"description":"GMGN OpenAPI skills for AI coding assistants — token info, market data, wallet portfolio, and swap execution across sol / bsc / base / eth / robinhood",
"description":"GMGN OpenAPI skills for AI coding assistants — token info, market data, wallet portfolio & copy-trade scoring, and swap execution across sol / bsc / base / eth / robinhood",
"owner":{
"name":"GMGN"
},
@@ -9,7 +9,7 @@
{
"name":"gmgn-cli",
"source":"./",
"description":"4 GMGN skills — token info & security, K-line market data, wallet portfolio analysis, and DEX swap execution",
@@ -29,6 +29,7 @@ This is a **Claude Code plugin** — a collection of GMGN OpenAPI skills for on-
| `gmgn-token` | Token info, security, pool, holders, traders | User asks about a token's price, market cap, security risk, liquidity pool, top holders, or top traders; user wants to research a token before buying; user asks "is this token safe", "who holds this token", "what's the liquidity" |
| `gmgn-market` | K-line / candlestick market data + trending tokens + newly launched launchpad tokens | User asks for price history, chart data, OHLCV candles, trading volume over time; user wants to analyze price trends; user asks "show me the 1h chart", "what was the price last week", "give me kline data for this token"; user wants to discover hot or trending tokens; user asks "what tokens are trending", "show me top tokens by volume", "find hot tokens on SOL"; **user asks about newly launched tokens, fresh tokens, latest tokens on launchpads** — e.g. "show me new tokens on pump.fun", "what tokens just launched on SOL", "find newly created tokens", "latest tokens on letsbonk" → use `market trenches --type new_creation` |
| `gmgn-portfolio` | Wallet holdings, activity, trading stats, token balance | User asks about a wallet's holdings, P&L, transaction history, trading statistics, or token balance; user wants to analyze a wallet; user asks "what tokens does this wallet hold", "show me recent trades", "what's the win rate of this wallet" |
| `gmgn-wallet-score` | Wallet scoring across three angles — profitability (track-record score), copy-tradeability (score + latency/slippage/gas backtest), and Dev reputation for token-creator wallets — plus trading-style tags | User asks about a wallet's profitability ("钱包盈利能力怎么样", "is this wallet profitable"), copy-trade worthiness ("is this wallet worth copying", "跟单评分", "钱包评分", "值不值得跟单", "if I copy this wallet what's my real return"), or launch/Dev reputation ("钱包发盘情况怎么样", "是不是发币方钱包", "dev 信誉怎么样"); user gives a wallet address and wants any of these judgments |
| `gmgn-track` | Track trade activity of wallets I follow, KOL trades, Smart Money trades across chains | User asks about trades from wallets they follow; user wants to see what KOLs or Smart Money are buying/selling; user asks "show me what wallets I follow have traded recently", "what are KOLs buying", "show me smart money moves on BSC" |
| `gmgn-swap` | Token swap execution + order status query | User wants to swap tokens, execute a trade, or check an order status; user asks "swap SOL for USDC", "buy this token", "check my order"; **requires private key configured in `.env`** |
@@ -48,6 +49,9 @@ Match the user's request to the right skill and workflow:
| "wallets I follow", "my followed wallets traded" | `gmgn-track follow-wallet` |
| "analyze this wallet", "is this wallet worth following", wallet address provided | `gmgn-portfolio` → full workflow: `docs/workflow-wallet-analysis.md` |
| [`/gmgn-cooking`](skills/gmgn-cooking/SKILL.md) | One-command cooking orders (buy + take-profit/stop-loss in a single flow) | [SKILL.md](skills/gmgn-cooking/SKILL.md) |
@@ -350,7 +351,7 @@ Skills are automatically discovered via the `.cursor-plugin/` configuration.
