Add ETH chain support to all P0 commands across CLI and SKILL.md docs:
Commands with ETH support added:
- token info/security/pool/holders/traders
- market kline/trending
- portfolio info/holdings/activity/stats/token-balance
- track follow-wallet
- swap, order quote/get
P1/P2 commands remain sol/bsc/base only:
- track kol/smartmoney (P1)
- multi-swap, order strategy create/list/cancel (P1)
- portfolio created-tokens (P2)
Also adds ETH chain currencies, explorer links, and gas price bounds
to gmgn-swap SKILL.md.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- parseDuration: bare numbers now default to minutes (e.g. "5" → "5m") instead of hard error
- Print a warning to stderr so users know the implicit conversion is happening
- Update SKILL.md: document unit suffix recommendation and bare-number fallback behavior
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Align SKILL with OpenAPI validation: signal_type must not include 14, 15,
or 16 (400 BAD_REQUEST). Update examples and clarify behavior when
--signal-type is omitted.
Made-with: Cursor
- Add POST /v1/market/token_signal client method and TokenSignalGroup interface
- Add market signal sub-command with individual flags for single-group queries
- Support --groups <json> override for multi-group parallel queries
- Document max 50 results per group limit
- Update SKILL.md, cli-usage.md, and README with signal types, response fields, and examples
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Shorten all 6 descriptions to 60-80 words with high-value terms in the
first 50 words (highest embedding weight). Add "crypto", "meme coin",
"meme token" where missing. Remove redundant chain-name repetition in
"Use when" sections. Keeps discriminating boundary hints (e.g. gmgn-track
→ gmgn-portfolio redirect for single-wallet queries).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Rewrite description fields across all 6 skills to follow a consistent
"Get [capabilities] via GMGN API. Use when user asks for [intents]."
pattern, aligned with how Openclaw agents search clawhub.ai. Adds
natural-language intent keywords (price, market cap, holder list,
Smart Money, KOL trades, copy-trading, etc.) so skills surface higher
in skill-search results.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Redefine price_scale: profit_stop uses gain % from entry (e.g. "100" = +100% / 2×), loss_stop uses drop % from entry (e.g. "65" = drops 65%)
- Update all condition-order examples in SKILL.md and both READMEs accordingly
- Add is_anti_mev recommended note and anti-mev flag to swap examples
- Add order strategy create to Financial Risk Notice
- Fix response section heading format (bold → ###) for order strategy create/list
- Add reset_at field extraction guidance to Rate Limit Handling in all 6 skills
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
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>
- OpenApiClient: extend getTrenches/buildTrenchesBody to accept and spread
server-side filter fields into each category section of the request body
- SKILL.md: clarify entrapment_ratio description as Entrapment/Phishing
- workflow-early-project-screening: add filter-preset examples to Step 1
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Validated all 31 min/max field pairs against the live API using extreme values.
Fields returning baseline count (80) on both min and max tests are silently
ignored by the server — confirmed not supported.
Removed fields (12 flags, 6 pairs):
- min/max_volume_24h
- min/max_net_buy_24h
- min/max_swaps_24h
- min/max_buys_24h
- min/max_sells_24h
- min/max_x_follower
Also removed min_volume_24h from the `strict` filter preset.
Remaining 50 filter flags (25 pairs) are confirmed to work.
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>
Replace raw --body JSON parameter with structured CLI flags for better AI agent readability.
Add full response key reference and SOL/BSC/Base examples to SKILL.md and docs.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
