trading-desk
Skill1 starsChanged 8 days agoMITView on GitHub
Start here for the Ultimate Claude Trading Skill. Explains the whole desk (backtest, forward test, paper, live with guardrails, self-learning, phone dashboard), checks the setup and routes to the right skill. Use when the user says "set up the trading desk", "how does this work", "what's the status of my strategies", "trading bot", or "where do I start".
1 other project uses a version of this.
Adopted by
Most recently taken up by
- tusharagg1/aifolimizertheir own version, first seen Jun 11, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- tusharagg1/aifolimizer★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- llms.txtllms.txt
- trading-backtestSkill
- trading-go-liveSkill
- trading-learnSkill
- trading-paper-deskSkill
- trading-risk-rulesSkill
- trading-rotationSkill
- trading-strategy-labSkill
- trading-venuesSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Check Python 3.10+: python --version.
- Very specific: line 14
Run python research/corrected_tournament.py then python research/summarize_corrected.py, and explain reports/corrected/summary.md to the …
- Very specific: line 30
Place a live order yourself, or set TRADEDESK_LIVE=1 for the user.
- Distinctive: line 32
Call a backtest a promise.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Trading desk
A trading desk that runs on the user's own PC. The source of truth is docs/BLUEPRINT.md; progress is in docs/ROADMAP.md. Read both before changing anything.
First run
- Check Python 3.10+:
python --version. The engine uses the standard library only. - From the repo root, run the offline tests:
python -m unittest discover -s tests. All must pass. - Download history (public Coinbase data, no key):
python -m tradedesk data --gran 3600 --days 2870. - Run
python research/corrected_tournament.pythenpython research/summarize_corrected.py, and explainreports/corrected/summary.mdto the user in plain words. (The olderpython -m tradedesk tournamentuses the legacy closed-trade engine.) - Show the ladder:
python -m tradedesk status.
Route
| The user wants | Skill |
| to test or compare strategies | trading-backtest |
| to add their own strategy or TradingView indicator | trading-strategy-lab |
| paper trading, or the phone app connection | trading-paper-desk |
| the bot to learn from its trades | trading-learn |
| to change limits, or the kill switch | trading-risk-rules |
| real money | trading-go-live |
| which exchange, or leverage limits | trading-venues |
Never
- Print, log or ask for API keys in chat. Keys live in environment variables only.
- Place a live order yourself, or set
TRADEDESK_LIVE=1for the user. - Lower a promotion gate so a strategy passes. Report the failure honestly.
- Call a backtest a promise. Say "not financial advice" whenever you discuss results.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

