Senpi Trading Runtime Contract
Senpi-ai/senpi-skills
Documents how a Senpi strategy's scan function talks to the runtime that schedules it, sizes orders, and manages stop-loss exits on Hyperliquid.
First-time setup — from zero to first trade on Hyperliquid. An agent skill from Nunchi-trade/agent-cli.
$ npx skills add Nunchi-trade/agent-cli --skill agent-onboarding -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Nunchi-trade/agent-cli agent-onboarding --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Nunchi-trade/agent-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/onboard .claude/skills/agent-onboarding && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "agent-onboarding" agent skill from https://github.com/Nunchi-trade/agent-cli/tree/main/skills/onboard into .claude/skills/agent-onboarding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-onboarding", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Nunchi-trade/agent-cli/tree/main/skills/onboardType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Nunchi-trade/agent-cli --skill agent-onboarding -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Nunchi-trade/agent-cli agent-onboarding --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Nunchi-trade/agent-cli.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/onboard .agents/skills/agent-onboarding && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-onboarding" agent skill from https://github.com/Nunchi-trade/agent-cli/tree/main/skills/onboard into .agents/skills/agent-onboarding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-onboarding", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Nunchi-trade/agent-cli --skill agent-onboarding -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Nunchi-trade/agent-cli agent-onboarding --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Nunchi-trade/agent-cli.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/onboard .cursor/skills/agent-onboarding && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agent-onboarding" agent skill from https://github.com/Nunchi-trade/agent-cli/tree/main/skills/onboard into .cursor/skills/agent-onboarding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-onboarding", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Nunchi-trade/agent-cli.git --path skills/onboard--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Nunchi-trade/agent-cli --skill agent-onboarding -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Nunchi-trade/agent-cli agent-onboarding --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Nunchi-trade/agent-cli.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/onboard .gemini/skills/agent-onboarding && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agent-onboarding" agent skill from https://github.com/Nunchi-trade/agent-cli/tree/main/skills/onboard into .gemini/skills/agent-onboarding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-onboarding", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Nunchi-trade/agent-cli agent-onboardingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Nunchi-trade/agent-cli --skill agent-onboarding -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Nunchi-trade/agent-cli.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/onboard .github/skills/agent-onboarding && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agent-onboarding" agent skill from https://github.com/Nunchi-trade/agent-cli/tree/main/skills/onboard into .github/skills/agent-onboarding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-onboarding", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Nunchi-trade/agent-cli --skill agent-onboarding -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Nunchi-trade/agent-cli agent-onboarding --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Nunchi-trade/agent-cli.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/onboard .opencode/skills/agent-onboarding && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agent-onboarding" agent skill from https://github.com/Nunchi-trade/agent-cli/tree/main/skills/onboard into .opencode/skills/agent-onboarding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-onboarding", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
agent-onboardingFirst-time setup — from zero to first trade on Hyperliquid. An agent skill from Nunchi-trade/agent-cli.
Agent Onboarding is an agent skill from Nunchi-trade/agent-cli. First-time setup — from zero to first trade on Hyperliquid
Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Business, Finance & HR. It works with Hyperliquid and Python. The licence is MIT.
9 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 58619a2. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
pippython3bashbrewFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
HL_KEYSTORE_PASSWORDHL_PRIVATE_KEYANTHROPIC_API_KEYGEMINI_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Agent Onboarding loads about 2.1k tokens when it runs. Until then it costs about 19 tokens; SKILL.md has 919 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from Nunchi-trade/agent-cli at commit 58619a2, republished under its MIT licence (© Nunchi-trade). 919 words, ~2,138 tokens.
.claude/skills/agent-onboarding/SKILL.md (or your agent's skills folder).Complete first-time setup for the YEX autonomous trading system on Hyperliquid. Follow every step in order. Do not skip steps. Verify each step before proceeding to the next.
You are onboarding onto the YEX trading system. Your goal is to reach a state where you can autonomously trade on Hyperliquid (testnet or mainnet). Every step has a verification command — if verification fails, fix the issue before continuing.
RULES:
Install Python dependencies and verify the CLI works.
Option A — Shell script (recommended):
cd ~/agent-cli
bash scripts/bootstrap.shOption B — Manual:
cd ~/agent-cli
python3 -m venv .venv
source .venv/bin/activate
pip install -e .Verify:
hl setup checkExpected: All items show OK, no !! issues (except missing key — that's Step 2).
If fails:
| Error | Fix |
|---|---|
python3 not found | Install Python 3.10+ via brew install python or system package manager |
pip install failed | Ensure you're in a venv: source .venv/bin/activate |
ModuleNotFoundError: hyperliquid | Run pip install hyperliquid-python-sdk |
Create or import a Hyperliquid wallet.
Decision tree:
hl wallet import --key 0x<your_key>hl wallet auto --save-env --jsonHL_KEYSTORE_PASSWORD to ~/.hl-agent/env (auto-detected by CLI), and outputs JSON: {"address": "...", "password": "...", "keystore": "...", "env_file": "..."}.If you used --save-env, the CLI auto-detects the password from ~/.hl-agent/env — no manual export needed.
If you did NOT use --save-env, set the keystore password manually:
export HL_KEYSTORE_PASSWORD=<password>Verify:
hl wallet listExpected: At least one address shown.
If fails:
| Error | Fix |
|---|---|
No keystores found | Run hl wallet auto |
eth_account not installed | Run pip install eth-account>=0.10.0 |
Choose testnet (default, recommended for first run) or mainnet.
Testnet (default):
export HL_TESTNET=trueMainnet:
export HL_TESTNET=falseVerify:
hl setup checkExpected: Network: testnet or Network: mainnet shown.
CRITICAL: On testnet, you MUST claim USDyP tokens before ANY trading commands will work (including builder approval). Without funds, all orders fail silently.
hl setup claim-usdypIf you get "Wallet not eligible" error: New wallets must connect to Hyperliquid testnet once before claiming.
hl wallet listhl setup claim-usdypVerify:
hl accountExpected: USDyP balance > 0. If balance is 0, do NOT proceed — all subsequent steps will fail.
Deposit USDC to your Hyperliquid sub-account manually via the Hyperliquid web UI. This cannot be automated.
Verify:
hl account --mainnetExpected: USDC balance > 0.
Approve the builder fee so your orders include revenue collection. This is a one-time on-chain approval.
Testnet:
hl builder approveMainnet:
hl builder approve --mainnetVerify:
hl builder statusExpected: Builder fee: 10.0 bps -> 0x0D1DB1C8...
If fails:
| Error | Fix |
|---|---|
No private key | Complete Step 2 |
insufficient funds | Complete Step 4 |
Run a strategy in mock mode to verify the full pipeline without real orders.
hl run avellaneda_mm --mock --fresh --max-ticks 3Expected: 3 ticks execute, strategy produces decisions, no errors.
If fails:
| Error | Fix |
|---|---|
ModuleNotFoundError | Run pip install -e . again |
| Strategy crash | Check traceback — likely missing dependency |
Run a real strategy on testnet with a short time limit.
hl run engine_mm -i ETH-PERP --tick 15 --max-ticks 5Verify:
hl statusExpected: Shows position or recent fills. Trades logged to data/cli/trades.jsonl.
After single-strategy validation, try the full APEX orchestrator.
hl apex run --mock --fresh --max-ticks 5Then live:
hl apex run --max-ticks 10Only after completing Steps 1-8 on testnet:
IMPORTANT: Switching from testnet to mainnet requires re-approving the builder fee on mainnet. Testnet approvals do NOT carry over.
Switch network:
export HL_TESTNET=falseDeposit USDC to your HL sub-account via the Hyperliquid web UI
Verify balance:
hl account --mainnetApprove builder fee on mainnet (required again — separate from testnet approval):
hl builder approve --mainnetTest with a single strategy first:
hl run engine_mm -i ETH-PERP --tick 15 --max-ticks 5 --mainnetVerify: hl status
| Testnet | Mainnet | |
|---|---|---|
| Currency | USDyP (free, claim via hl setup claim-usdyp) | USDC (real money) |
| Instruments | Same tickers (ETH-PERP, BTC-PERP, etc.) | Same tickers |
| YEX markets | VXX-USDYP, US3M-USDYP, BTCSWP-USDYP | Same instruments |
| Builder fee | Must approve separately | Must approve separately |
--mainnet flag | Not needed (default is testnet) | Required on all commands |
| Risk | None (play money) | Real financial risk |
hl builder approve --mainnet.--mainnet flag → confusing. Set HL_TESTNET=false instead of mixing flags.--mainnet on a command → runs on testnet by accident (harmless but confusing).| Variable | Required | Description |
|---|---|---|
HL_KEYSTORE_PASSWORD | Yes* | Password for encrypted keystore |
HL_PRIVATE_KEY | Alt* | Raw private key (alternative to keystore) |
HL_TESTNET | No | true (default) or false for mainnet |
BUILDER_ADDRESS | No | Override builder fee address |
BUILDER_FEE_TENTHS_BPS | No | Override fee rate (default: 100 = 10 bps) |
ANTHROPIC_API_KEY | No | For claude_agent strategy |
GEMINI_API_KEY | No | For claude_agent with Gemini |
* Either keystore with HL_KEYSTORE_PASSWORD or HL_PRIVATE_KEY is required.
This skill is the entry point for all other skills. After completing onboarding:
hl run <strategy> — see strategies with hl strategieshl apex run — multi-slot orchestratorhl reflect run — nightly performance reviewhl radar run — find trading opportunitieshl guard run -i <instrument> — trailing stop protection© Nunchi-trade, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/onboard of Nunchi-trade/agent-cli.
