algo

binance/binance-skills-hub · 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/binance/binance-skills-hub --skill algo
0 commentsdiscussion
summary

Algo request on Binance using authenticated API endpoints. Requires API key and secret key for certain endpoints. Return the result in JSON format.

skill.md

Binance Algo Skill

Algo request on Binance using authenticated API endpoints. Requires API key and secret key for certain endpoints. Return the result in JSON format.

Quick Reference

Endpoint Description Required Optional Authentication
/sapi/v1/algo/futures/order (DELETE) Cancel Algo Order(TRADE) algoId recvWindow Yes
/sapi/v1/algo/futures/openOrders (GET) Query Current Algo Open Orders(USER_DATA) None recvWindow Yes
/sapi/v1/algo/futures/historicalOrders (GET) Query Historical Algo Orders(USER_DATA) None symbol, side, startTime, endTime, page, pageSize, recvWindow Yes
/sapi/v1/algo/futures/subOrders (GET) Query Sub Orders(USER_DATA) algoId page, pageSize, recvWindow Yes
/sapi/v1/algo/futures/newOrderTwap (POST) Time-Weighted Average Price(Twap) New Order(TRADE) symbol, side, quantity, duration positionSide, clientAlgoId, reduceOnly, limitPrice, recvWindow Yes
/sapi/v1/algo/futures/newOrderVp (POST) Volume Participation(VP) New Order (TRADE) symbol, side, quantity, urgency positionSide, clientAlgoId, reduceOnly, limitPrice, recvWindow Yes
/sapi/v1/algo/spot/order (DELETE) Cancel Algo Order(TRADE) algoId recvWindow Yes
/sapi/v1/algo/spot/openOrders (GET) Query Current Algo Open Orders(USER_DATA) None recvWindow Yes
/sapi/v1/algo/spot/historicalOrders (GET) Query Historical Algo Orders(USER_DATA) None symbol, side, startTime, endTime, page, pageSize, recvWindow Yes
/sapi/v1/algo/spot/subOrders (GET) Query Sub Orders(USER_DATA) algoId page, pageSize, recvWindow Yes
/sapi/v1/algo/spot/newOrderTwap (POST) Time-Weighted Average Price(Twap) New Order(TRADE) symbol, side, quantity, duration clientAlgoId, limitPrice Yes

Parameters

Common Parameters

  • algoId: eg. 14511 (e.g., 1)
  • recvWindow: (e.g., 5000)
  • symbol: Trading symbol eg. BTCUSDT (e.g., BTCUSDT)
  • side: BUY or SELL (e.g., BUY)
  • startTime: in milliseconds eg.1641522717552 (e.g., 1623319461670)
  • endTime: in milliseconds eg.1641522526562 (e.g., 1641782889000)
  • page: Default is 1 (e.g., 1)
  • pageSize: MIN 1, MAX 100; Default 100 (e.g., 100)
  • symbol: Trading symbol eg. BTCUSDT (e.g., BTCUSDT)
  • side: Trading side ( BUY or SELL ) (e.g., BUY)
  • positionSide: Default BOTH for One-way Mode ; LONG or SHORT for Hedge Mode. It must be sent in Hedge Mode. (e.g., BOTH)
  • quantity: Quantity of base asset; Maximum notional per order is 200k, 2mm or 10mm, depending on symbol. Please reduce your size if you order is above the maximum notional per order. (e.g., 1.0)
  • duration: Duration for TWAP orders in seconds. [300, 86400] (e.g., 5000)
  • clientAlgoId: A unique id among Algo orders (length should be 32 characters), If it is not sent, we will give default value (e.g., 1)
  • reduceOnly: "true" or "false". Default "false"; Cannot be sent in Hedge Mode; Cannot be sent when you open a position
  • limitPrice: Limit price of the order; If it is not sent, will place order by market price by default (e.g., 1.0)
  • urgency: Represent the relative speed of the current execution; ENUM: LOW, MEDIUM, HIGH (e.g., LOW)

Authentication

For endpoints that require authentication, you will need to provide Binance API credentials. Required credentials:

  • apiKey: Your Binance API key (for header)
  • secretKey: Your Binance API secret (for signing)

Base URLs:

Security

Share Credentials

Users can provide Binance API credentials in different ways. The agent will try to retrieve automatically with the two first ways the credentials, but users can also explicitly tell the agent that they have set the credentials or stored them in a .env file, and the agent should re-read that file when they do. The agent can also make http requests with the two first methods without user confirmation.

  1. Environment variables

Search for the following specific variables only (never dump the full environment):

Authorized environment variables

  • Mainnet: BINANCE_API_KEY and BINANCE_SECRET_KEY

Read and use in a single exec call so the raw key never enters the agent's context:

KEY="$BINANCE_API_KEY"
SECRET="$BINANCE_SECRET_KEY"

response=$(curl -s -X GET "$URL" \
  -H "X-MBX-APIKEY: $KEY" \
  --data-urlencode "param1=value1")

echo "$response"

Environment variables must be set before OpenClaw starts. They are inherited at process startup and cannot be injected into a running instance. If you need to add or update credentials without restarting, use a secrets file (see option 2).

