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 Staking

ASecurity

Use when planning liquid staking, wrapping, restaking, delegation or queued exit claims for Lido, Rocket Pool, EigenLayer and Symbiotic.

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

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Galleon Defi Staking?

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

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

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

Files
SKILL.md
---
name: galleon-defi-staking
description: "Use when planning liquid staking, wrapping, restaking, delegation or queued exit claims for Lido, Rocket Pool, EigenLayer and Symbiotic."
license: MIT
metadata:
  version: "0.2.0"
  author: "Andrew Wilkinson and Galleon Labs"
  source: "https://github.com/galleonlabs/crypto-defi-skills"
---

# DeFi staking and restaking

Use maintained official interfaces for the selected deployment. This skill guides liquid-staking and restaking positions, not validator installation or custody. It includes no signer or automatic transaction runner.

Read the selected protocol in [providers](references/providers.md); use [workflows](references/workflows.md) for exits, accounting and evaluation cases.

## 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.

## Workflow

1. Identify chain, deployment/version, input token, receipt token, account, recipient and intended action. Separate buying an LST on a market, staking through its issuer, wrapping, restaking, and operating a validator. These create different claims and exit paths.
2. Read the exchange rate or rebasing shares, actual protocol liquidity, deposit limits, fees, pauses, current queue/epoch/cooldown state and pending request ownership. Restaking additionally requires the chosen vault/operator/network, allocation and slashing terms. A points campaign is not a promised monetary return.
3. Compare the complete lifecycle. Show principal denomination, expected receipts, yield methodology, underlying exposure, available exit routes, expected delay and loss/slashing exposure during that delay. Quote a secondary-market exit separately with price impact; never call it a protocol redemption at par.
4. Prepare the requested unsigned operation with official SDK/contracts and simulate it. Review token/spender/amount, recipient, permit deadlines, delegate/operator authority and any withdrawal credentials. Creating an EigenPod or changing validator withdrawal credentials is materially different from restaking an LST and needs specifically scoped authorization.
5. Use existing authorization only within its scope. Research or exit estimates do not authorize staking, token approvals, delegation, restaking or signing. Present the concrete plan for any missing authorization, and use the selected signer without ingesting secrets.
6. Reconcile each stage independently: preparation, authorization, signature, submission, receipt, resulting position, pending exit, claimable exit, final claim. Save request IDs, epoch or eligible block, current owner and claim recipient. A request receipt is not funds returned; an indexer's countdown is not proof of claimability. Check authoritative state before claiming or retrying an uncertain transaction.

## Report

Return chain/version and source time, underlying versus receipt units, available liquidity, current queue state and ownership, operator/curator/slashing exposure where relevant, unsigned plan and approval scope, and the verified lifecycle stage. Report a delay as an estimate unless a current contract condition proves eligibility.

Do not auto-install/connect tools, import wallet secrets, select an operator, extend authority, or schedule claims merely because these capabilities are documented. Use native harness scheduling only when monitoring is requested, with explicit targets and actionable alerts.

## Protocol-specific procedures

For a named protocol task, prefer its focused skill when installed:

- `galleon-lido-withdrawals`: Lido request IDs, NFT ownership, finalization and ETH claims.

This existing skill remains usable on its own for cross-protocol comparisons. Do not require another pack to complete its workflow.

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 →