GMGN kline pattern reader for token charts
Classify a token's candles into a named price-action pattern (uptrend channel, breakdown, bounce, distribution, consolidation) and score it 0-100 from six explicit measurements
- What
- Classify a token's candles into a named price-action pattern (uptrend channel, breakdown, bounce, distribution, consolidation) and score it 0-100 from six explicit measurements
- Cost
- Free
- Needs
- Node.js (for npm install -g gmgn-cli) and a GMGN API key (a free key tier exists; 1s candles need a Pro key); analysis is read-only — never share your key in chat
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @gmgnai's price-action pattern reader (from GMGN's own skill repo): fetch a token's candles with `gmgn-cli market kline` and classify them into a named pattern — vertical run-up, uptrend channel, breakdown, bounce off the lows, distribution at highs, slow bleed, basing, wide chop, bullish/bearish/sideways consolidation — scored 0-100 from six measurements the agent computes and shows its work for (trend, slope, volatility, drawdown, volume ratio, distance from the low), with address-shape validation before any command and read-only access only. By @gmgnai, listed here with credit to its creator. Honest caveats: requires `gmgn-cli` (npm) and a GMGN API key (a free key tier exists; second-level candles are Pro-only); answers in Chinese if you write Chinese, English otherwise. A pattern describes what already happened — it does not predict price and is not investment advice. MIT-licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: Node.js (for npm install -g gmgn-cli) and a GMGN API key (a free key tier exists; 1s candles need a Pro key); analysis is read-only — never share your key in chat Install "GMGN kline pattern reader for token charts" for me. It teaches the agent @gmgnai's kline analysis: given a chain, token address and resolution, fetch candles via gmgn-cli, validate the address shape first, compute six explicit measurements (trend, slope, volatility, drawdown, volume ratio, distance from low), classify the chart into a named pattern, and score it 0-100 with per-item evidence — while stating plainly that a pattern describes the past, not the future, and is not investment advice. MIT-licensed. Repository: https://github.com/gmgnai/gmgn-skills/blob/main/skills/gmgn-kline-pattern/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "gmgn-kline-pattern". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. install gmgn-cli globally and configure your API key via gmgn-cli config). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.