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication

Find and resume interrupted Copilot CLI sessions using session_store queries

Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.

Entry point for Internet Court — the trust layer for agent-to-agent commerce. Use whenever an agent needs to transact with another agent or a paid service, or a user mentions agent payments, paid APIs (HTTP 402/x402), wallet custody or trust concerns, spending mandates, delegated permissions (ERC-7710/7715), escrow, agent identity or reputation (ERC-8004), negotiation between agents (A2A), agent jobs (ERC-8183), machine payments (MPP, AP2), supervision of agent behavior, revocation, verification, or dispute resolution (GenLayer) — even if they never say "Internet Court". Routes to the vendored protocol skills and connector skills in this package.

Use this skill when the user wants to launch a new AltClaw, OpenClaw, PicoClaw, or Ottie deployment through Cloud Claw. Covers the same user-facing fields and constraints exposed in the Cloud Claw UI, using the local altllm cloud-claw-* commands. Do NOT use for post-launch lifecycle tasks like start/stop/delete/logs; use cloud-claw-manage-vm.

Use this umbrella skill when the request spans multiple Cloud Claw user-facing domains, especially launching a new AltClaw or OpenClaw VM and then managing lifecycle, logs, renewal, or dashboard access through the local altllm cloud-claw-* commands in this repository.

BNB Chain MCP server connection and tool usage. Covers npx @bnb-chain/mcp@latest, PRIVATE_KEY and RPC, and every MCP tool — blocks, transactions, contracts, ERC20/NFT transfers, wallet, ERC-8004 agent registration, Greenfield. Use when connecting to bnbchain-mcp, querying or transacting on BNB Chain/opBNB/EVM, registering as ERC-8004 agent, or using Greenfield.

Give the AI agent its own EVM wallet with admin-controlled policies the agent CANNOT bypass even under prompt injection. Encrypted keystore (AES-256-GCM, scrypt KDF), policy file the agent has no tool to write, deterministic policy gate on every signing operation, optional local HTTP dashboard. Triggers: agent wallet, give the agent a wallet, agent address, fund the agent, agent autonomy, policy gate, kill switch, agent permissions, bounded autonomy, ERC-4337 alternative, session-key alternative.

Upload files to IPFS through the Kleros x402 payment gateway in exchange for $0.01 USDC on Base mainnet. Use this skill **specifically** when the user is uploading content destined for the Kleros ecosystem — dispute evidence, meta-evidence JSON, court / dispute / arbitrator policies, Curate item metadata, juror justifications, or any artifact a Kleros smart contract or subgraph will reference by IPFS CID. Trigger when the request mentions Kleros, a court / arbitrator / dispute / juror / curate / proof-of-humanity context, or any of the conventional Kleros operation tags (evidence, meta-evidence, justification). Do NOT trigger for generic 'upload to IPFS' / 'get me a CID' requests with no Kleros context — point those users at Pinata, web3.storage, or any general-purpose pinning service instead. Exception: if the user explicitly names this gateway (kleros-ipfs-gateway.fly.dev / kleros-api.netlify.app/.netlify/functions/upload-to-ipfs), explicitly requests this skill, or asks the agent to test / validate / sanity-check this gateway or skill, trigger regardless of topical context — a deliberate end-to-end test is a valid trigger.

Use when an agent hits HTTP 402 / payment-required, or the user mentions x402, x402Version, X-PAYMENT, PAYMENT-REQUIRED, PAYMENT-SIGNATURE, WWW-Authenticate: Payment, permit2, upto, metered billing, a payment channel / voucher / session, channelId / channel_id, opening / closing / topping up / settling / refunding a channel, a paymentId or a2a_ link, creating / checking a payment link, A2MCP / an A2MCP endpoint, or sending a request to / calling an Agent's endpoint with a concrete endpoint URL. Covers x402 (exact, exact+Permit2, upto, aggr_deferred), MPP (charge / session), and a2a-pay paymentId flows. Any close / topup / settle / voucher / refund near a channel_id or session is an MPP mid-session op. The full bilingual trigger list (including Chinese) lives in the skill body.

> provider/change budget/修改卖家/修改预算/draft/草稿/我的任务/my tasks/what am I working on/关闭/取消任务/决策列表/decision list/指定服务商/browse (sender.role = COUNTERPARTY, not you); (3) literal "Read the okx-ai skill" (or legacy "Read the okx-agent-task skill") in the envelope.

Onchain OS onboarding & guide hub — the single entry for first-time, 'what is this / how do I use it', OKX.AI, and customer-support intents; classifies the intent and routes to the right sub-flow via its Intent Routing table. Covers: (1) Onchain OS onboarding + welcome banner — 'what is onchainos', 'what is onchain os', 'what can it do', 'what can onchainos do', 'what does onchainos do', 'how do I use this', 'how do I play', 'how to use onchainos', 'how to play onchainos', 'how does onchainos work', 'how do I start', 'getting started', 'tutorial', 'onboarding', 'first time', 'I just installed', 'now what', 'what do I do now', 'where do I start', 'who are you', 'what are you', 'introduce onchainos', 'tell me about onchainos', 'I'm new'; (2) OKX.AI intro & role-registration routing (the Agent economic system — roles User / ASP / Evaluator) — 'what is OKX.AI', 'OKX.AI 是什么', 'how to use OKX.AI', 'OKX.AI 快速开始', and any spelling / spacing / casing / typo variant (OKXAI, okx ai, okx-ai, lowercase okx.ai, 啥是okxai); (3) customer support / Help Center — 'contact support', 'talk to a human', 'customer service', 'file a complaint', 'give feedback', 'report a bug / system error', 'help center', 'FAQ', 'user guide', 'something is broken'. NOT for: direct on-chain actions (swap / wallet / balance / token) or Agent task lifecycle (publish / accept / deliver / dispute) — those have their own skills.

Register AI agents on-chain using the ERC-8004 Trustless Agents standard. Manage agent identity as NFTs, build reputation through feedback, and request third-party validation.

Create and manage Starknet wallets for AI agents. Transfer tokens, check balances, manage session keys, deploy accounts, and interact with smart contracts using native Account Abstraction.

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.

Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmi_path, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar. USE FOR: Agent Identity Blueprint, BlueprintPrincipal, agent OAuth, fmi_path token exchange, agent OBO, Workload Identity Federation for agents, polyglot agent auth, Microsoft.Identity.Web.AgentIdentities. DO NOT USE FOR: standard Entra app registration (use entra-app-registration), Microsoft Foundry agent authoring (use microsoft-foundry).

> Use this skill when a user wants to create, run, or analyze evaluation suites for Microsoft 365 Copilot declarative agents with the public @microsoft/m365-copilot-eval CLI. Trigger on intents such as "evaluate my agent", "test my agent", "run my evals", "create eval prompts", "add multi-turn tests", "tune evaluator thresholds", "why is my agent failing", or "set up eval environment variables".

Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns

Creates a new Angular app using the Angular CLI. This skill should be used whenever a user wants to create a new Angular application and contains important guidelines for how to effectively create a modern Angular application.

> Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

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 examples', 'agent tools', 'agent colors', 'autonomous agent', or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

> Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. "save context", "compressed agent output".

> Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.

Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.

Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.

The 100th skill! Your intelligent guide to all 99 other skills. Recommends the perfect skill for any task, creates skill combinations, and helps you discover capabilities you didn't know you had.

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.