senpi-onboard

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-onboard
0 commentsdiscussion
summary

Onboard an AI agent into the Senpi trading platform. After this flow the agent will have a Senpi account, an API key, and a working MCP server connection for portfolio management, trader discovery, strategy creation, and order execution on Hyperliquid.

skill.md

Senpi Agent Onboarding

Onboard an AI agent into the Senpi trading platform. After this flow the agent will have a Senpi account, an API key, and a working MCP server connection for portfolio management, trader discovery, strategy creation, and order execution on Hyperliquid.

Prerequisites: Shell/code execution access and Node.js (required for npx).

Defaults

  • SENPI_MCP_ENDPOINT: https://mcp.prod.senpi.ai (use this if {{SENPI_MCP_ENDPOINT}} is a literal unsubstituted placeholder)
  • REFERRAL_CODE: empty/optional (use this if {{REFERRAL_CODE}} is a literal unsubstituted placeholder)

Arena intent hard-gate: If the user's message contains "arena", "agents arena", "competition", "prize pool", "qualify", "qualification", "weekly cycle", or "weekly competition" — call read_senpi_guide(uri="senpi://guides/arena") before composing any answer. Do not use web search or leaderboard data for Arena questions. Full routing rules in references/post-onboarding.md.


Onboarding Flow

Follow every step in order. Do not skip steps.

Before you begin: State initialization

Per the state lifecycle, ensure state.json exists so routing and transitions are well-defined. If it does not exist, create it with initial FRESH state:

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
fi

Then continue with Step 0.

Transition to ONBOARDING: Before running Step 0, if state is FRESH, update state.json so the state machine and resume behavior work. Set state to ONBOARDING, set onboarding.startedAt to current ISO 8601 UTC, and keep onboarding.step as IDENTITY. Use a read-modify-write (merge) so other fields are preserved:

node -e "
  const fs = require('fs');
  const p = require('os').homedir() + '/.config/senpi/state.json';
  const s = JSON.parse(fs.readFileSync(p, 'utf8'));
  if (s.state === 'FRESH') {
    s.state = 'ONBOARDING';
    s.onboarding = s.onboarding || {};
    s.onboarding.startedAt = new Date().toISOString();
    s.onboarding.step = s.onboarding.step || 'IDENTITY';
    fs.writeFileSync(p, JSON.stringify(s, null, 2));
  }
"

If state is already ONBOARDING, read onboarding.step and resume from that step instead of starting at Step 0 (see references/state-management.md).

Step 0: Verify mcporter (OpenClaw only)

Check if mcporter CLI is available:

if command -v mcporter &> /dev/null; then
  MCPORTER_AVAILABLE=true
else
  MCPORTER_AVAILABLE=false
fi

If unavailable and on OpenClaw, install it:

npm i -g mcporter
mcporter --version

Set MCPORTER_AVAILABLE=true once installed and proceed.


Step 1: Collect Identity

Present all three options to the user and wait for them to choose:

  1. Option A -- Telegram user ID: The skill will read your Telegram identity from USER.md automatically.
  2. Option B -- User-provided wallet: Must be 0x-prefixed, exactly 42 hex characters. Validate before proceeding.
  3. Option C -- Agent-generated wallet (only if you have neither).

Option A: Collect Telegram user ID

When the user chooses Option A, first attempt to read from ${OPENCLAW_WORKSPACE_DIR}/USER.md:

USER_MD="${OPENCLAW_WORKSPACE_DIR}/USER.md"
if [ -f "$USER_MD" ]; then
  TELEGRAM_USER_ID=$(awk '/^## Telegram/{f=1; next} f && /^## /{f=0} f && /- Chat ID:/{print $NF; exit}' "$USER_MD")
  TELEGRAM_USERNAME=$(awk '/^## Telegram/{f=1; next} f && /^## /{f=0} f && /- Username:/{print $NF; exit}' "$USER_MD")
  TELEGRAM_USERNAME="${TELEGRAM_USERNAME#@}" # normalize for API userName field
fi

If both TELEGRAM_USER_ID (digits-only, non-empty) and TELEGRAM_USERNAME (non-empty) are found, set the variables automatically without prompting the user:

IDENTITY_TYPE="TELEGRAM"
IDENTITY_VALUE="$TELEGRAM_USER_ID"

If USER.md is missing or either field is absent/invalid, fall back to the manual prompt: see references/telegram-identity.md for user-facing instructions and validation rules. Also set TELEGRAM_USERNAME from the user's input if prompted manually, then normalize it before API use with TELEGRAM_USERNAME="${TELEGRAM_USERNAME#@}".