```bash
echo "$(npm root -g)/gmgn-skills/skills"
```
3. Restart Cline — `/gmgn-token`, `/gmgn-market`, `/gmgn-portfolio`, `/gmgn-track`, `/gmgn-swap`, `/gmgn-cooking` will be available
3. Restart Cline — `/gmgn-token`, `/gmgn-market`, `/gmgn-portfolio`, `/gmgn-wallet-score`, `/gmgn-track`, `/gmgn-swap`, `/gmgn-cooking` will be available
description: Score any wallet address across three angles — profitability (a real track-record score: is this trader actually good?), copy-tradeability (can YOU actually capture what it makes, plus a latency/slippage/gas backtest), and Dev reputation (if it's mostly a token launcher, how trustworthy are its launches) — plus trading-style tags, all computed deterministically from GMGN portfolio data. Use when the user asks about a wallet's profitability ("这个钱包盈利能力怎么样", "钱包战绩怎么样", "is this wallet profitable"), copy-trade worthiness ("is this wallet worth following", "跟单评分", "钱包评分", "值不值得跟单", "if I copy this wallet what's my real return"), or token-launch/Dev reputation ("这个钱包发盘情况怎么样", "是不是发币方钱包", "dev 信誉怎么样", "is this a token-creator wallet"), or gives a wallet address and wants any of these judgments.
**BEFORE RUNNING ANY COMMAND: Run `gmgn-cli config --check`. If exit code is 0, proceed normally. If exit code is 1, (1) run `gmgn-cli config` and show the output to the user; (2) once the user sends the API Key, run `gmgn-cli config --apply <KEY>` to complete configuration and verification, then show the output to the user. If `--check` returns an error (unknown option or command not found), tell the user to run `npm install -g gmgn-cli` to update, then retry.**
**IMPORTANT: Always use `gmgn-cli` commands. Do NOT use web search, WebFetch, curl, or visit gmgn.ai — the website requires login and does not expose structured data.**
**IMPORTANT: Do NOT guess field names or values. Fields not listed in [Field Reference](#field-reference) below have not been confirmed against the live API — if the script's defensive lookups come back empty for them, degrade gracefully (see [Notes](#notes)) rather than inventing a value.**
**⚠️ IPv6 NOT SUPPORTED: If you get a `401` or `403` error and credentials look correct, check for IPv6 immediately: (1) list all network interfaces and their IPv6 addresses — run `ifconfig | grep inet6` (macOS) or `ip addr show | grep inet6` (Linux); (2) send a test request to `https://ipv6.icanhazip.com` — if the response is an IPv6 address, outbound traffic is going via IPv6. Tell the user immediately: "Please disable IPv6 on your network interface — gmgn-cli commands only work over IPv4."**
When the user gives a wallet address, extract `--chain` and `--wallet` from their message, then run the analysis script below — it computes all three angles (profitability, copy-tradeability, Dev reputation) from a single shared data pull, regardless of which one the user actually asked about. Also detect the user's language: set `LANG` to `'zh'` if the user wrote in Chinese, `'en'` if in English (default `'zh'`). Ask for `--latency` / `--slippage` / `--gas` only if the user wants a customized backtest — otherwise use the defaults baked into the script. Once the script runs, decide which section to lead with in your reply — see [Framing the Report by Question](#framing-the-report-by-question) below.
## Core Concepts
This skill deliberately splits "is this trader good?" from "can you copy it?" — a wallet can be great at trading and terrible to copy, or mediocre at trading but easy to ride along with:
- **Track-record score (0–100)** — Is this trader actually good, judged by outcome distribution, not just win rate. A wallet with a 30% win rate can still score high here if it cuts losses hard and the 30% that win pay for the rest — that's disciplined risk management, not luck.
- **Copy-tradeability score (0–100)** — Even if the wallet is genuinely skilled, can *you* capture that edge? A wallet that snipes sub-$100k market caps or round-trips in 5 seconds is not copyable — by the time your transaction lands, the wallet has already exited and you're the exit liquidity. This score penalizes early entries, thin per-trade margins, ultra-short holds, and bot-tier trade frequency.