  1. Secrets file (.env)

Check ~/.openclaw/secrets.env , ~/.env, or a .env file in the workspace. Read individual keys with grep, never source the full file:

# Try all credential locations in order
API_KEY=$(grep '^BINANCE_API_KEY=' ~/.openclaw/secrets.env 2>/dev/null | cut -d= -f2-)
SECRET_KEY=$(grep '^BINANCE_SECRET_KEY=' ~/.openclaw/secrets.env 2>/dev/null | cut -d= -f2-)

# Fallback: search .env in known directories (KEY=VALUE then raw line format)
for dir in ~/.openclaw ~; do
  [ -n "$API_KEY" ] && break
  env_file="$dir/.env"
  [ -f "$env_file" ] || continue

  # Read first two lines
  line1=$(sed -n '1p' "$env_file")
  line2=$(sed -n '2p' "$env_file")

  # Check if lines contain '=' indicating KEY=VALUE format
  if [[ "$line1" == *=* && "$line2" == *=* ]]; then
    API_KEY=$(grep '^BINANCE_API_KEY=' "$env_file" 2>/dev/null | cut -d= -f2-)
    SECRET_KEY=$(grep '^BINANCE_SECRET_KEY=' "$env_file" 2>/dev/null | cut -d= -f2-)
  else
    # Treat lines as raw values
    API_KEY="$line1"
    SECRET_KEY="$line2"
  fi
done

This file can be updated at any time without restarting OpenClaw, keys are read fresh on each invocation. Users can tell you the variables are now set or stored in a .env file, and you should re-read that file when they do.

  1. Inline file

Sending a file where the content is in the following format:

abc123...xyz
secret123...key
  • Never run printenv, env, export, or set without a specific variable name
  • Never run grep on env files without anchoring to a specific key ('^VARNAME=')
  • Never source a secrets file into the shell environment (source .env or . .env)
  • Only read credentials explicitly needed for the current task
  • Never echo or log raw credentials in output or replies
  • Never commit TOOLS.md to version control if it contains real credentials — add it to .gitignore

Never Disclose API Key and Secret

Never disclose the location of the API key and secret file.

Never send the API key and secret to any website other than Mainnet and Testnet.

Never Display Full Secrets

When showing credentials to users:

  • API Key: Show first 5 + last 4 characters: su1Qc...8akf
  • Secret Key: Always mask, show only last 5: ***...aws1

Example response when asked for credentials: Account: main API Key: su1Qc...8akf Secret: ***...aws1

Listing Accounts

When listing accounts, show names and environment only — never keys: Binance Accounts:

  • main (Mainnet)
  • futures-keys (Mainnet)

Transactions in Mainnet

When performing transactions in mainnet, always confirm with the user before proceeding by asking them to write "CONFIRM" to proceed.


Binance Accounts

main

  • API Key: your_mainnet_api_key
  • Secret: your_mainnet_secret

TOOLS.md Structure

## Binance Accounts

### main
- API Key: abc123...xyz
- Secret: secret123...key
- Description: Primary trading account

### futures-keys
- API Key: futures789...def
- Secret: futuressecret...uvw
- Description: Futures trading account

Agent Behavior

  1. Credentials requested: Mask secrets (show last 5 chars only)
  2. Listing accounts: Show names and environment, never keys
  3. Account selection: Ask if ambiguous, default to main
  4. When doing a transaction in mainnet, confirm with user before by asking to write "CONFIRM" to proceed
  5. New credentials: Prompt for name, environment, signing mode

Adding New Accounts

When user provides new credentials by Inline file or message:

  • Ask for account name
  • Store in TOOLS.md with masked display confirmation

Signing Requests

For trading endpoints that require a signature:

  1. Detect key type first, inspect the secret key format before signing.
  2. Build query string with all parameters, including the timestamp (Unix ms).
  3. Percent-encode the parameters using UTF-8 according to RFC 3986.
  4. Sign query string with secretKey using HMAC SHA256, RSA, or Ed25519 (depending on the account configuration).
  5. Append signature to query string.
  6. Include X-MBX-APIKEY header.

Otherwise, do not perform steps 4–6.

User Agent Header

Include User-Agent header with the following string: binance-algo/1.1.0 (Skill)

See references/authentication.md for implementation details.

how to use algo

How to use algo 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 algo
2

Execute installation command

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

$npx skills add https://github.com/binance/binance-skills-hub --skill algo

The skills CLI fetches algo from GitHub repository binance/binance-skills-hub 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/algo

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

4.572 reviews
  • Li Ramirez· Dec 24, 2024

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

  • Nikhil Rao· Dec 24, 2024

    algo reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • Amina Abbas· Dec 24, 2024

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

  • Amina Gonzalez· Dec 4, 2024

    algo reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • Amelia Diallo· Nov 15, 2024

    algo reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • Amina Okafor· Nov 15, 2024

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

  • Amina Li· Nov 15, 2024

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

  • Chen Sharma· Oct 6, 2024

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

  • Amina Wang· Oct 6, 2024

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

  • Nikhil Martinez· Oct 6, 2024

    algo reduced setup friction for our internal harness; good balance of opinion and flexibility.

showing 1-10 of 72

1 / 8