Option B: Set variables

IDENTITY_TYPE="WALLET"
IDENTITY_VALUE="0x..."  # 0x-prefixed wallet address

Option C: Generate EVM wallet

Use only when the user confirms they have neither wallet nor Telegram. Inform the user before proceeding.

Run the bundled script to generate a wallet:

# Try npx first, then local install fallbacks
WALLET_DATA=$(npx -y -p ethers@6 node scripts/generate_wallet.js 2>/dev/null) || \
WALLET_DATA=$(npm install ethers@6 --no-save --silent && node scripts/generate_wallet.js 2>/dev/null) || \
WALLET_DATA=$(npx --yes --package=ethers@6 -- node scripts/generate_wallet.js)

If the script is not available at scripts/generate_wallet.js, generate inline:

WALLET_DATA=$(npx -y -p ethers@6 node -e "
  const { ethers } = require('ethers');
  const w = ethers.Wallet.createRandom();
  console.log(JSON.stringify({
    address: w.address,
    privateKey: w.privateKey,
    mnemonic: w.mnemonic.phrase
  }));
")

Do not prompt the user on failure -- try fallbacks silently. Only report if all methods fail. See references/error-handling.md for wallet generation failure handling.

Parse WALLET_DATA JSON to extract address, privateKey, and mnemonic. Validate the address is not empty or null. If invalid, stop and see error handling reference.

Persist the wallet immediately (before continuing) using the parsed values:

mkdir -p ~/.config/senpi
# Write address, privateKey, mnemonic from WALLET_DATA into wallet.json
chmod 600 ~/.config/senpi/wallet.json

The file must contain: address, privateKey, mnemonic, generatedAt (ISO 8601 UTC), and "generatedBy": "senpi-onboard".

CRITICAL:

  • Do not log or display the private key or mnemonic.
  • Do not proceed until wallet.json is written and permissions set.

Set the identity variables using the parsed address:

WALLET_GENERATED=true
IDENTITY_TYPE="WALLET"
IDENTITY_VALUE="<address from WALLET_DATA>"

Notify the user that a wallet was generated and saved to ~/.config/senpi/wallet.json with restricted permissions. Instruct them to back up this file immediately.

Verify before proceeding

Before Step 2, confirm these are set:

  • IDENTITY_TYPE -- "WALLET" or "TELEGRAM"
  • IDENTITY_VALUE -- wallet address (with 0x) or Telegram numeric user ID (digits only)
  • WALLET_GENERATED -- true if Option C was used, unset otherwise
  • TELEGRAM_USERNAME -- required and non-empty when IDENTITY_TYPE="TELEGRAM" (unset otherwise)

Persist progress for resume: Update ~/.config/senpi/state.json: set onboarding.step to REFERRAL, and if available set onboarding.identityType, onboarding.subject, onboarding.walletGenerated from current variables. Use read-modify-write so other fields are preserved.


Step 2: Set Referral Code

REFERRAL_CODE="{{REFERRAL_CODE}}"

If empty and user hasn't provided one, that's fine -- it's optional. Do not prompt unless the user mentions having one.

Persist progress for resume: Update ~/.config/senpi/state.json: set onboarding.step to API_CALL. Use read-modify-write.


Step 3: Call Onboarding API

Execute the CreateAgentStubAccount GraphQL mutation. This is a public endpoint -- no auth required.

if [ "$IDENTITY_TYPE" = "TELEGRAM" ] && [ -z "${TELEGRAM_USERNAME:-}" ]; then
  echo "TELEGRAM_USERNAME must be set when IDENTITY_TYPE=TELEGRAM" >&2
  exit 1
fi

RESPONSE=$(curl -s -X POST https://moxie-backend.prod.senpi.ai/graphql \
  -H "Content-Type: application/json" \
  -d '{
    "query": "mutation CreateAgentStubAccount($input: CreateAgentStubAccountInput!) { CreateAgentStubAccount(input: $input) { user { id privyId userName name referralCode referrerId } apiKey apiKeyExpiresIn apiKeyTokenType referralCode agentWalletAddress } }",
    "variables": {
      "input": {
        "from": "'"${IDENTITY_TYPE}"'",
        "subject": "'"${IDENTITY_VALUE}"'",
        '"$([ "$IDENTITY_TYPE" = "TELEGRAM" ] && echo "\"userName\": \"${TELEGRAM_USERNAME}\",")"'
        "referralCode": "'"${REFERRAL_CODE}"'",
        "apiKeyName": "agent-'"$(date +%s
how to use senpi-onboard

How to use senpi-onboard 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-onboard
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-onboard

The skills CLI fetches senpi-onboard 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-onboard

Reload or restart Cursor to activate senpi-onboard. Access the skill through slash commands (e.g., /senpi-onboard) 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

User Story & Requirements Generation

Create detailed user stories, acceptance criteria, and feature specs

Example

Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios

Reduce spec writing time by 50%, ensure comprehensive coverage

Competitive Analysis

Research competitors, compare features, identify gaps

Example

Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities

Complete competitive research in 2 hours instead of 2 days

Roadmap Prioritization

Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs

Example

Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale

Make data-driven prioritization decisions faster

Stakeholder Communication

Draft PRDs, status updates, and stakeholder presentations

Example

Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement

Save 3-5 hours/week on communication overhead

Implementation Guide

Prerequisites

  • Claude Desktop or compatible AI client
  • Access to product documentation and roadmap tools (Jira, Notion, etc.)
  • Understanding of product management frameworks (RICE, Jobs-to-be-Done, etc.)
  • Stakeholder contact information and communication channels

Time Estimate

30-60 minutes to see productivity improvements

Installation Steps

  1. 1.Install product management skill
  2. 2.Start with user story generation for known feature
  3. 3.Progress to competitive analysis: research 2-3 competitors
  4. 4.Use for roadmap prioritization: apply RICE/ICE scoring
  5. 5.Draft stakeholder communications and refine based on feedback
  6. 6.Build template library for recurring PM tasks
  7. 7.Share effective prompts with product team

Common Pitfalls

  • Not validating competitive research—verify facts before sharing
  • Accepting user stories without involving engineering team
  • Over-relying on frameworks without qualitative judgment
  • Not customizing outputs to company culture and communication style
  • Skipping stakeholder validation of generated requirements

Best Practices

✓ Do

  • +Validate research and competitive analysis with real data
  • +Collaborate with engineering when generating technical requirements
  • +Customize frameworks and templates to your company context
  • +Use skill for first drafts, refine with stakeholder input
  • +Document successful prompt patterns for PM tasks
  • +Combine AI efficiency with human judgment and intuition

✗ Don't

  • Don't publish competitive analysis without fact-checking
  • Don't finalize user stories without engineering review
  • Don't make prioritization decisions solely on AI scoring
  • Don't skip customer validation of generated requirements
  • Don't ignore company-specific context and culture

💡 Pro Tips

  • Provide context: company goals, constraints, customer feedback
  • Ask for alternatives: 'Show 3 ways to prioritize this roadmap'
  • Request stakeholder-specific formatting: 'Executive summary vs. engineering spec'
  • Use skill for 70% generation + 30% customization to company needs

When to Use This

✓ Use When

Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.

✗ Avoid When

Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.

Learning Path

  1. 1Basic: user stories, feature specs, status updates
  2. 2Intermediate: competitive analysis, prioritization frameworks, PRDs
  3. 3Advanced: product strategy, go-to-market planning, OKR setting
  4. 4Expert: product vision, market positioning, business model innovation

Discussion

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

Ratings

4.746 reviews
  • Mia Taylor· Dec 28, 2024

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

  • Ama Abbas· Dec 24, 2024

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

  • Shikha Mishra· Dec 20, 2024

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

  • Henry Singh· Dec 16, 2024

    I recommend senpi-onboard for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • Benjamin Liu· Dec 12, 2024

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

  • Mia Abebe· Nov 19, 2024

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

  • Meera Jain· Nov 15, 2024

    I recommend senpi-onboard for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • Yash Thakker· Nov 11, 2024

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

  • Lucas Torres· Nov 7, 2024

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

  • Sakshi Patil· Nov 3, 2024

    Keeps context tight: senpi-onboard is the kind of skill you can hand to a new teammate without a long onboarding doc.

showing 1-10 of 46

1 / 5