Each skill now guides the AI Agent through full credential setup when
GMGN_API_KEY is not configured: generate Ed25519 key pair, show public
key to user with instructions to apply at https://gmgn.ai/ai, wait for
API key, then write to ~/.config/gmgn/.env.
- gmgn-token / gmgn-market / gmgn-portfolio: API key setup only
- gmgn-track: API key + optional private key for follow-wallet
- gmgn-swap: both API key and private key required from the start
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
GMGN API does not support IPv6. When a 401/403 error occurs and
credentials look correct, AI agents and users now have a clear
two-step diagnostic: list inet6 interfaces, then probe
ipv6.icanhazip.com to confirm whether outbound traffic is IPv6.
If confirmed, the instruction is to disable IPv6 immediately.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add IPv6 not supported warning to all 5 SKILL.md headers
- Add detailed `track follow-wallet` response field reference based on actual API output
- Fix `--tag` default value to empty in gmgn-token SKILL.md
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Replace `npm install -g gmgn-cli@1.1.0` with `npm install -g gmgn-cli`
across all SKILL.md files and CLAUDE.md, so users always install the
latest published version instead of a pinned one that may lack newer
commands (e.g. track).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add new `track` command group with three sub-commands:
- `track follow-wallet`: monitor trade activity of followed wallets (critical auth)
- `track kol`: KOL trade records with optional --chain and client-side --side filter
- `track smartmoney`: Smart Money trade records with optional --chain and client-side --side filter
- Remove follow-wallet, kol, smartmoney sub-commands from portfolio
- Add getKol/getSmartMoney optional chain param in OpenApiClient
- Switch getFollowWallet to criticalRequest (signature auth required)
- Align track follow-wallet options to actual API params (remove unsupported flags)
- Add skills/gmgn-track/SKILL.md with sub-command guide, options, response fields
- Add IMPORTANT notice to all SKILL.md files to prevent AI from scraping gmgn.ai
- Add CRITICAL RULE section to CLAUDE.md to enforce CLI-only data access
- Update Readme.md and Readme.zh.md: add gmgn-track skill, Track CLI section, user tip
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds a recommended pre-swap safety check section to gmgn-swap SKILL.md.
Before swapping into unknown tokens, agents can verify honeypot/rug risk
with a single curl call to Maiat's free API (no API key required).
- Returns trustScore (0-100), verdict (proceed/caution/avoid), riskFlags
- Zero dependencies — pure curl + jq
- Works for any ERC-20 on Base
deepfeature