- **Backtest estimate** — A concrete "what you'd actually keep" number: the wallet's raw return minus your entry-latency price drift, minus round-trip slippage, minus gas — using the latency/slippage/gas the user specifies (or sane defaults).
- **Dev-reputation score** — Only computed when the wallet is itself a token creator (its `created_token_count` exceeds half its traded-token count — i.e. it's mostly launching, not trading). Judges the wallet as a *developer*: survival rate of tokens it created, how many are stuck on the bonding curve and never graduated, and whether its recent launches passed a basic security check. When this applies, entry-timing / win-rate factors are unreliable (the wallet controls its own token's price and holder list) — the track-record and copy-tradeability scores are shown at a steep discount, and the verdict pivots to Dev reputation instead.
- **No trading history** — If the wallet has zero buy/sell transactions in the sampled period (only transfers/airdrops), none of the above can be computed honestly. The script detects this and reports it plainly instead of forcing a score onto empty data.
## Framing the Report by Question
This skill answers three related but distinct questions from **one shared data pull** — always run the full [Analysis Script](#analysis-script) regardless of which angle the user asked about; the underlying `portfolio stats` / `activity` / `created-tokens` / `token security` calls don't change, only what you lead with in your reply does. Never re-run the script per angle — that just burns extra rate-limit budget for data you already have.
| User's question | Lead with | Still mention, briefer |
|---|---|---|
| Profitability — "这个钱包盈利能力怎么样", "钱包战绩怎么样", "is this wallet profitable" | 🎯 Track-Record Score + factors | Style tags. Skip the backtest and Dev section unless the wallet turns out to be a Dev (see below) |
| Copy-trade worthiness — "值不值得跟单", "is this wallet worth copying", "if I copy this wallet what's my real return" | 🚀 Copy-Tradeability Score + 🧮 Backtest | Track-Record score as context, and the final Verdict |
| Dev/launch reputation — "这个钱包发盘情况怎么样", "是不是发币方钱包", "dev 信誉怎么样", "is this a token-creator wallet" | 👨💻 Dev-Reputation section | That this discounts the other two scores (self-dealing) — no need to walk through their factors in detail |
| Generic — "帮我看看这个钱包", "钱包评分", an address with no specific angle | The full report, all sections | — |
**Safety override**: if the user asked a Profitability or Copy-tradeability question but the wallet turns out to be classified as a Dev wallet (`dev is not None`), still surface the Dev-Reputation section and the self-dealing discount notice up front — a wallet that mostly launches tokens needs that caveat regardless of which angle was asked, since it changes how much the other two scores can be trusted.
## Analysis Script
Run this Python script inline, replacing the `<FILL_IN_*>` placeholders with the actual values. `LATENCY_S` / `SLIPPAGE_PCT` / `GAS_USD` / `SAMPLE` default to `3.0` / `0.05` / `0.2` / `200` if the user didn't specify — pass those literals when unspecified.
```python
python3<<'PYEOF'
importjson,math,subprocess
CHAIN="<FILL_IN_CHAIN>"
WALLET="<FILL_IN_WALLET_ADDRESS>"
LANG="<FILL_IN_LANG>"# 'zh' or 'en'
LATENCY_S=<FILL_IN_LATENCY># seconds you'd lag entering after this wallet (default 3.0)
SLIPPAGE_PCT=<FILL_IN_SLIPPAGE># one-sided slippage fraction, e.g. 0.05 = 5% (default 0.05)
GAS_USD=<FILL_IN_GAS># your cost per trade in USD (default 0.2)
SAMPLE=<FILL_IN_SAMPLE># activity rows to sample, max 400 (default 200)
"This address has no real buy/sell activity in the last 7 days (may be a new wallet, or its holdings were transferred/airdropped in) — not enough data to score, skipping."))
print(f" ⚠️ {_('该钱包主要在发币而非交易——下面两个分已按 ×0.45 打折显示，仅供参考。','This wallet mostly launches tokens rather than trading — the two scores below are shown at a ×0.45 discount for reference only.')}")
print()
sec=_("🎯 真实战绩分（这交易员是不是真有本事）","🎯 Track-Record Score (is this trader actually good?)")
