Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Galleon Defi Infra

ASecurity

Set up and diagnose DeFi agent infrastructure, RPC access, managed wallets, payment permissions and Hermes tool connections. Use when onboarding or resolving connection failures before protocol-specific activity; market-data methodology belongs to the data workflow.

2 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentsgonodeapi

Works with

cliapimcp

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add galleonlabs/crypto-defi-skills --skill galleon-defi-infra --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Galleon Defi Infra?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Galleon Defi Infra
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/galleonlabs-galleon-defi-infra/badge)](https://www.skillsdirectory.com/skills/galleonlabs-galleon-defi-infra)

More formats (shields.io, HTML) on the badges page.

Files
SKILL.md
---
name: galleon-defi-infra
description: Set up and diagnose DeFi agent infrastructure, RPC access, managed wallets, payment permissions and Hermes tool connections. Use when onboarding or resolving connection failures before protocol-specific activity; market-data methodology belongs to the data workflow.
license: MIT
compatibility: Portable instructions; optional diagnostics require Node.js 20+ and public network access.
metadata:
  version: "0.3.0"
  author: Galleon Labs
---

# DeFi infrastructure

Make the requested agent capable of its first task through maintained provider tools. Separate installed software, available credentials, authenticated access, live reads and transaction authority; success at one does not prove the next.

## Start with the requested task

Read [task examples and user configuration](references/task-examples.md) for a completed example and recovery path. Apply only the workflow stages needed by the current request. Reuse supplied preferences and compatible tools; ask only for missing terms that affect this task. Public explanation or comparison does not require transaction fields. Keep any existing authorization within its exact scope.

## Pick the needed plumbing

- RPC and Alchemy: read [RPC and Alchemy](references/rpc-alchemy.md) to select a chain, verify node freshness and choose CLI or MCP transport.
- Wallet ownership and Coinbase: read [Managed wallets](references/wallets.md) before selecting custody, an isolated portfolio or an agent wallet. Existing exchange access is not an onchain signer.
- Paid APIs, sponsorship and scoped permissions: read [Payments and authority](references/payments.md). An HTTP 402 is a price offer, not approval to pay.
- Hermes installation and tool exposure: read [Hermes wiring](references/hermes.md). Keep Hermes as the runtime; integrate its native skills, profiles and MCP configuration instead of maintaining a fork.
- CLI prompts, authentication failures or stalled sessions: use [CLI recovery](references/cli-recovery.md) to distinguish missing access from transport and uncertain writes.
- Broken connectivity: use [Readiness diagnostics](references/readiness.md) for a bounded, read-only probe and a precise readiness report.

Start with the user's selected chain and task. Read-only research needs RPC or indexed data, not a newly created wallet. Reuse an existing compatible provider connection when its account and permissions match; do not install every wallet product. Keep seed phrases and private keys outside agent prompts, repository files and diagnostic logs.

Read [primitive tool wiring](references/primitive-tools.md) for official MCP/SDK selection, progressive disclosure, schema changes and EVM/Solana transaction context.

## First usable result

For example, given “Check whether my existing Base RPC is ready; do not create a wallet,” load the readiness reference, run its bounded chain and freshness check, and report the observed chain ID and block time. A response from a different chain or a stale node is a failed readiness check even when the connection succeeds. If the endpoint is missing, identify the required environment setting without requesting its secret value in chat.

Record the runtime/profile, provider, chain ID, tool or CLI version, authentication state, successful read with timestamp, and remaining limitation. For a signer also record its owner, active account, supported actions, spending/contract/chain limits, expiry and revocation path. Report unknown permission enforcement as unknown, rather than treating a prompt as a wallet policy.

A missing dependency or expired session should produce the exact relevant setup step. Authentication that creates an account, wallet, signer session or new spending permission requires the user's authorization for that action; installing a skill does not provide it. Preserve existing authorization when its scope still matches.

After onboarding, hand the verified chain/account/capabilities to the requested protocol, portfolio, payments, governance or data workflow if present. This pack supplies infrastructure procedures and diagnostics; it does not execute a trade, fund a wallet or implement a signer.

## Named provider procedures

For Coinbase AgentKit readiness, use `galleon-coinbase-agentkit-readiness` when installed. This generic skill remains independently usable for setup and cross-provider work.

Attribution

galleonlabsgalleonlabs
View sourceMore from galleonlabs →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

695601 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →