Opportunity Radar

Q: Why use Opportunity Radar on TypingMind?

Because you install it once and use it with any model. Opportunity Radar is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

Q: How do I install Opportunity Radar in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Nunchi-trade/agent-cli/tree/main/skills/radar. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Q: Which AI models can use Opportunity Radar?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

Q: How many AI models can I use with Opportunity Radar?

As many as you like. As long as a model supports skills, you can use Opportunity Radar with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Q: Is the Opportunity Radar AI skill free?

Yes. It is published on GitHub by Nunchi-trade under the MIT license. You only pay your own AI provider for the tokens you use.

Q: What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

Q: How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Organization

Nunchi-trade

opportunity-radar

Screens all Hyperliquid perps and surfaces top trading setups

Overview

Publisher	Nunchi-trade
Repository	`agent-cli`
Skill name	`opportunity-radar`
Stars	521
Forks	136
Bundled files	1
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by Nunchi-trade on GitHub. Read the source before you install it.

Installation

Install the Opportunity Radar AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/Nunchi-trade/agent-cli/tree/main/skills/radar
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/Nunchi-trade/agent-cli.git /tmp/agent-cli
mkdir -p .claude/skills
cp -r /tmp/agent-cli/skills/radar .claude/skills/opportunity-radar

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Opportunity Radar in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Opportunity Radar on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Opportunity Radar is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Opportunity Radar

Screens all Hyperliquid perpetual markets through a 4-stage funnel to surface the highest-conviction trading setups.

Architecture


Stage 0: BTC Macro Context (EMA 5/13 on 4h, 1h momentum)
Stage 1: Bulk Screen (~500 assets → ~70 by volume)
Stage 2: Top-N Selection (by composite liquidity score)
Stage 3: Deep Dive (multi-TF technicals + 3-pillar scoring)
Stage 4: Momentum + Final Ranking

3-Pillar Scoring (0-400 scale)

Pillar	Weight	Signals
Market Structure	35%	Volume tiers, surge, OI, OI/Vol health
Technicals	40%	4h trend, hourly trend, RSI, patterns, volume
Funding	25%	Neutral (+40), favorable, unfavorable penalties

Hard Disqualifiers

Counter-trend on hourly structure
Extreme RSI (>80 for LONG, <20 for SHORT)
Strong 4h counter-trend (strength > 50)
Volume dying on both timeframes
Heavy unfavorable funding (>50% annualized)
BTC macro headwind (modifier < -30)

Usage

CLI

bash
hl radar once              # Single scan
hl radar run --tick 900    # Continuous (15 min intervals)
hl radar once --json       # JSON output
hl radar once --mock       # With mock data (no HL connection)
hl radar status            # Show last scan results
hl radar presets            # List presets

Standalone

python
from skills.radar.scripts.standalone_runner import RadarRunner
from cli.hl_adapter import DirectHLProxy

runner = RadarRunner(hl=hl, tick_interval=900)
runner.run()

Configuration

Via YAML config or CLI flags:

--min-volume: Minimum 24h volume to qualify (default: $500K)
--top-n: Assets to deep dive (default: 20)
--preset: "default" or "aggressive"
--score-threshold: Minimum final score (default: 150)

Agent Mandate

You are the opportunity radar. Your job is to screen the entire Hyperliquid perps universe and rank assets by trading conviction. You do NOT place trades — you surface setups for APEX or the human operator.

RULES:

ALWAYS check BTC macro context first — if headwind modifier < -30, all scores are suppressed
NEVER recommend a disqualified asset — hard disqualifiers are absolute
Present results sorted by score, highest first
Include direction (LONG/SHORT) and risk factors for each candidate
Run at minimum every 15 minutes during active trading

Decision Rules

Score Range	Interpretation	Action
250-400	Elite setup — rare, strong multi-pillar confluence	Immediate entry candidate for APEX
170-250	Good setup — solid edge	Standard entry if Pulse confirms
140-170	Marginal — needs confirmation	Queue only, wait for Pulse signal
100-140	Weak — one pillar carrying	Skip — insufficient edge
0-100	No edge	Ignore completely

BTC Macro	Effect	Action
Strong uptrend (mod > +20)	Tailwind for longs	Score longs normally, penalize shorts
Neutral (mod -10 to +10)	No macro effect	Score normally
Downtrend (mod < -20)	Headwind	Raise entry threshold to 200+
Crash (mod < -40)	Major headwind	Skip all entries, wait for stabilization

Anti-Patterns

Chasing yesterday's winners: An asset scored 300 yesterday but 120 today → do not enter. Scores are point-in-time.
Ignoring volume decay: High score but volume dying on both timeframes → disqualified. The setup is stale.
Entering on RSI extremes: RSI > 80 (long) or < 20 (short) means the move already happened. Radar correctly disqualifies these.
Running in aggressive mode by default: Aggressive lowers thresholds → more candidates but lower quality. Use default unless you have excess budget.

Error Recovery

Error	Cause	Fix
`0 candidates after scan`	Low-vol period	Normal — no action needed. Don't force trades.
`Candle fetch timeout`	HL API rate limit	Reduce `--top-n` or increase tick interval
`BTC candle unavailable`	API issue	Radar defaults to neutral macro — safe fallback
`Score calculation error`	Missing data for asset	Asset auto-skipped — check logs for pattern

Composition

Radar is a sub-component of APEX (runs every 15 ticks). Can also be used standalone for manual trade selection. Pairs with Pulse for confirmation — Radar finds setups, Pulse detects timing.

Cron Template

bash
# Standalone radar every 15 min during trading hours
*/15 8-20 * * 1-5 cd ~/agent-cli && hl radar once --json >> data/radar/scans.jsonl 2>&1

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

scripts/standalone_runner.py7 KB

Frequently asked questions

What does the Opportunity Radar AI skill do?

Screens all Hyperliquid perps and surfaces top trading setups

Why use Opportunity Radar on TypingMind?

Because you install it once and use it with any model. Opportunity Radar is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Opportunity Radar in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Nunchi-trade/agent-cli/tree/main/skills/radar. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Opportunity Radar?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Opportunity Radar?

As many as you like. As long as a model supports skills, you can use Opportunity Radar with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Opportunity Radar AI skill free?

Yes. It is published on GitHub by Nunchi-trade under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Constraint Driven Development

addyosmani

CommunityPopular

Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no…

Spec Driven Development

addyosmani

CommunityPopular

Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when drafting a PRD or requirements document with objectives and…

Ramp

Fetch and follow Ramp's published agent playbooks inside Paperclip, with mandatory approval gates for spend, incorporation, cards, account setup, and other financial actions.

Agent Agentic Payments

ruvnet

CommunityPopular

Agent skill for agentic-payments - invoke with $agent-agentic-payments

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Opportunity Radar

Architecture

3-Pillar Scoring (0-400 scale)

Hard Disqualifiers

Usage

CLI

Standalone

Configuration

Agent Mandate

Decision Rules

Anti-Patterns

Error Recovery

Composition

Cron Template

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now