Fields the script reads, confirmed against `portfolio stats` / `portfolio activity` / `portfolio created-tokens` / `token security` output (see [gmgn-portfolio](../gmgn-portfolio/SKILL.md) and [gmgn-token](../gmgn-token/SKILL.md) for the full reference):
| `token security` | `is_honeypot`, `renounced_mint`, `renounced_freeze_account` (SOL), `open_source` (EVM) | Recent-launch security scan for Dev reputation |
**Fields used defensively, not guaranteed present in every API response** — the script degrades gracefully (see [Notes](#notes)) rather than failing if these are absent:
| Field | Used for | Degrade behavior if missing |
| `token.total_supply` on activity rows | Entry market-cap estimate (`price_usd × total_supply`) | `entry_under_100k` / `median_entry_mcap` fall back to `0` — copy-tradeability's entry factor and backtest drift use a neutral assumption |
| `gas_usd` on activity rows | Average gas cost display | Falls back to `0`; the backtest still uses the user-specified `--gas` |
| `event_type` on activity rows | buy/sell classification | Falls back to the `type` field per the [gmgn-portfolio](../gmgn-portfolio/SKILL.md) reference |
## Scoring Rules Reference
**Track-record score** (0–100, weighted sum) — rewards disciplined risk management over raw win rate:
| Entry mcap | 22% | Later entries score higher — sub-$100k entries mean you'd be buying after the wallet already has its position |
| Profit per trade | 22% | Thin average per-trade profit (< ~$30–80) gets eaten by slippage and gas |
| Hold vs latency | 20% | Penalizes both high 5-second flip rates and very short average holds — you can't react that fast |
| Execution feasibility | 18% | Penalizes very high trade counts (bot-tier, > ~1000/week) — no human can keep pace |
| Edge type | 18% | Speed/scale-driven edges (early entries, fast flips) are not learnable/copyable; selection/timing edges are |
**Dev-reputation score** (0–100, applies only when the wallet is a token creator) — survival-rate driven:
- Base: `0.25 + 0.55 × survival_rate` (survival = tokens still open with ≥$4,000 liquidity, or `open_ratio` if no per-token data)
-`− 0.30 ×` penalty for heavy bonding-curve pileup (`inner_count` beyond 50, capping at 1000 — a hallmark of factory/serial-launch wallets)
-`+ 0.15 ×` bonus for a strong all-time-high launch, gated by survival rate (a factory wallet's one lucky moonshot doesn't count)
-`− 0.35 ×` penalty for the fraction of recently-scanned launches that failed a basic security check
- **Self-dealing discount**: when a wallet is classified as a Dev (its own launches make up more than half its traded tokens), the track-record and copy-tradeability scores are shown at `× 0.45` — its own entry timing and win rate are self-authored, not a market read.
## Verdict Rules
| Condition | Verdict |
|-----------|---------|
| Wallet is a Dev, Dev-reputation < 40 | 🔴 Stay away from its new launches |
| Wallet is a Dev, Dev-reputation ≥ 40 | 🟡 Check survival rate / security record before following new launches |
| Track ≥65, Copy <35 | ⚠️ Learn the discipline, don't copy the entries |
| Track ≥60, Copy ≥55 | 🟢 Worth a small copy-trade to verify |
| Track <40 | 🔴 Not recommended as a copy-trade target |
| Otherwise | 🟡 Worth watching; verify latency/slippage cost with a small trade first |
-`GMGN_API_KEY` configured in `~/.config/gmgn/.env` (exist auth only — no private key required for this skill)
## Rate Limit Handling
All routes this skill calls go through GMGN's leaky-bucket limiter with `rate=20` and `capacity=20`. Sustained throughput is roughly `20 ÷ weight` requests/second, and the max burst is roughly `floor(20 ÷ weight)` when the bucket is full. All of them use **exist auth** (API Key only, no private key needed).
