Surface key features upfront: buying/selling meme coins, multi-wallet
trading, trailing stop loss, and trailing take profit — so clawhub.ai
skill search matches more user intents precisely.
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>
- Clarify `inner_count` description: add "(NOT graduated)" to distinguish from `open_count`
- Add explicit note that total created = `inner_count + open_count` (tokens array is capped at 100 and may be truncated)
- Add routing guidance for dev token queries: direct AI to use `portfolio created-tokens` when user asks about tokens a dev created
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add POST /v1/trade/multi_swap support: new MultiSwapParams interface,
multiSwap() method, and multi-swap CLI command with full options
(accounts, input/output amounts, slippage, fees, condition-orders, etc.)
- Fix track follow-wallet: switch from criticalRequest to normalRequest;
--wallet is now optional (API Key's bound user resolves the follow list)
- Update SKILL.md, cli-usage.md, Readme.md, Readme.zh.md to reflect both changes
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add order strategy list (with required --group-tag) and order strategy
create (with required --order-type) to the frontmatter argument-hint,
reflecting newly required parameters added after 2026-04-07.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Replace top-level filled_input_amount/filled_output_amount with the
report object returned when state=30 and status=successful. Document
all report fields (amounts, tokens, decimals, price, gas) and update
order polling, post-swap receipt template, and cooking status polling
to reference report.input_amount / report.output_amount.
ClosesGMGNAI/gmgn-skills#34
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add common object fields table to portfolio stats key fields section
- Update stats summary output template with optional Identity line
- Document graceful degradation when common is absent
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add dev nested object table to Response Field Reference with all 21 fields
(creator wallet, DEXScreener activity, CTO flag, funding source, etc.)
- Update nested objects description to include dev as the 5th object
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Mark --group-tag as required (LimitOrder or STMix)
- Add usage examples: STMix for condition orders, LimitOrder for limit orders
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add drawdown_rate optional field to StrategyConditionOrder interface
- Make price_scale optional (required only for fixed-price types)
- Update --condition-orders help text with trace type example
- Document all 4 condition order types in SKILL.md with field requirements,
drawdown_rate semantics, and usage examples
- Sync order strategy create params: replace --side / auto-inference with
explicit --order-type and --sub-order-type required options
- Add --group-tag to order strategy list params
- Add --order-type to order strategy cancel params
- Fix --gas-price description: gwei (not wei); CLI converts internally
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Rewrite Guided Launch Flow: required fields collected one at a time,
optional fields grouped into a single question for faster UX
- Add env lookup warning: document that a local .env in the workspace
overrides ~/.config/gmgn/.env, with a check command
- 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>
- Add "Swap with Take-Profit / Stop-Loss Orders" section to Readme.md and Readme.zh.md
with hold_amount and buy_amount mode examples (TP at +100%/+300%, SL at -65%)
- Reorder CLI Reference section: basic Swap moved before TP/SL examples
- Update SKILL.md condition-orders examples: add stop-loss at -65%, bump slippage to 0.3,
add note that hold_amount includes any added positions at trigger time
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add --condition-orders parameter with max-10-sub-orders note and best-effort strategy behavior
- Add --sell-ratio-type with detailed explanation of buy_amount vs hold_amount semantics
- Add ConditionOrder sub-table (order_type, side, price_scale, sell_ratio) with supported types
- Add two full CLI examples: hold_amount (sell 50% at 2x, remaining 50% at 4x) and buy_amount (fixed ratio each trigger)
- Add strategy_order_id to swap response fields
- Update --sell-ratio-type description in order strategy create section
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Remove --open-price option from swap order strategy create command
- Remove open_price field from OpenApiClient StrategyCreateParams type
- Update skills/gmgn-swap/SKILL.md: drop open-price row and inference table, simplify examples to use --sub-order-type directly
- Update docs/cli-usage.md: remove --open-price from command signature and parameter table
- Add /gmgn-cooking skill to Skills tables in Readme.md and Readme.zh.md
- Add limit order and cooking CLI examples to section 8 of both readmes
- Update Cline install instructions to include /gmgn-cooking
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>
Replace the 10-line placeholder with a complete field reference based
on actual API output, grouped into Identity & Holdings, Trading Summary,
Cost & P&L, Transfer History, Timing, Wallet Identity, and Last
Transaction Records sections.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Portfolio holdings to return empty results for wallets that only have closed positions (issue #21).
Changes:
- Convert --hide-closed, --hide-airdrop, --hide-abnormal to value options with explicit defaults (hide_closed=true, hide_airdrop=true, hide_abnormal=false), so defaults are enforced by the CLI and users can override with e.g. --hide-closed false
- Remove --sell-out and --show-small which are hard-coded in the service and were never forwarded to the upstream API
- Update SKILL.md to reflect new option signatures and defaults
Fixes#21
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Remove hardcoded "renowned" default from --tag in `token holders` command
- Remove hardcoded "renowned" default from --tag in `token traders` command
- Update skills/gmgn-token/SKILL.md to show --tag has no default (returns all wallets when omitted)
Fixes#14
- 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>
