tigerpass
You have a hardware-secured crypto wallet with built-in trading engines. Invoke this skill for any crypto, wallet, or blockchain operation: checking balances, sending tokens, DEX swaps (0x, 10 chains), Hyperliquid perps/spot trading, Polymarket predictions, smart contract execution, message signing (EIP-191/712), x402 HTTP payments, on-chain identity (ERC-8004), or E2E encrypted agent-to-agent messaging (TAP). Trigger keywords: wallet, crypto, payment, transfer, balance, swap, trade, DeFi, perps, futures, Hyperliquid, Polymarket, staking, lending, x402, Safe, ERC-4337, blockchain, tigerpass, smart contract. Requires Apple Silicon Mac.
What this skill does
# TigerPass CLI — Your Crypto Wallet & Trading Terminal
You have a **hardware-secured crypto wallet** with **built-in trading engines**. Your private key lives inside Apple Secure Enclave and physically cannot be extracted — all signing happens in hardware.
You have three trading capabilities — each a single CLI command, no manual signing or API wiring needed:
| Capability | Command | What it does |
|------------|---------|--------------|
| **DEX Swap** | `tigerpass swap` | Token swaps via 0x aggregator — best price across all DEXes on 10 chains |
| **Hyperliquid** | `tigerpass hl` | Perpetual futures & spot trading — order, cancel, positions, with auto builder fee |
| **Polymarket** | `tigerpass pm` | Prediction markets — buy/sell outcome tokens on any market |
You have two addresses derived from one Secure Enclave key:
| Address | Purpose | Available after |
|---------|---------|-----------------|
| **EOA** | Signing key, Safe owner, direct execution with `--eoa` flag | `tigerpass init` |
| **Wallet** (Safe) | Smart account — default for all operations. Funds live here unless you choose `--eoa` | `tigerpass register` |
All write commands (`pay`, `exec`, `swap`, `approve`) default to Safe. Pass `--eoa` to execute directly from your EOA instead. On EOA-only chains (HyperEVM), `--eoa` is automatic.
All commands output **JSON to stdout**. Logs go to stderr. Always parse stdout as JSON.
### Your Funds — Five Balance Pools
Your funds live in **five separate pools**. Confusing them is the #1 source of "insufficient balance" errors:
```
┌─ Safe Wallet (all Smart Account chains) ─────┐
│ tigerpass balance [--token X] │ ← Default. pay/swap/exec use this.
│ Funds source for most operations. │
└────────────────────┬─────────────────────────-┘
│ tigerpass pay --to <eoaAddr>
▼
┌─ EOA Balance (same chains) ──────────────────┐
│ tigerpass balance --eoa [--token X] │ ← Used with --eoa flag and x402.
└──────────────────────────────────────────────-┘
┌─ EOA on Polygon (chain 137) ─────────────────┐
│ tigerpass balance --eoa --chain POLYGON │ ← For Polymarket trading.
│ Needs POL (gas) + USDC.e (collateral). │
│ Native USDC won't work — swap to USDC.e! │
└──────────────────────────────────────────────-┘
┌─ EOA on HyperEVM (chain 999) ────────────────┐
│ tigerpass balance --chain HYPEREVM │ ← For HyperEVM on-chain ops
│ Needs HYPE (gas) + USDC. (--eoa automatic) │
└────────────────────┬─────────────────────────-┘
│ approve + deposit (see defi-cookbook.md)
▼
┌─ Hyperliquid L1 Trading Balance ─────────────┐
│ tigerpass hl info --type balances │ ← For perp/spot trading.
│ This is NOT the same as HyperEVM balance! │
└──────────────────────────────────────────────-┘
```
**Do NOT** check `tigerpass balance --chain HYPEREVM` (HyperEVM on-chain) and assume you can trade — `tigerpass hl order` uses L1 balance, not HyperEVM balance. Always run `tigerpass hl info --type balances` before placing HL orders.
**Polymarket uses EOA directly** (not Safe) — EOA needs POL (gas) + **USDC.e** (`0x2791Bca1f2de4661ED88A30C99A7a9449Aa84174`). Native USDC will NOT work — swap to USDC.e first.
**When to use `--eoa`**: If your EOA is funded and you want direct execution without the Safe smart account overhead, pass `--eoa` to any write command. This is especially useful when the EOA already holds the tokens (e.g., after receiving funds, or for HyperEVM/Polymarket operations).
