Trader Diagnosis
Testing & Qualitytrader-diagnosisTrader Diagnosis is an Agent Skill for testing & quality published in the HammerGPT/Hyper-Alpha-Arena repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
This skill should be used when the user reports that their AI Trader is not triggering, not executing trades, or behaving unexpectedly. Trigger phrases include "why isn't my trader working", "strategy not executing", "no trades happening", "trader not triggering", "why no signals".
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/HammerGPT/Hyper-Alpha-Arena/blob/HEAD/backend/skills/trader-diagnosis/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/trader-diagnosis, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Trader Diagnosis
Systematically diagnose why an AI Trader is not triggering or executing trades as expected. Follow a structured checklist approach.
Pre-requisites (MUST confirm before proceeding)
- Identify WHICH trader has the issue (if user doesn't specify,
list_tradersand ask) - Confirm the exchange and environment the trader is on
Workflow
Phase 0: Environment and Data Foundation Check
Before diagnosing the trader itself, verify the system foundation:
-
Check trading environment:
get_trading_environment()- Confirm it matches what user expects (testnet vs mainnet)
- If mismatch, guide user to switch via UI top-right mode switcher
-
Check watchlist:
get_watchlist()- Verify the symbol(s) the trader's signal pools monitor are in the watchlist
- If using default config (only BTC), warn user that other symbols have no data
- If target symbol missing, use
update_watchlist()to add it (after user confirmation)
→ [CHECKPOINT] Report environment and watchlist status. If issues found here, they are ROOT CAUSES — fix them first before proceeding.
Phase 1: Full Diagnostic Scan
Run comprehensive diagnosis: diagnose_trader_issues(trader_id)
This checks:
- Trader enabled status
- Wallet binding and balance
- Strategy binding (prompt or program)
- Signal pool configuration and recent triggers
- Cooldown timer status
- Recent error logs
→ [CHECKPOINT] Present diagnostic results in plain language. Categorize issues found.
Phase 2: Issue Resolution
Based on diagnostic results, address each issue:
Configuration Issues (you can fix):
- Signal pool not bound → help bind one (confirm exchange match)
- Trigger interval too long → suggest adjustment
- Signal thresholds too strict → delegate to Signal AI for recalibration
Manual Operations (guide user to UI):
- Wallet not bound → AI Trader → click trader → bind wallet (Hyperliquid: API Wallet key + master address; Binance: API key + secret)
- Trading not started → AI Trader → click trader → "Start Trading"
- Program binding not active → Programs → "Program Bindings" → Edit → activation switch
Data Issues (investigate further):
- API errors → check
get_system_logsfor details - Balance insufficient → advise deposit to the master wallet address (for Hyperliquid API Wallet)
- Exchange connectivity → verify API key / API Wallet status
→ [CHECKPOINT] Summarize fixes applied and remaining manual steps. Wait for user to complete manual actions.
Phase 3: Verification
After user completes manual steps:
- Re-run
diagnose_trader_issues(trader_id)to verify all clear - Check
list_traders(trader_id)for current status - Confirm the trader is now ready to execute
Key Rules
- Always run the full diagnostic first, don't guess
- Signal pool exchange must match trader's wallet exchange
- Be specific about UI paths for manual operations
- If the issue is "signal triggered but AI decided HOLD", explain this is normal behavior