Fetch raw ad creative, app, ranking, and revenue data from AdMapix as structured JSON.
by fly0pants4.3k installs296 stars
Memory
drt-self-improving-agent
Try itSelf-improving DRT/ICT trading agent — journals every trade (setup type, bias, R:R, outcome), analyzes its own win/loss patterns, and builds a personal trading memory that makes the agent smarter over time. 100% lokal — ingen netværkskald.
What it does
A trading agent that **learns from its own trades**. Every trade is journaled → analyzed → patterns are discovered → the agent adjusts its own rules. The more trades, the sharper it gets.
The skill document
DRT Self-Improving Trading Agent 🤖📈
A trading agent that learns from its own trades. Every trade is journaled → analyzed → patterns are discovered → the agent adjusts its own rules. The more trades, the sharper it gets.
What the skill does
- Journals every trade (DRT type, bias, entry/SL/TP, R:R, outcome, killzone)
- Analyzes patterns — which setups win, which lose, what time of day
- Builds memory —
trades.jsongrows with every trade - Learns and adjusts — prints changed rules based on data (not gut feeling)
- Proactive — reminds about killzones and A+ setups
Files
drt-self-improving-agent/
├── SKILL.md
├── scripts/
│ ├── journal.py # Add trade to trades.json (CLI)
│ ├── analyze.py # Analyze patterns + print learnings
└── data/
└── trades.json # Trade memory (auto-created)
Quick start
# Journal a trade (after every trade!)
python3 scripts/journal.py --symbol SP500 --bias LONG --type 2 \
--entry 7741 --sl 7681 --tp 7802 --rr 2.5 --result win --killzone NY
# See what the agent has learned
python3 scripts/analyze.py
Journal fields
| Field | Value | Description |
|---|---|---|
symbol | SP500, BTCUSD… | Instrument |
bias | LONG / SHORT | Direction |
type | 1, 2, 3 | DRT type (continuation/reversal/consolidation) |
entry / sl / tp | price | Trade levels |
rr | 1.5, 2.0, 3.0 | R:R at entry |
result | win / loss / be | Outcome |
killzone | London, NY, SB-AM, SB-PM | Where the trade was taken |
notes | text | Free note (e.g. "sweep 12 bars old") |
Learning logic (analyze.py)
The agent prints concrete learnings, e.g.:
- "Type 2 LONG wins 92% — keep taking them"
- "Trades in SB-PM lose 60% — avoid or tighten the filter"
- "R:R < 1.5 gives 40% WR — skip, wait for 2R+"
- "When the sweep is older than 12 bars: 0 winners — set an age gate"
Killzone reminder (proactive)
Use the agent to remind about trading windows (CET/Danish time):
- London 09:00-11:00 · NY 14:30-17:00 · SB AM 09:00-10:00 · SB PM 19:30-21:30
- ⛔ Never NY open 15:30-16:00 · max 3 trades/day · SL ALWAYS
Rules that never change (even if the data says otherwise)
- Stop loss ALWAYS · Max 3 trades/day · Never revenge trade
- Only A+ setups — a high win rate requires saying no to 80% of setups
Related skills
Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.
by Iván559 installs18 stars
Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.
by johnpatternai22 installs8 stars
Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.
by nssa.io1.0k installs47 stars
Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.
by Iván855 installs69 stars
Write, debug, and tune Playwright specs with locator strategy, trace diagnosis, and CI-aware timeouts.
by ivangdavila1.3k installs130 stars
More from Northcap Group
Browse all skillsDealing Range Theory (DRT) — complete ICT structure: Type 1 (continuation), Type 2 (reversal), Type 3 (consolidation), quadrant levels (25/50/75), entry models, SMT confirmation and news filter. For market analysis and trade setups.
by Northcap Group2 installs1 stars
Crypto DRT scalping strategy + backtest reference on 12 crypto pairs (TRX, BNB, BTC, LINK, AVAX, DOGE, SOL, NEAR, XRP, LDO, ADA, ETH), all 7 days. Backtested 2 years (~400+ trades). 100% lokal backtest-reference — ingen netværkskald, ingen API-nøgle. Backtest results are historical and not a guarantee of future performance.
by Northcap Group2 installs1 stars
How to build wealth from zero — bootstrapping, scaling strategies, resource allocation, and wealth mindset. Strategic advisory for Mohamed.
by northcap-group1 installs
Provides pay-per-call crypto trading signals with entry, stop-loss and take-profit via the x402 standard (USDC on Ethereum). Live DRT/ICT signals for agents and traders.
by Northcap Group1 installs1 stars
How the world's best entrepreneurs network, negotiate, and create partnerships. Relationships that build millions.
by northcap-group
Crypto DRT scalping — Dealing Range Theory on 12 crypto pairs (TRX, BNB, BTC, LINK, AVAX, DOGE, SOL, NEAR, XRP, LDO, ADA, ETH), all 7 days. Backtested 2 years (~400+ trades). Backtest results are historical and not a guarantee of future performance. Separate play-money account rules.
by northcap-group