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 Derivatives

ASecurity

Assess perpetuals, options and funding-rate derivatives, prepare bounded exposure plans, and reconcile order and margin state. Use when comparing GMX, Drift, Derive, Jupiter Perps or Boros, planning hedges, monitoring positions or recovering orders.

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

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Galleon Defi Derivatives?

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

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

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

Files
SKILL.md
---
name: galleon-defi-derivatives
description: Assess perpetuals, options and funding-rate derivatives, prepare bounded exposure plans, and reconcile order and margin state. Use when comparing GMX, Drift, Derive, Jupiter Perps or Boros, planning hedges, monitoring positions or recovering orders.
license: MIT
compatibility: Portable Agent Skills instructions. Live work needs official venue data and optional user-authorized wallet tooling. No signer, provider or runtime is installed by this skill.
metadata:
  author: Galleon Labs
  version: "0.1.4"
---

# DeFi derivatives

Translate a market or hedge request into explicit exposure, collateral requirements and venue-specific order evidence. Reuse official tooling; keep research, planning and authorized execution distinct.

## 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.

## Select the product and tools

Read [providers](references/providers.md) for GMX, Drift, Derive, Jupiter and Boros, their official integration surfaces and version gaps. Read [workflows](references/workflows.md) for risk planning and order reconciliation. [Evaluation cases](references/evaluation.md) provide bounded fixture scenarios.

For Hyperliquid, use the installed `hyperliquid-analyze`, `hyperliquid-plan`, `hyperliquid-execute` or `hyperliquid-monitor` skill when available. This pack provides the cross-venue comparison and handoff; it does not reproduce Hyperliquid signing or nonce rules. No other pack is required for the general workflow here.

## Define the exposure

Identify network, protocol version, exact instrument/market, expiry, payoff denomination, collateral, margin mode, owner, subaccount and signer role. An ETH perpetual, an ETH option and an ETH funding-rate contract are different exposures. Do not normalize them into a single token price or label annualized funding as guaranteed yield.

Obtain fresh oracle/mark/index prices, order book or available capacity, current positions and orders, balances, margin requirements and accrued funding/borrow costs. State the observation time and source. Missing account data prevents a personalized risk or execution-ready claim; public market analysis can still proceed.

## Build a bounded plan

Use the user's existing risk budget and approved terms. Specify size in both native venue units and economic notional, side, order type, limit/acceptable price, maximum slippage, collateral change, leverage/margin mode, expiry, reduce-only intent, fee recipients and maximum costs. Stress adverse price, funding, volatility and exit liquidity; calculate combined exposure across existing orders and positions, not just the new order. A stop order may trigger without filling.

For options include premium, contract multiplier, settlement asset, exercise/expiry model and uncovered short liability. For funding-rate hedges include settlement period, rate convention, maturity, collateral and basis mismatch against the exposure being hedged. A hedge across venues creates separate liquidation and settlement risks.

## Authorize and reconcile

Use the official builder within the user's established execution boundary. A delegated key with limited withdrawals can still lose trading collateral. Granting or renewing delegation, changing margin mode, depositing and withdrawing are distinct financial actions; none is incidental setup. Never handle a key, create an agent wallet, insert a fee recipient or authorize a trade from this skill's presence.

Before manual changes to a managed account, read [account control](references/account-control.md) to reconcile active bots, open orders and an authorized handoff.

Follow [the venue lifecycle](references/workflows.md): persist operation identity; separate prepared, submitted, created/resting, partially filled, executed, cancelled and unknown states; reconcile authoritative fills and account changes. Resolve unknown outcomes before retries. A keeper-created order, relayer acceptance or successful transport response is not a completed trade. Cancel and replace can race with fills; reread both before calculating remaining size.

## Deliver

Return the market answer, comparison or proposed ticket with exact instrument and account identity, exposure, downside constraints, costs, source times, supported capabilities and material gaps. For monitoring, report position/order/margin changes with trigger conditions and a bounded next action. Creating a schedule, starting continuous trading or changing an existing automation requires the user's actual request; the skill does not start a background service.

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 →