coingecko▌
starchild-ai-agent/official-skills · updated Apr 8, 2026
MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.
Comprehensive crypto market data including prices, charts, trending coins, exchange info, and global statistics.
- ›28+ tools covering spot prices, OHLC candles, historical charts, trending/top movers, and new coin discovery
- ›Market overview capabilities: global stats, DeFi metrics, sector performance by category, and exchange listings with volumes
- ›Coin and exchange detail queries: tickers, trading pairs, contract address lookups, and NFT collection data
- ›Automatic symbol resolution fo
CoinGecko Skill
🚫 CRITICAL: STOP — READ THIS BEFORE CALLING ANY TOOL
The #1 error is calling Coinglass tools instead of CoinGecko tools. They have similar names but are COMPLETELY DIFFERENT systems.
WRONG → RIGHT Tool Substitution Table
| ❌ NEVER call this | ✅ Call this instead | How to tell them apart |
|---|---|---|
cg_coins_market_data |
cg_coins_markets |
market_data=Coinglass derivatives. markets=CoinGecko spot. |
cg_ohlc_history |
coin_ohlc |
ohlc_history=Coinglass futures candles. coin_ohlc=CoinGecko spot candles. |
cg_pair_market_data |
cg_coin_tickers |
pair_market_data=Coinglass futures pair. coin_tickers=CoinGecko spot pairs. |
cg_supported_exchanges |
cg_exchanges |
supported_exchanges=Coinglass futures. exchanges=CoinGecko spot. |
cg_taker_exchanges |
cg_exchange |
taker=Coinglass volume. exchange=CoinGecko exchange info. |
cg_aggregated_taker_volume |
cg_coin_tickers |
taker_volume=Coinglass. coin_tickers=CoinGecko volume across exchanges. |
defillama_chains |
cg_global_defi |
For DeFi stats from CoinGecko, use cg_global_defi(). |
Also FORBIDDEN:
- ❌
web_search/web_fetch— ALL data is available via native CoinGecko tools above. NEVER use web_search for crypto market data. - ❌
bashfor data processing — CoinGecko tools return clean data. No bash needed. - ❌ NEVER answer with training data — all prices, rankings, OHLC are stale. CALL THE TOOL.
⚠️ MANDATORY TOOL CALLS — You MUST call a tool before answering these
| Request type | You MUST call | Why |
|---|---|---|
| K线 / OHLC / candlestick / open high low close | coin_ohlc(coin_id, days) |
Price data is real-time; training data is stale |
| 走势图 / price chart / 价格趋势 | coin_chart(coin_id, days) |
Same reason |
| 当前价格 / price right now | coin_price(coin_ids) |
Training data has no live prices |
DO NOT return any numeric market data (prices, OHLC values, percentages) without calling a tool first.
⚡ Question → Tool Map (match first keyword, call immediately)
| Question keyword | Tool to call | Example |
|---|---|---|
| 价格 / price / 多少钱 (single coin) | coin_price(coin_id) |
coin_price(coin_ids="bitcoin") |
| K线 / OHLC / candlestick / 蜡烛图 | coin_ohlc(coin_id, days) |
coin_ohlc(coin_id="ethereum", days=7) |
| 走势 / trend / price chart / 价格历史 | coin_chart(coin_id, days) |
coin_chart(coin_id="solana", days=30) |
| 热门 / trending / 趋势币 | cg_trending() |
cg_trending() |
| 涨幅最大 / 跌幅最大 / gainers / losers | cg_top_gainers_losers() |
cg_top_gainers_losers() |
| 新币 / 新上线 / new coins / recently added | cg_new_coins() |
cg_new_coins() |
| 总市值 / BTC市占率 / global / 晨报 / 市场概况 | cg_global() |
cg_global() |
| DeFi总市值 / DeFi TVL / DeFi dominance | cg_global_defi() |
cg_global_defi() |
| 板块 / sector / category / L1 / L2 / Meme / AI coins | cg_categories() |
cg_categories() |
| 板块内个币 / Meme前10 / AI币排名 / DeFi币排名 | cg_coins_markets(category=X) |
cg_coins_markets(category="meme-token", per_page=10) |
| 市值排名 / top 10 / ranking / 前10币 | cg_coins_markets(per_page=N) |
cg_coins_markets(per_page=10) |
| ATH / 历史最高 / 社区 / dev / 研究 / fundamentals | cg_coin_data(coin_id) |
cg_coin_data(coin_id="solana", community_data=True) |
| 对比两个币 / compare / XX vs YY | cg_coin_data() × 2 |
call once per coin |
| NFT排名 / NFT市场 / floor price / top NFTs | cg_nfts_list() |
cg_nfts_list() |
| 某个NFT (BAYC/Punks/Azuki) | cg_nft(nft_id) |
cg_nft(nft_id="bored-ape-yacht-club") |
| 交易所详情 / Binance详情 / exchange data | cg_exchange(exchange_id) |
cg_exchange(exchange_id="binance") |
| 交易所列表 / exchange ranking | cg_exchanges() |
cg_exchanges() |
| 交易对 / trading pairs / 流动性分布 | cg_coin_tickers(coin_id) |
cg_coin_tickers(coin_id="bitcoin") |
| 交易所交易量趋势 / volume chart | cg_exchange_volume_chart(exchange_id) |
cg_exchange_volume_chart(exchange_id="binance", days=30) |
| 合约地址价格 / token price on-chain | cg_token_price(platform, contract) |
cg_token_price(platform="ethereum", contract_addresses="0xa0b...") |
| 搜索币 / 找币 / coin lookup / search | cg_search(query) |
cg_search(query="pepe") |
| 永续合约交易所 / derivatives exchange / OI排名 | cg_derivatives_exchanges() |
cg_derivatives_exchanges() |
| 合约ticker / perpetual / funding / basis | cg_derivatives() |
cg_derivatives() |
| 交易所对比 + 永续交易所 | cg_exchanges() + cg_derivatives_exchanges() |
both calls |
🌳 Decision Tree
How many coins?
