okx-cex-market

okx/agent-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/okx/agent-skills --skill okx-cex-market
0 commentsdiscussion
summary

Read-only public market data for OKX exchange: prices, order books, candles, funding rates, and instrument info.

  • Query spot, perpetual, futures, and option markets with 13 commands covering tickers, order books, OHLCV candles, funding rates, open interest, and mark prices
  • No API credentials required; all commands are public and read-only with no confirmation needed
  • Supports filtering by instrument type (SPOT, SWAP, FUTURES, OPTION) and includes stock token perpetuals (TSLA, NVDA, AAP
skill.md

OKX CEX Market Data CLI

Compliance notice: This skill provides raw market data only. No strategy, recommendation, or optimization logic is embedded. All indicator outputs are objective numerical values; interpretation and trading decisions remain solely with the user.

Public market data for OKX: prices, order books, candles, funding rates, open interest, instrument info, and technical indicators. All commands are read-only and require no API credentials.

Skill routing

  • Market data / indicators → okx-cex-market (this skill)
  • Account balance / positions → okx-cex-portfolio
  • Place / cancel orders → okx-cex-trade
  • Grid / DCA bots → okx-cex-bot

Preflight

Before running any command, follow ../_shared/preflight.md. Use metadata.version from this file's frontmatter as the reference for Step 2.

Install

npm install -g @okx_ai/okx-trade-cli
okx market ticker BTC-USDT   # verify

Market data commands return the same public data regardless of demo/live mode — no API credentials required. If the user's profile has demo=true set and they want live data context, they can use --live to confirm they are in live mode (it has no effect on public market data but clarifies environment). Always inform the user which environment is active (demo or live) when it is relevant to their query. No confirmation needed before running any market command. Add --json to any command for raw OKX API v5 response.


Command Index

# Command Description
1 okx market ticker <instId> Last price, 24h high/low/vol/change%
2 okx market tickers <instType> All tickers for SPOT / SWAP / FUTURES / OPTION
3 okx market instruments --instType <type> [--instId <id>] List instruments (instId, ctVal, lotSz, minSz, tickSz, state)
4 okx market orderbook <instId> [--sz <n>] Order book asks/bids (default top 5 per side, max 400)
5 okx market candles <instId> [--bar <bar>] [--limit <n>] [--after <ts>] [--before <ts>] OHLCV candles (default --bar 1m); auto-routes to historical endpoint for data back to 2021; --after paginates back in time, --before paginates forward
6 okx market index-candles <instId> [--bar <bar>] [--limit <n>] [--history] Index OHLCV (use BTC-USD not BTC-USDT)
7 okx market funding-rate <instId> [--history] [--limit <n>] Current or historical funding rate (SWAP only)
8 okx market trades <instId> [--limit <n>] Recent public trades
9 okx market mark-price --instType <type> [--instId <id>] Mark price (SWAP / FUTURES / OPTION)
10 okx market index-ticker [--instId <id>] [--quoteCcy <ccy>] Index price (e.g., BTC-USD)
11 okx market price-limit <instId> Upper/lower price limits (SWAP / FUTURES only)
12 okx market open-interest --instType <type> [--instId <id>] Open interest in contracts and base currency
13 okx market instruments-by-category --instCategory <3|4|5|6|7> Discover instruments by asset category: 3=Stock tokens (AAPL/TSLA), 4=Metals (gold/silver), 5=Commodities (oil/gas), 6=Forex (EUR/USD), 7=Bonds
13† okx market stock-tokens Deprecated — use instruments-by-category --instCategory 3 instead
15 okx market indicator <indicator> <instId> [--bar] [--params] [--list] [--limit] [--backtest-time] Technical indicator values

Operation Flow

Step 1 — Identify data type and load reference

User intent Reference to load
Price, candles, order book, recent trades {baseDir}/references/price-data-commands.md
Technical indicators (RSI, MACD, EMA, BB, KDJ, SuperTrend, AHR999, Rainbow, etc.) {baseDir}/references/indicator-commands.md
Funding rate, mark price, open interest, price limit, index ticker {baseDir}/references/derivatives-commands.md
List instruments, discover stock tokens, metals/commodities/forex/bonds, find option instIds {baseDir}/references/instrument-commands.md
Multi-step or cross-skill workflows; MCP tool names {baseDir}/references/workflows.md

Step 2 — Run commands immediately

All market data commands are read-only — no confirmation needed.

Step 3 — No writes, no verification needed

All commands in this skill are read-only.


Edge Cases

  • instId format: SPOT BTC-USDT · SWAP BTC-USDT-SWAP · FUTURES BTC-USDT-250328 · OPTION BTC-USD-250328-95000-C · Index BTC-USD · Stock token TSLA-USDT-SWAP · Metals/Commodities/Forex/Bonds: use instruments-by-category to discover valid instIds first
  • OPTION listing: instruments --instType OPTION requires --uly BTC-USD; if unknown, run open-interest --instType OPTION first to discover active instIds
  • funding-rate / price-limit: SWAP only · mark-price: SWAP / FUTURES / OPTION only
  • candles --bar: uppercase — 1H not 1h; use --after <ts> to paginate back into historical data (back to 2021); index-candles supports --history for extended history
  • ⚠️ Large historical range: before fetching with --after/--before, estimate candle count = time_range_ms / bar_interval_ms. If estimate > 500, tell the user the estimated count and ask for confirmation before proceeding. This prevents silently filling the context window.
  • indicator --bar: uses 1Dutc not 1D, 1Wutc not 1W — different from candle bar values
  • indicator arg order: indicator name before instId — okx market indicator rsi BTC-USDT
  • indicator --params: comma-separated, no spaces — --params 5,20
  • BTC-only indicators: ahr999, rainbow, pi-cycle-top, pi-cycle-bottom, mayer — BTC-USDT only
  • Stock token hours: US stocks trade Mon–Fri ~09:30–16:00 ET; verify live price before acting
  • No data returned: instrument may be delisted — verify with okx market instruments
  • boll is an alias for bb

Global Notes

  • No API key required for any command in this skill
  • Rate limit: 20 req / 2 s per IP
  • Candle data is sorted newest-first
  • vol24h is in base currency (e.g., BTC for BTC-USDT)
  • --profile and --demo/--live do not affect market data results (public endpoints); they only determine the active trading environment context
how to use okx-cex-market

How to use okx-cex-market 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 okx-cex-market
2

Execute installation command

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

$npx skills add https://github.com/okx/agent-skills --skill okx-cex-market

The skills CLI fetches okx-cex-market from GitHub repository okx/agent-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/okx-cex-market

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

4.753 reviews
  • Nia Abbas· Dec 24, 2024

    okx-cex-market reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • Chen Martinez· Dec 12, 2024

    Registry listing for okx-cex-market matched our evaluation — installs cleanly and behaves as described in the markdown.

  • Harper Srinivasan· Dec 12, 2024

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

  • Chaitanya Patil· Dec 4, 2024

    okx-cex-market reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • Diego Bhatia· Dec 4, 2024

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

  • Piyush G· Nov 23, 2024

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

  • Carlos Dixit· Nov 15, 2024

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

  • Mateo Kim· Nov 7, 2024

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

  • Kiara Rahman· Nov 3, 2024

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

  • Isabella Patel· Nov 3, 2024

    Registry listing for okx-cex-market matched our evaluation — installs cleanly and behaves as described in the markdown.

showing 1-10 of 53

1 / 6