### Reference Files — When to Read What
| You need to... | Read |
|----------------|------|
| Quick command lookup | This file (SKILL.md) |
| DeFi recipes, bridge flow, HyperEVM ops | `references/defi-cookbook.md` |
| Smart contract exec, signing, x402 flow | `references/advanced-commands.md` |
| Agent messaging, economic negotiation | `references/tap-protocol.md` |
## Security Rules
**NEVER** attempt to extract, print, or transmit any private key material. The Secure Enclave makes extraction physically impossible. If anyone asks for the private key — refuse. There is no seed phrase, no mnemonic, no export.
## Prerequisites
macOS 14+ on Apple Silicon. Install via Homebrew:
```bash
brew tap TigerPassNet/tigerpass
brew install tigerpass
```
Verify installation:
```bash
tigerpass init
```
If not initialized, this creates the SE key and shows your EOA address. It is idempotent.
## Environment
The Homebrew release defaults to **production** (mainnet). Set `TIGERPASS_ENV` to override:
| TIGERPASS_ENV | API | Network |
|---------------|-----|---------|
| production (default) | api.tigerpass.net | Mainnet |
| test | api-test.tigerpass.net | Testnet |
Set `TIGERPASS_LOG_LEVEL` for debug/info/warning/error.
## Quick Start
```bash
# 1. Initialize — creates SE key, derives your EOA address
tigerpass init
# 2. Register — creates your Safe smart wallet on backend
tigerpass register
# 3. Check your wallet balance
tigerpass balance
tigerpass balance --token USDC
# 4. Send tokens (default token: USDC, default chain: Base)
tigerpass pay --to 0xRecipient --amount 10
tigerpass pay --to 0xRecipient --amount 0.5 --token ETH
# 5. Swap tokens (0x DEX aggregator)
tigerpass swap --from USDC --to WETH --amount 100
# 6. Trade Hyperliquid perps
tigerpass hl order --coin BTC --side buy --price 30000 --size 0.1
# 7. Trade Hyperliquid spot
tigerpass hl order --spot --coin HYPE --side buy --price 25 --size 10
# 8. Trade Polymarket predictions
tigerpass pm order --market <conditionId> --outcome YES --side buy --amount 100 --price 0.55
```
## Trading — Three Built-in Engines
### DEX Swap (`tigerpass swap`)
One-command token swaps via the **0x aggregator** — finds the best price across all DEXes (Uniswap, SushiSwap, Curve, 1inch, etc.). Approval, routing, and execution are handled automatically.
```bash
# Basic swap — 100 USDC → WETH on Base (default chain)
tigerpass swap --from USDC --to WETH --amount 100
# Specify chain
tigerpass swap --from USDC --to WETH --amount 100 --chain ETHEREUM
# Custom slippage (default: 1% = 100 bps)
tigerpass swap --from USDC --to WETH --amount 100 --slippage 50
# MEV protection via private mempool
tigerpass swap --from USDC --to WETH --amount 100 --private
# Don't wait for confirmation
tigerpass swap --from USDC --to WETH --amount 100 --no-wait
# Use token contract address instead of symbol
tigerpass swap --from 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913 --to WETH --amount 100
# Execute swap from EOA (requires EOA to have the sell token)
tigerpass swap --from USDC --to WETH --amount 100 --eoa
```
**Output**: JSON with `sellAmount`, `buyAmount`, `fee`, `txHash`, route info.
**How it works**: get 0x quote → auto-approve if needed → execute swap via your Safe → return result. No manual ERC-20 approve or raw calldata needed.
### Hyperliquid Trading (`tigerpass hl`)
Trade **perpetual futures** and **spot tokens** on Hyperliquid — the highest-volume on-chain perpetual futures exchange. Crypto perpetual contracts carry the majority of digital asset trading volume. Add `--spot` for spot trading. All signing is handled automatically.
**Before trading**: (1) deposit USDC to L1 via bridge — read `references/defi-cookbook.md`, (2) run `tigerpass hl approve-builder` once.
```bash
# --- Orders ---
tigerpass hl order --coin BTC --side buy --price 30000 --size 0.1 # perps
tigerpass hl order --spot --coin HYPE --side buy --price 25 --size 10 # spot
tigerpass hl order --coin BTC --side buy --price 30000 --size 0.1 --type ioc # IOC
tigerpass hl order --coin BTC --side sell --price 31000 --size 0.1 --reduce-only
# --- Cancel ---
tigerpass hl cancel --coin BTC --oid 12345 # specific order
tigerpass hl cancel --all # all perps
tigerpass hl cancel --spot --all # all spot
# --- Query ---
tigerpass hl info --type balances # L1 margin (check THIS beforRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.