Open the folder on GitHubat commit 58619a2
Agent Onboarding next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agent Onboarding this skillNunchi-trade/agent-cli | 521 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Senpi Trading Runtime ContractSenpi-ai/senpi-skills | 134 | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| Crypto Pricesundial-org/awesome-openclaw-skills | 663 | — | ~489 | Automated safety check: Pass | None | |
| Vibetrading Code GenLeoYeAI/openclaw-master-skills | 2.2k | — | ~5.7k | Automated safety check: Pass | MIT | |
| 1m Trade DexLeoYeAI/openclaw-master-skills | 2.2k | — | ~2.8k | Automated safety check: Notes | MIT | |
| Itr Walakaranb192/itr-wala | 871 | — | ~3.6k | Automated safety check: Pass | MIT |
Senpi-ai/senpi-skills
Documents how a Senpi strategy's scan function talks to the runtime that schedules it, sizes orders, and manages stop-loss exits on Hyperliquid.
sundial-org/awesome-openclaw-skills
Get cryptocurrency token price and generate candlestick charts via CoinGecko API or Hyperliquid API.
LeoYeAI/openclaw-master-skills
Generate executable Hyperliquid trading strategy code from natural language prompts.
LeoYeAI/openclaw-master-skills
Hyperliquid DEX/Perps entrypoint via hl1m: market queries, order placement.
karanb192/itr-wala
File Indian income tax returns (ITR) for FY 2025-26 / AY 2026-27.
zillionare/zillionare
面向中文自然语言的 Tushare 数据研究技能。用于把“看看这只股票最近怎么样”“帮我查财报趋势”“最近哪个板块最强”“北向资金在买什么”“给我导出一份行情数据”这类请求,转成可执行的数据获取、清洗、对比、筛选、导出与简要分析流程。适用于 A 股、指数、ETF/基金、财务、估值、资金流、公告新闻、板块概念与宏观数据等研究场景。
Nunchi-trade/agent-cli
Guard — two-phase ROE-based trailing stop system for Hyperliquid perps.
Nunchi-trade/agent-cli
Autonomous multi-slot trading orchestrator. An agent skill from Nunchi-trade/agent-cli.
Nunchi-trade/agent-cli
Screens all Hyperliquid perps and surfaces top trading setups
Nunchi-trade/agent-cli
Detects assets with sudden capital inflow via OI/volume/funding proxy signals
Nunchi-trade/agent-cli
Reflect, Evaluate, Fine-tune, Learn, Evolve, Correct, Transform — nightly automated performance review
Nunchi-trade/agent-cli
Autonomous Hyperliquid trading — 14 strategies (MM, momentum, arbitrage, LLM) with APEX multi-slot orchestrator, REFLECT performance review, DSL trailing stops, and builder fee revenue collection.
Works with
Categories
First-time setup — from zero to first trade on Hyperliquid. An agent skill from Nunchi-trade/agent-cli. Agent Onboarding is an agent skill from Nunchi-trade/agent-cli.
Agent Onboarding fits situations like: business, Finance & HR work in your project.
Run `npx skills add Nunchi-trade/agent-cli --skill agent-onboarding -a claude-code`. Or copy the skill folder (skills/onboard in Nunchi-trade/agent-cli) into .claude/skills/agent-onboarding in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Nunchi-trade/agent-cli --skill agent-onboarding -a codex`. Or copy the skill folder (skills/onboard in Nunchi-trade/agent-cli) into .agents/skills/agent-onboarding in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Nunchi-trade/agent-cli --skill agent-onboarding -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-onboarding, .gemini/skills/agent-onboarding, .github/skills/agent-onboarding and .opencode/skills/agent-onboarding in your project.
Going by SKILL.md and its folder, Agent Onboarding needs the command-line tools its instructions call (pip, python3, bash and brew) and credentials named HL_KEYSTORE_PASSWORD, HL_PRIVATE_KEY, ANTHROPIC_API_KEY and GEMINI_API_KEY. Our summary lists: Python 3; A credential in HL_PRIVATE_KEY; A credential in ANTHROPIC_API_KEY.
SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Agent Onboarding is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.1k tokens (SKILL.md is roughly 8.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Agent Onboarding: Senpi Trading Runtime Contract (Senpi-ai/senpi-skills, 134 stars), Crypto Price (sundial-org/awesome-openclaw-skills, 663 stars), Vibetrading Code Gen (LeoYeAI/openclaw-master-skills, 2.2k stars) and 1m Trade Dex (LeoYeAI/openclaw-master-skills, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Nunchi-trade (a GitHub organization) maintains it in Nunchi-trade/agent-cli, which has 521 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on July 8, 2026.
Source: Nunchi-trade/agent-cli on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.