senpi-getting-started-guide

senpi-ai/senpi-skills · updated Apr 8, 2026

MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.

$npx skills add https://github.com/senpi-ai/senpi-skills --skill senpi-getting-started-guide
0 commentsdiscussion
summary

Guide users through their first complete trade on Hyperliquid via Senpi. This skill teaches the core loop: discover top traders → create a strategy that mirrors a chosen trader → monitor → close strategy.

skill.md

Getting Started: Your First Trade

Guide users through their first complete trade on Hyperliquid via Senpi. This skill teaches the core loop: discover top traderscreate a strategy that mirrors a chosen trader → monitorclose strategy.

Prerequisites (agent-only): Senpi MCP connected. Onboarding complete (see state check below). Wallet funded for creating a strategy; if not yet funded, show a funding reminder and do not start until balance ≥ $100 or user confirms they funded.

User-facing rule: Never show the user internal details. Do not mention state names (e.g. UNFUNDED, READY, FRESH), file paths (e.g. state.json, ~/.config/senpi), step codes (e.g. STRATEGY_CREATED), or MCP/tool names. Use only plain, friendly language (e.g. "You're all set to start", "Fund your wallet to begin", "Your strategy is running").

Minimum strategy budget: Use $100 as the minimum when creating the first-trade mirror strategy. Do not suggest or use $50 or any amount below $100.


Prerequisites

Before starting the tutorial, verify:

  1. MCP Connected — Senpi MCP server is configured and accessible.
  2. Onboarding complete — If not complete (state FRESH or ONBOARDING), redirect with a user-friendly message only (see below). Do not mention "state" or "onboarding" to the user.
  3. Wallet funded (for creating a strategy) — If not yet funded, show a single friendly funding reminder; do not start the tutorial until balance ≥ $100 or user confirms they funded.

Ensure state file exists; if missing, create it and redirect. When redirecting, tell the user only: "You need to complete setup first. Say 'set up Senpi' or 'connect to Senpi' to get started." Do not mention state file, FRESH, or any internal state.

# Ensure state file exists (per state lifecycle); if missing, create and redirect
if [ ! -f ~/.config/senpi/state.json ]; then
  mkdir -p ~/.config/senpi
  cat > ~/.config/senpi/state.json << 'STATEEOF'
{
  "version": "1.0.0",
  "state": "FRESH",
  "error": null,
  "onboarding": {
    "step": "IDENTITY",
    "startedAt": null,
    "completedAt": null,
    "identityType": null,
    "subject": null,
    "walletGenerated": false,
    "existingAccount": false
  },
  "account": {},
  "wallet": { "funded": false },
  "firstTrade": { "completed": false, "skipped": false },
  "mcp": { "configured": false }
}
STATEEOF
  # Tell user only (do not echo internal messages):
  # "You need to complete setup first. Say 'set up Senpi' or 'connect to Senpi' to get started."
  exit 1
fi

STATE=$(cat ~/.config/senpi/state.json | node -p "JSON.parse(require('fs').readFileSync(0,'utf8')).state")
if [ "$STATE" = "FRESH" ] || [ "$STATE" = "ONBOARDING" ]; then
  # Tell user only (do not echo "User needs to complete onboarding" or state names):
  # "You need to complete setup first. Say 'set up Senpi' or 'connect to Senpi' to get started."
  exit 1
fi

Triggers

Start this tutorial when:

  • User says: "let's trade", "first trade", "teach me to trade", "how do I trade", "make a trade"
  • State is AWAITING_FIRST_TRADE and user sends a trading-related message
  • User explicitly asks for trading guidance

Do NOT start if: MCP not connected — then tell the user to set up Senpi first (do not mention MCP or state). If user says "skip tutorial", set state to READY and show the skip message from references/next-steps.md. If wallet has less than $100 when starting, do not create a strategy until funded; use the funding reminder below (user-friendly wording only).


Tutorial Flow

Follow steps in order. Reference files contain display copy, state schemas, and error handling.

When the wallet isn’t funded yet (before Step 1)

If the user asked for the first-trade guide (e.g. "let's trade") but the wallet is not yet funded:

  1. Check balance — Use MCP to fetch portfolio/balance.
  2. If balance < $100: Do not start the introduction. Show one clear, user-friendly message only:
    • Your trading wallet address (from state; do not say "agent wallet" or "state.json").
    • That they need to send at least $100 USDC on a supported network (Base, Arbitrum, Optimism, Polygon, or Ethereum).
    • "Once you’ve sent the funds, say 'I funded my wallet' or 'let’s trade' and we’ll start the tutorial."
  3. If balance ≥ $100: Update state (AWAITING_FIRST_TRADE, wallet.funded true), then proceed to Step 1.

If onboarding is not complete (state FRESH or ONBOARDING), tell the user only: "Complete setup first — say 'set up Senpi' to get started." Do not say "onboarding", "state", or "User needs to complete onboarding first."

Step 1: Introduction

Display the trade cycle. When showing the 4-step list to the user, use this exact wording:

1️⃣ Discover — Find top-performing traders on Hyperliquid
2️⃣ Create a strategy — Mirror a chosen trader's positions ($100 budget)
3️⃣ Monitor — Watch how the strategy performs
4️⃣ Close — Exit when you're ready

Recommend a $100 minimum budget for the first strategy and include a short risk disclaimer. Ask user to say "yes" to continue or "skip" if experienced.

Update state: set firstTrade.step to INTRODUCTION, firstTrade.started true, startedAt (ISO 8601). Preserve existing fields in state.json.

Wait for user confirmation before proceeding.


Step 2: Discovery

Use MCP discovery_get_top_traders to fetch top traders. Optionally use discovery_get_trader_state or discovery_get_trader_history for extra detail. Show a short table of top traders (e.g. by PnL, win rate) and recommend one trader to mirror for the first trade.

See references/discovery-guide.md for display template and state update (firstTrade.step: "DISCOVERY", recommendedTraderId, recommendedTraderName).


Step 3: Strategy Sizing

Before creating the strategy, explain: chosen trader, budget ($100 minimum), and that the strategy will mirror that trader's positions. Warn about risk and liquidation. Ask user to say "confirm" to create the strategy.

See references/strategy-management.md for the sizing table and wording.


Step 4: Create Strategy

On user confirmation, call MCP strategy_create with the chosen trader (from Step 2) and budget (minimum $100). On success, show the celebration (see references/next-steps.md — "Celebrate (After First Strategy Created)"): congratulate the user for opening their first strategy, then offer "how's my strategy?", "close my strategy", or "show my positions". Do not show strategy status or raw IDs.

Update state per references/strategy-management.md: set firstTrade.step: "STRATEGY_CREATED", tradeDetails (strategyId, mirroredTraderId, etc.), and set firstTrade.completed: true, firstTrade.step: "COMPLETE", firstTrade.completedAt. On failure, see references/error-handling.md.


Step 5: Monitor Strategy

When user asks "how's my strategy?" or similar, fetch data via MCP: strategy_get, strategy_get_clearinghouse_state, or execution_get_open_position_details for open positions. Show strategy value, open positions (if any), unrealized PnL, ROE. Offer: Hold, Close strategy, or Add protection. Do not show a separate congratulations here — that was already shown when they created their first strategy (Step 4).


Step 6: Close Strategy

When user says "close", "exit", "close my strategy", "take profit", etc., call MCP strategy_close with the strategy ID from state. Tell the user the strategy is closed and show realized PnL, duration, and fees in plain language. Show the "After Close" result and next steps from references/next-steps.md (no separate congratulations — already shown when they created the strategy). Do not mention strategy status or internal codes. Update state (STRATEGY_CLOSE, tradeDetails with closedAt, pnl, etc.). See references/strategy-management.md.


Step 7: After Close — Result & Next Steps

When the user has closed their strategy (Step 6), the result and next steps are shown there. No separate celebration step — state was already set to READY and firstTrade.completed when they created their first strategy (Step 4). Full "After Close" copy: references/next-steps.md. State shape: references/strategy-management.md.


Interrupted Tutorial / Resume

If the user returns mid-tutorial, read firstTrade.step from state and resume from the matching step. See references/next-steps.md for resume logic. Resume message must be user-friendly only — e.g. "You were in the middle of your first trade. Here’s where we left off…" Do not mention step names (INTRODUCTION, DISCOVERY, STRATEGY_CREATED, etc.) or state.


Reference Files


Installation

npx skills add Senpi-ai/senpi-skills/senpi-getting-started-guide

Or manually:

mkdir -p ~/.senpi/skills/senpi-getting-started-guide
curl -sL "https://raw.githubusercontent.com/Senpi-ai/senpi-skills/main/senpi-getting-started-guide/SKILL.md" \
  -o ~/.senpi/skills/senpi-getting-started-guide/SKILL.md
# Copy references/ into the same skill directory
how to use senpi-getting-started-guide

How to use senpi-getting-started-guide on Cursor

AI-first code editor with Composer

1

Prerequisites

Before installing skills in Cursor, ensure your development environment meets these requirements:

  • Cursor installed and configured on your development machine
  • Node.js version 16.0+ with npm package manager (verify with node --version)
  • Active project directory or workspace where you want to add senpi-getting-started-guide
2

Execute installation command

Execute the skills CLI command in your project's root directory to begin installation:

$npx skills add https://github.com/senpi-ai/senpi-skills --skill senpi-getting-started-guide

The skills CLI fetches senpi-getting-started-guide from GitHub repository senpi-ai/senpi-skills and configures it for Cursor.