├─ ONE coin
│ ├─ Just price? → coin_price()
│ ├─ ATH/community/dev/deep? → cg_coin_data()
│ ├─ OHLC candles? → coin_ohlc()
│ ├─ Price trend? → coin_chart()
│ └─ Unknown ID? → cg_search() first
├─ MULTIPLE coins / ranking
│ ├─ Sector aggregate (板块总市值)? → cg_categories()
│ ├─ Sector individual (Meme前10)? → cg_coins_markets(category=X)
│ └─ General ranking? → cg_coins_markets(per_page=N)
├─ NFTs → cg_nfts_list() or cg_nft(nft_id)
├─ Exchange → cg_exchange(id) or cg_exchanges()
├─ Global → cg_global() or cg_global_defi()
└─ Token by contract → cg_token_price()
Common Category IDs
meme-token, artificial-intelligence, layer-1, layer-2, decentralized-finance-defi, gaming, real-world-assets-rwa
Output Formatting
- Prices: always use
$sign →$66,697 - Percentages: always use
%→+4.2% - NFT floor in ETH: show USD too →
5.17 ETH ($10,534)
Important Notes
- CoinGecko uses slug IDs: "bitcoin", "ethereum", "solana". Symbols (BTC, ETH, SOL) auto-resolve.
- If unsure about a coin ID →
cg_search(query="coin name")first. - Most questions need only 1-2 tool calls. Do NOT chain 3+ calls.
Common Issues
coin_price failed with invalid ID
Solution: Use cg_search(query="coin name") to find the correct CoinGecko ID first, or use the symbol directly (e.g., 'COMP').
How to use coingecko on Cursor
AI-first code editor with Composer
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 coingecko
Execute installation command
Execute the skills CLI command in your project's root directory to begin installation:
The skills CLI fetches coingecko from GitHub repository starchild-ai-agent/official-skills and configures it for Cursor.
Select Cursor when prompted
The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:
Verify installation
Confirm successful installation by checking the skill directory location:
Reload or restart Cursor to activate coingecko. Access the skill through slash commands (e.g., /coingecko) 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
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.Install product management skill
- 2.Start with user story generation for known feature
- 3.Progress to competitive analysis: research 2-3 competitors
- 4.Use for roadmap prioritization: apply RICE/ICE scoring
- 5.Draft stakeholder communications and refine based on feedback
- 6.Build template library for recurring PM tasks
- 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▌
- 1Basic: user stories, feature specs, status updates
- 2Intermediate: competitive analysis, prioritization frameworks, PRDs
- 3Advanced: product strategy, go-to-market planning, OKR setting
- 4Expert: product vision, market positioning, business model innovation
Discussion
Product Hunt–style comments (not star reviews)- No comments yet — start the thread.
Ratings
4.6★★★★★62 reviews- ★★★★★Dhruvi Jain· Dec 20, 2024
Useful defaults in coingecko — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
- ★★★★★Sofia Liu· Dec 12, 2024
coingecko is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
- ★★★★★Anaya Sethi· Dec 4, 2024
Solid pick for teams standardizing on skills: coingecko is focused, and the summary matches what you get after install.
- ★★★★★Naina Khanna· Nov 23, 2024
We added coingecko from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
- ★★★★★Oshnikdeep· Nov 11, 2024
coingecko is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
- ★★★★★Kwame Abbas· Nov 11, 2024
coingecko reduced setup friction for our internal harness; good balance of opinion and flexibility.
- ★★★★★Advait Sanchez· Nov 3, 2024
Useful defaults in coingecko — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
- ★★★★★Anaya Shah· Oct 22, 2024
I recommend coingecko for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
- ★★★★★Advait Ramirez· Oct 14, 2024
coingecko fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
- ★★★★★Ganesh Mohane· Oct 2, 2024
Keeps context tight: coingecko is the kind of skill you can hand to a new teammate without a long onboarding doc.
showing 1-10 of 62