mirror of https://github.com/GMGNAI/gmgn-skills.git synced 2026-11-02 07:46:11 +00:00

Files

T

chenjunfengandClaude Opus 5.5 e6574f95e4 feat(wallet skills): add gmgn-wallet-review and gmgn-wallet-style, route both

Adds two wallet skills and wires them into the routing.

gmgn-wallet-review (new): a glanceable trading portrait of one wallet. It
gives one style tag, a one-sentence recap of the record and a one-sentence
next step, for 1D / 7D / 30D / all, voiced 你 for the user's own wallet and
他 for anyone else's. It is a single SKILL.md with read-only gmgn-cli
portfolio calls, fixed rules and closed sentence templates. It covers SOL and
all 8 EVM chains, probing the chain for a 0x address.
- The recap names only problems in the trader's own trading: fees, holding
  time, loss cutting, sizing, adds, open bags, return trend and launches.
  Follower count appears only as a warning in visitor advice.
- Discipline rules from holdings, checked on 22 wallets: losers held 2x
  longer, losers sized 1.5x bigger (median per-buy ticket), adds 10 points
  worse, and 3+ open bags down 50% with $50+ cost.
- The next step never repeats the recap's problem.

gmgn-wallet-style (new to the repo): the full style tagging, with a 20-cell
title, speed subtitle and badges, each tag stating its triggering number.
It has a nine-chain allowlist and address patterns checked before any
command, and escapes every string it renders.

Both skills' tag rules match freq_level / pnl_level / style_title /
style_speed in gmgn-wallet-analysis/analyze.py. P5 needs ROI > 50% plus
token_num >= 5 plus ONE of {win rate >= 50%, heavy-loss share < 15%}. A diff
against the imported functions over 5,000+ cases gave 0 mismatches. The one
intended difference is gmgn-wallet-review's 3% 净盈 line at machine speed.

Routing:
- CLAUDE.md lists both skills and sends 这个钱包什么风格 / 交易风格 /
  wallet style to gmgn-wallet-style instead of the smart-money-profile
  workflow.
- gmgn-wallet-analysis hands style-only asks and one-line recap / next-step
  asks to the new skills.
- gmgn-wallet-score hands one-line recap asks to gmgn-wallet-review. Its
  description becomes a >- block (the old plain scalar failed yaml.safe_load)
  with identical text.
- Readme.md and Readme.zh.md list both skills.
No trigger phrase is claimed by two skill descriptions.

Both skills stop on a rejected API key (401 AUTH_KEY_INVALID) as well as on a
rate limit, and reference only skills that exist in this repo.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

2026-09-28 17:20:45 +08:00

14 KiB

Raw Blame History

CLAUDE.md

This file provides guidance to Claude Code when working with the gmgn-cli plugin.

CRITICAL RULE — Read This First

ALL queries about GMGN data MUST use gmgn-cli via the skills below.

This includes: trending tokens, token info, security checks, K-line / price history, wallet holdings, KOL trades, Smart Money trades, swaps, and any other on-chain data.

NEVER do any of the following to fetch GMGN data:

Web search (e.g. searching "gmgn trending solana")
WebFetch / curl to gmgn.ai or any gmgn domain
Browser automation or scraping
Any method other than gmgn-cli

Why: The gmgn.ai website requires login, uses dynamic rendering, and does not expose structured data. The CLI is the only correct and supported method. If you attempt to scrape the site, you will get no data or be blocked.

When a user asks anything about GMGN data — always invoke the matching skill and run the CLI command. No exceptions.

Project Overview

This is a Claude Code plugin — a collection of GMGN OpenAPI skills for on-chain operations. It provides CLI tools and skills for token queries, market data, wallet portfolio analysis, and swap execution across sol / bsc / base / eth.