3

Select Cursor when prompted

The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:

◆ Which agents do you want to install to?
│ ── Universal (.agents/skills) ── always included ────
│ • Amp
│ • Antigravity
│ • Cline
│ • Codex
│ ●Cursor(selected)
│ • Cursor
│ • Windsurf
4

Verify installation

Confirm successful installation by checking the skill directory location:

.cursor/skills/senpi-getting-started-guide

Reload or restart Cursor to activate senpi-getting-started-guide. Access the skill through slash commands (e.g., /senpi-getting-started-guide) or your agent's skill management interface.

Security & Verification Notice

We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.

Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.

List & Monetize Your Skill

Submit your Claude Code skill and start earning

GET_STARTED →

Use Cases

Task Automation & Efficiency

Automate repetitive workflows and reduce manual effort

Example

Generate reports, summarize documents, draft communications

Save 3-5 hours per week on routine tasks

Knowledge Enhancement

Learn new skills, understand complex topics, get expert guidance

Example

Explain concepts, provide examples, suggest learning resources

Accelerate learning and skill development by 2x

Quality Improvement

Enhance output quality through reviews, suggestions, and refinements

Example

Review drafts, suggest improvements, catch errors

Improve work quality by 30-40% with less effort

Implementation Guide

Prerequisites

  • Claude Desktop or compatible AI client with skill support
  • Clear understanding of task or problem to solve
  • Willingness to iterate and refine outputs

Time Estimate

15-45 minutes depending on use case complexity

Installation Steps

  1. 1.Install skill using provided installation command
  2. 2.Test with simple use case relevant to your work
  3. 3.Evaluate output quality and relevance
  4. 4.Iterate on prompts to improve results
  5. 5.Integrate into regular workflow if valuable

Common Pitfalls

  • Expecting perfect results without iteration
  • Not providing enough context in prompts
  • Using skill for tasks outside its intended scope
  • Accepting outputs without review and validation

Best Practices

✓ Do

  • +Start with clear, specific prompts
  • +Provide relevant context and constraints
  • +Review and refine all outputs before using
  • +Iterate to improve output quality
  • +Document successful prompt patterns

✗ Don't

  • Don't use without understanding skill limitations
  • Don't skip validation of outputs
  • Don't share sensitive information in prompts
  • Don't expect skill to replace human judgment

💡 Pro Tips

  • Be specific about desired format and style
  • Ask for multiple options to choose from
  • Request explanations to understand reasoning
  • Combine AI efficiency with human expertise

When to Use This

✓ Use When

Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.

✗ Avoid When

Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.

Learning Path

  1. 1Familiarize yourself with skill capabilities and limitations
  2. 2Start with low-risk, non-critical tasks
  3. 3Progress to more complex and valuable use cases
  4. 4Build expertise through regular use and experimentation

Discussion

Product Hunt–style comments (not star reviews)
  • No comments yet — start the thread.
general reviews

Ratings

4.543 reviews
  • Kaira Harris· Dec 16, 2024

    senpi-getting-started-guide reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • Chaitanya Patil· Dec 8, 2024

    senpi-getting-started-guide fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.

  • Carlos Ramirez· Dec 4, 2024

    senpi-getting-started-guide is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

  • Ira Abbas· Dec 4, 2024

    senpi-getting-started-guide fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.

  • Piyush G· Nov 27, 2024

    Registry listing for senpi-getting-started-guide matched our evaluation — installs cleanly and behaves as described in the markdown.

  • Neel Iyer· Nov 23, 2024

    Solid pick for teams standardizing on skills: senpi-getting-started-guide is focused, and the summary matches what you get after install.

  • Yuki Diallo· Nov 23, 2024

    Registry listing for senpi-getting-started-guide matched our evaluation — installs cleanly and behaves as described in the markdown.

  • Zaid Khan· Nov 15, 2024

    Useful defaults in senpi-getting-started-guide — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • Kiara Huang· Oct 26, 2024

    senpi-getting-started-guide fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.

  • Shikha Mishra· Oct 18, 2024

    senpi-getting-started-guide reduced setup friction for our internal harness; good balance of opinion and flexibility.

showing 1-10 of 43

1 / 5