A single run of this skill's script can burn through several of these in sequence: 1×`portfolio stats` + up to 4×`portfolio activity` (pagination) + 1×`portfolio created-tokens` + up to 3×`token security` (Dev security scan) — only the last two fire when the wallet is classified as a Dev. Account for that combined weight before batch-scoring several wallets back to back.
**When a request returns `429`, stop and proactively tell the user exactly when they can retry — never fail silently, never keep retrying without saying anything.**
- Extract the reset time: read `X-RateLimit-Reset` from the response headers (Unix timestamp), or if the response body contains `reset_at` (e.g., `{"code":429,"error":"RATE_LIMIT_BANNED","message":"...","reset_at":1775184222}`), use that instead — it's the Unix timestamp when the ban lifts (typically 5 minutes for a ban).
- Convert whichever timestamp you got to the user's local time and state it plainly, e.g. *"Rate-limited — you can retry this wallet after 14:32:05 (in ~4 minutes)."* Do this even if the run partially succeeded (see below) — the user needs to know when the rest of the analysis can resume.
- **Resume, don't restart**: if the script is mid-run (e.g. the Dev security scan hits `429` after `portfolio stats` and `activity` already succeeded), report what you already have (stats/tags/track-record score can still be shown), state the reset time for the remaining calls, and re-run only those remaining calls after it passes — don't re-fetch data you already have.
- For `RATE_LIMIT_EXCEEDED` or `RATE_LIMIT_BANNED`, repeated requests during the cooldown extend the ban by 5 seconds each time, up to 5 minutes. Never loop retries — wait for the stated reset time before trying again.
- Scoring multiple wallets in one request (a leaderboard-style comparison): space the calls out or reduce `--sample` rather than firing all wallets' full analysis concurrently. If one wallet in the batch gets rate-limited, report the completed wallets immediately and tell the user when the rest will be ready, rather than holding the whole batch back silently.
## Notes
- This skill only reads data (`portfolio stats` / `activity` / `created-tokens`, `token security`) — it never executes a trade. For actually copy-trading, use [gmgn-swap](../gmgn-swap/SKILL.md) after this skill gives a 🟢 verdict.
- Scores over a 7-day window can be noisy for low-trade-count wallets — the sample-size factor in the track-record score already discounts this, but treat a score built on <10 trades as low-confidence and say so.
- The backtest (`--latency` / `--slippage` / `--gas`) is a rough estimate, not a precise simulation — actual slippage depends on the specific token's liquidity at the moment you'd have traded it.
- Dev-reputation is only computed when `created_token_count` exceeds half the wallet's traded-token count — a wallet that launched one token in passing while mostly trading normally will NOT be treated as a Dev, and its trading-style tags/scores apply as normal.
- Use `--raw` on any underlying `gmgn-cli` command to get single-line JSON if you want to inspect the raw response yourself before trusting a derived field.
## References
| Skill | Description |
|-------|--------------|
| [gmgn-portfolio](../gmgn-portfolio/SKILL.md) | Underlying `portfolio stats` / `activity` / `created-tokens` commands and full field reference |
| [gmgn-token](../gmgn-token/SKILL.md) | `token security` command used for the Dev-reputation security scan |
| [gmgn-track](../gmgn-track/SKILL.md) | Discover candidate wallets to score — Smart Money / KOL / followed-wallet trade feeds |
| [gmgn-swap](../gmgn-swap/SKILL.md) | Execute an actual copy-trade once this skill's verdict is 🟢 |
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
GMGN.AI