Available Skills

Skill	Purpose	When to Use
`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", "check my order", or "buy this token" only when they also say to skip the checks; a plain buy request with no skip instruction is `gmgn-token-buy`; requires private key configured in `.env`
`gmgn-kline-pattern`	Names the chart pattern (uptrend channel / breakdown / bounce off the lows / distribution / basing / chop) and scores it 0-100 from six measurements computed off the kline response	User asks about 走势, 趋势, 形态, price action, chart pattern, "is it breaking down", "is it consolidating"; user wants a read of the chart rather than the raw candles
`gmgn-token-buy`	Resolves a token NAME to the one right contract, then sizes the buy order	User names a token by name/symbol (not only an address) and wants to buy it, or gives an address plus an amount and wants the order sized: 能不能买, 能不能冲, 我想梭, 帮我买 200u 的 XX, 确认是正主不是仿盘再买. Owns copycat disambiguation and position/slippage/gas sizing; hands execution to `gmgn-swap` after explicit confirmation.
`gmgn-contract-dd`	One 0-100 contract due-diligence score for a bare address	User pastes a token address and wants a verdict number, with no name to disambiguate and no amount to size.
`gmgn-holder-analysis`	Chip / holder structure of one token	User asks about holder distribution or chip concentration.
`gmgn-wallet-analysis`	Wallet decision dossier	User asks whether a wallet is worth copy-trading.
`gmgn-wallet-style`	One wallet's trading-style tags — a main title from the 20-cell frequency × P&L grid, a speed subtitle, badges; every tag states its triggering number	User asks what kind of trader a wallet is: 这个钱包什么风格, 交易风格, 是不是机器人, 是不是狙击盘的, 帮我给这个钱包打标签, "what's this wallet's trading style", "tag this wallet"
`gmgn-wallet-review`	One wallet in three lines — a single style tag, a one-sentence recap of its record, a one-sentence next step; 你 for the user's own wallet, 他 for others	A wallet address plus a request for a brief recap or what to change: 帮我复盘一下这个钱包, 一句话总结他的战绩, 我的打法有什么问题, 我钱包下一步该怎么打, 交易画像, 钱包风格加建议
`gmgn-cooking`	Launchpad token creation	User wants to create or launch a token.

Quick Decision Guide

Match the user's request to the right skill and workflow:

User says	Action
a plain buy request naming a token and/or an amount, with NO instruction to skip checks — "我想买 200u 的 PENGU", "帮我买 500 刀的 BONK", "买 1 个 SOL 的 WIF", "想梭 100u 的 XX", "帮我买点 dogwifhat", "XX 现在能买吗", "buy me $500 of PENGU"	`gmgn-token-buy` — this is the DEFAULT for any plain buy request. Route to `gmgn-swap` only if the user explicitly says skip/don't check/just buy/我很急.
token NAME or symbol + buy intent — "能不能买", "能不能冲", "我想梭", "帮我买 200u 的 XX", "确认是正主不是仿盘再买", with or without an amount	`gmgn-token-buy` — the only skill that resolves a name to the one right contract and sizes the order
bare token address + "safe?" / "打个分" / "尽调", no name to disambiguate and no amount to size	`gmgn-contract-dd`
"is this token safe", "check this token", "research this token", raw fields for an address already in hand	`gmgn-token` → full workflow: `docs/workflow-token-research.md`
"deep report", "full analysis", "全面分析这个项目", "深度报告", "值不值得重仓"	`gmgn-token` + `gmgn-market` → `docs/workflow-project-deep-report.md`
"what's trending", "hot tokens", "top tokens by volume"	`gmgn-market trending`
"走势怎么样", "什么形态", "is it breaking down"	`gmgn-kline-pattern`
"new tokens", "just launched", "pump.fun new"	`gmgn-market trenches --type new_creation`
"early project screening", "新币筛选", "值得埋伏吗", "哪些新项目有聪明钱"	`gmgn-market trenches` → `docs/workflow-early-project-screening.md`
"daily brief", "today's market", "每日简报", "今天市场怎么样", "聪明钱今天买了什么"	`gmgn-market` + `gmgn-track` → `docs/workflow-daily-brief.md`
"what is smart money buying", "what are KOLs trading"	`gmgn-track smartmoney` / `gmgn-track kol`
"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`
"这个钱包什么风格", "交易风格", "是不是机器人", "是不是狙击盘的", "帮我给这个钱包打标签", "wallet style", "tag this wallet" — wallet address + wants the style tags themselves	`gmgn-wallet-style`. A bare address with no question stays with `gmgn-wallet-analysis`
"smart money profile", "聪明钱画像", "这个钱包是长线还是短线", "跟着他买收益如何", "聪明钱排行榜"	`gmgn-portfolio` + `gmgn-track` → `docs/workflow-smart-money-profile.md`
"帮我复盘一下这个钱包", "一句话总结他的战绩", "我的打法有什么问题", "我钱包下一步该怎么打", "交易画像", "钱包风格加建议，简短点" — wallet address + wants a short recap or what to change	`gmgn-wallet-review` — 打法 / 风格 / 战绩 paired with 问题, 建议, 复盘 or 一句话 routes here; asked alone, they stay with the rows around it
"钱包盈利能力怎么样", "钱包战绩怎么样", "is this wallet profitable"	`gmgn-wallet-score` (profitability angle — track-record score); a one-line recap of the record → `gmgn-wallet-review`
"跟单评分", "钱包评分", "值不值得跟单", "is this wallet worth copying", "copy trade score", wallet address provided + copy-trade decision	`gmgn-wallet-score` (copy-tradeability angle — score + backtest)
"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"	`gmgn-wallet-score` (Dev-reputation angle)
"risk warning", "风险预警", "有没有巨鲸出货", "流动性正常吗", "这个项目还安全吗"	`gmgn-token` + `gmgn-track` → `docs/workflow-risk-warning.md`
"swap", "sell TOKEN", "buy TOKEN" only when the user says skip the checks	`gmgn-swap` — MUST run `gmgn-token security` on output token first. A plain "buy TOKEN" with no skip-the-checks instruction is `gmgn-token-buy`.
"chart", "price history", "kline", "OHLCV"	`gmgn-market kline`
"my holdings", "my portfolio", "what tokens do I hold"	`gmgn-portfolio holdings`

