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

Hyperliquid Monitor

ASecurity

Reconcile a Hyperliquid account, position, order, fill, funding stream, liquidation buffer, or watch from current exchange data. Use when the user asks what is open, whether protection exists, whether an order filled, how close liquidation is, what changed, or to watch and alert on a condition. Read-only; not for placing, changing, or canceling orders.

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

Works with

api

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add galleonlabs/crypto-defi-skills --skill hyperliquid-monitor --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Hyperliquid Monitor?

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

Security grade badge for Hyperliquid Monitor
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/galleonlabs-hyperliquid-monitor/badge)](https://www.skillsdirectory.com/skills/galleonlabs-hyperliquid-monitor)

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

Files
SKILL.md
---
name: hyperliquid-monitor
description: "Reconcile a Hyperliquid account, position, order, fill, funding stream, liquidation buffer, or watch from current exchange data. Use when the user asks what is open, whether protection exists, whether an order filled, how close liquidation is, what changed, or to watch and alert on a condition. Read-only; not for placing, changing, or canceling orders."
license: MIT
compatibility: "Requires read-only Hyperliquid API access and the user account address. The bundled funding script needs Node.js 20 or newer."
metadata:
  version: "0.3.4"
  protocol: "hyperliquid"
---

# Hyperliquid monitor

Reconstruct current exchange state and distinguish safe, triggered, and unavailable observations.

If a skill rule blocks progress, cite its file and exact rule, explain the missing input or authority, and continue independent work within this skill's boundary. User instructions govern workflow and style defaults; they do not bypass tool or financial controls.

## Tool selection

When connecting or choosing tools, read [official tools](references/official-tools.md). Reuse a suitable maintained upstream capability before implementing new integration code; tool adoption stays optional and never supplies wallet authority.

## First task and connected workflow

Reconcile one requested public user account from read-only tools and report positions, protection, timestamps and gaps. A failed read is unavailable, never an empty healthy account. Read [agent integration and handoffs](references/agent-integration.md) on first use or when a tool or related skill is missing.

## Task handling

Reuse the requested account or position identity, then verify it from current reads. Ask only for missing identity or monitoring constraints; never substitute another account. Finish unaffected checks when a source fails and mark the affected result unavailable. Report the current state, material changes, and next required read concisely, retaining the output contract.

## Workflow

1. Bind the network, user account address, account abstraction mode, DEX, markets, observation time, freshness bound, and requested condition.
2. Read [authoritative state](references/authoritative-state.md). Query the account or subaccount being monitored, never the API wallet address.
3. Reconcile positions, balances, open orders, trigger details, order status, fills, funding, ledger updates, fee tier, and action budget. Under unified or portfolio margin, include spot clearinghouse and borrow/lend state.
4. Check every open position against [protection and incidents](references/protection-and-incidents.md). Match stop side, reduce-only state, trigger, size, and position-tied status.
5. Normalize funding by its stated interval. Use `node scripts/funding.mjs --help` for arithmetic. Preserve funding signs from the account's perspective.
6. For continuous work, use [stream discipline](references/stream-discipline.md). Snapshot first, deduplicate, heartbeat, detect gaps, and reconcile after reconnect.
7. Evaluate the condition as exactly one of `triggered`, `not-triggered`, or `unavailable`. A failed, empty, stale, partial, or gapped read is unavailable.
8. Emit [the monitor contract](references/output-contract.md). Alerts state facts and open a plan; they never act.

## Hard rules

- `frontendOpenOrders` or an equivalent detailed stream is required to prove trigger and reduce-only properties.
- Order response text is not final state. Use order status, open orders, fills, and position state together.
- `liquidationPx` is a live estimate. Cross, unified, and portfolio modes couple risk across positions and balances.
- The first fills message on a subscription may be a snapshot. Do not alert on it as new activity.
- An open candle changes until close. Label intrabar signals.
- WebSocket reconnect without backfill creates an unknown interval.
- A scheduled cancel can remove protective stops. It is not a position-aware safety system.

## Boundary

Do not place, modify, cancel, close, change leverage, transfer, or submit any exchange action. State the exact next read or unsigned action needed. Route a requested action to `hyperliquid-plan` or `hyperliquid-execute`.

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 →