poorrican/analyzing-backtests
configs/claude-code/skills/analyzing-backtests/SKILL.md
Analyzes algorithmic trading backtest results from Jupyter notebooks and generates summary reports. Use when the user wants to analyze or summarize backtest notebooks.
development
Updated Apr 16, 2026
$ install --global
skillsauthnpx skillsauth add poorrican/dotfiles analyzing-backtestsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 16, 2026, 5:19 AM7.5s1 file scanned
SKILL.md
- name:
- analyzing-backtests
- description:
- Analyzes algorithmic trading backtest results from Jupyter notebooks and generates summary reports. Use when the user wants to analyze or summarize backtest notebooks.
- allowed-tools:
- Read, Bash, Glob, Grep
Backtest Analysis Skill
Analyze a Jupyter notebook containing algorithmic trading backtest results and generate a comprehensive summary report.
Analysis Steps
-
Version Control Information
- Run
git statusto check current state - Run
git log -1 --format="%H %ci"for latest commit hash and date - Note any uncommitted changes
- Run
-
Read the Notebook
- Use Read tool to load the specified .ipynb file
- Parse cells for code, markdown, and outputs
-
Extract Key Information
Model/Strategy Details:
- Strategy name, type, and configuration
- Key hyperparameters
- Training and testing period information
Date Coverage:
- Backtest period (start, end, duration)
Performance Metrics:
- Monetary results: returns, capital, drawdowns, trade statistics
- Statistical analysis: risk metrics, benchmark comparisons, distributions
- Extract whatever metrics are available in the notebook
-
Generate Report
Output a structured markdown report:
# Backtest Analysis Report
**Notebook:** [filename]
**Generated:** [date]
**Git Commit:** [hash] ([date])
**Uncommitted Changes:** [yes/no]
## Strategy
[Name and brief description]
**Configuration:**
- [Key parameters]
## Period
- **Dates:** [start] to [end] ([duration])
## Performance
| Metric | Value | Benchmark |
|--------|-------|-----------|
| Total Return | X% | X% |
| Annualized Return | X% | X% |
| Max Drawdown | X% | X% |
| Sharpe Ratio | X.XX | X.XX |
| Win Rate | X% | - |
| Total Trades | X | - |
## Risk Metrics
| Metric | Value |
|--------|-------|
| Volatility | X% |
| Alpha | X% |
| Beta | X.XX |
## Key Findings
- [Notable observations]
- [Strengths and weaknesses]
## Concerns/Recommendations
- [Any issues or suggestions]
Instructions
- Extract all available metrics from the notebook
- Mark unavailable metrics as "N/A"
- Provide brief analysis, not just data
- Flag unusual results or potential issues
- Keep report concise but comprehensive
Related Skills
poorrican/stacked-issues
development
VerifiedTrustedCommunity
Implement multiple GitHub issues sequentially as stacked branches in separate worktrees, with an implementer sub-agent and an independent reviewer sub-agent per issue. Use when the user gives you two or more dependent issues and asks for them to be implemented in order, or says "stacked branches", "sequential issues", "issue chain", "do these in worktrees", or describes a parent epic with child issues that build on each other. Also reach for this whenever the user wants implementation and verification done by separate agents.
SKILL.mdUpdated May 10, 2026
poorrican/research-proposal-structure
testing
VerifiedTrustedCommunity
Use when an agent needs to produce, update, validate, or normalize a standardized research proposal artifact without running an interview. Defines the canonical structure, confidence-tag semantics, decision logic, and completion checks for proposal.md-style research plans.
SKILL.mdUpdated May 5, 2026
poorrican/research-proposal-interview
development
VerifiedTrustedCommunity
Conducts a structured Socratic interview to produce a comprehensive markdown research proposal that handles cascading uncertainty (fixed end-question, branching experiments). Use this skill whenever the user wants to write a research proposal, research plan, study design, experiment plan, thesis proposal, RFC, or "spec out" a research direction — even if they don't explicitly say "interview me." Trigger when the user says things like "help me plan this research", "I want to design experiments for X", "draft a proposal for...", "think through a research direction", or shares a half-formed research idea and asks for help structuring it. The skill interviews the user, challenges their priors with evidence requests and falsifiers, optionally uses sub-agents to explore prior art, and builds the proposal markdown incrementally so context stays clean and the document is always grounded.
SKILL.mdUpdated May 5, 2026
poorrican/experiment-log-structure
testing
VerifiedTrustedCommunity
Use when an agent needs to produce, update, validate, or normalize a standardized experiment-log entry without running an interview. Defines the canonical structure, pre-registration rules, evidence/interpretation split, calibration tags, and append-only revision model for durable experiment records.
SKILL.mdUpdated May 5, 2026