Workflow docs (read these when the user wants a full multi-step analysis):

Token research (address → buy/watch/skip): docs/workflow-token-research.md
Project deep report (comprehensive analysis + verdict): docs/workflow-project-deep-report.md
Wallet analysis (address → follow/skip): docs/workflow-wallet-analysis.md
Smart money profile (trading style, copy-trade estimate, leaderboard): docs/workflow-smart-money-profile.md
Risk warning (whale exit, liquidity drain, dev dump check): docs/workflow-risk-warning.md
Early project screening (new tokens → smart money filter → verdict): docs/workflow-early-project-screening.md
Daily brief (market pulse + smart money moves + early watch + risk scan): docs/workflow-daily-brief.md
Market discovery (find opportunities from trending): docs/workflow-market-opportunities.md

Architecture

src/ — TypeScript source (CLI commands, API client, signer)
skills/ — 9 skill definitions for Claude Code
dist/ — Compiled output (generated by npm run build)
.claude-plugin/ — Plugin metadata for Claude Code

Prerequisites

Config lookup order (project overrides global):

~/.config/gmgn/.env — global config, set once for all projects
.env in the current working directory — project-level override (takes precedence)

Required variables:

GMGN_API_KEY — apply at https://gmgn.ai/ai
GMGN_PRIVATE_KEY — PEM content, required for swap/order commands only

If the user has not configured credentials or commands fail with a missing key error, guide them to create ~/.config/gmgn/.env:

mkdir -p ~/.config/gmgn
cat > ~/.config/gmgn/.env << 'EOF'
GMGN_API_KEY=your_api_key_here
EOF

Auth Modes

Mode	Commands	Requirements
Normal	token / market / portfolio (except holdings) / track kol / track smartmoney / order quote	`GMGN_API_KEY` only, no signature
Critical	swap / order (except order quote) / portfolio holdings / track follow-wallet	`GMGN_API_KEY` + `GMGN_PRIVATE_KEY` — CLI handles signing automatically

SKILL.md Authoring Rules

When creating or updating any file in skills/:

Language: English only — no bilingual content. SKILL.md files are read by AI, not humans.
Package runner: Always use the pre-installed gmgn-cli binary (e.g. gmgn-cli token info ...). Never use npx gmgn-cli or npx gmgn-cli@<version> — npx downloads the package at runtime alongside live credentials. The package must be installed once with npm install -g gmgn-cli.
Section order: Sub-commands → Supported Chains → Prerequisites → Parameters/Options (if needed) → Usage Examples → Notes
--raw flag: All commands support --raw for single-line JSON output. Always document it in the Notes section.
YAML frontmatter: Quote argument-hint values that contain | characters to avoid YAML parsing errors.

Keeping Docs in Sync

src/commands/*.ts is the single source of truth for all commands, sub-commands, and options.

When any file in src/commands/ is modified, you MUST also update:

skills/gmgn-{command}/SKILL.md — Sub-commands table and Options tables must exactly reflect the current command definitions.
Readme.md — The ## Commands section bash examples must reflect added/removed commands or options.
Readme.zh.md — Same as Readme.md for the bash examples (Chinese descriptions are maintained separately).

14 KiB Raw Blame History Unescape Escape