QuantConnect Optimization
QuantConnect optimization API and Phase 4 parameter tuning (project)
npx skills add majiayu000/claude-skill-registry --skill quantconnect-optimization-derekcrosslu-claude-code-explore-01cce --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# QuantConnect Optimization (Phase 4) **Progressive Disclosure**: This primer loads essential information. Detailed guides in `reference/` (load on-demand). --- ## When to Use Load when running `/qc-optimize` command for parameter tuning after successful backtest (Phase 3). --- ## ⚠️ CRITICAL CONSTRAINT: Project ID Rule **YOU MUST USE project_id FROM iteration_state.json (created during /qc-backtest)** ### Why This Matters 1. **QC API requires baseline backtest** - Cannot optimize empty project 2. **Must optimize correct strategy** - Use project from Phase 3 3. **Prevents API errors** - Missing baseline causes failures 4. **Maintains audit trail** - Same project through all phases ### Correct Workflow ```python # ✅ CORRECT: Read from iteration_state.json with open('iteration_state.json', 'r') as f: state = json.load(f) project_id = state['project']['project_id'] # REQUIRED backtest_id = state['phase_results']['backtest']['backtest_id'] # Validate exists # Validate before optimization if not project_id or not backtest_id: raise ValueError("Run /qc-backtest first - no baseline found") # Now safe to optimize ``` ### Wrong Examples (DO NOT DO) ```python # ❌ WRONG: Creating new project
- When to Use
- ⚠️ CRITICAL CONSTRAINT: Project ID Rule
- Why This Matters
- Correct Workflow
- Wrong Examples (DO NOT DO)
- CLI Command
- Quick Start
- 1. Define Parameter Grid
- 2. Run Optimization
- 3. Evaluate Results (Phase 4 Decision)
- Common Issues
- 1. "No baseline backtest found"
- 2. "Grid too large" (>100 combinations)
- 3. API Authentication Errors
Using qc_optimize.py CLI (progressive disclosure pattern) qc_optimize.py run --config optimization_params.json --state iteration_state.json Check status qc_optimize.py status --optimization-id <id> Get results qc_optimize.py results --optimization-id <id> qc_optimize.py run --config optimization_params.json qc_optimize.py run --strategy euler --max-backtests 50 python SCRIPTS/qc_optimize.py --help
What does the QuantConnect Optimization skill do?
QuantConnect optimization API and Phase 4 parameter tuning (project)
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill quantconnect-optimization-derekcrosslu-claude-code-explore-01cce --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.