performance-tracking

Record and evaluate Doctore betting performance by model version, sport, market, and price timing.

IndexedMIT

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/jambovisuaalit-performance-tracking

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Record and evaluate Doctore betting performance by model version, sport, market, and price timing. Use when the user asks for bet logging, tulosseuranta, ROI, yield, units, CLV, Brier score, log loss, calibration, drawdown, model drift, or a monthly performance review.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found
Runs as: Python package

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/performance-tracking

Tools it pre-approves 4

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

Read
Grep
Glob
Bash(python:*)

What's inside

Skill name: performance-tracking
Description: Record and evaluate Doctore betting performance by model version, sport, market, and price timing. Use when the user asks for bet logging, tulosseuranta, ROI, yield, units, CLV, Brier score, log loss, calibration, drawdown, model drift, or a monthly performance review.
License: MIT
Compatibility: Agent Skills filesystem. Python 3.11+ for CSV metric calculation.
Allowed tools: Read, Grep, Glob, Bash(python:*)
Metadata: author: doctore-sports · version: 2.0.0 · category: analytics
Instructions: 20 lines in SKILL.md · view on GitHub

Before installing

Ships executable scripts
Pre-approves some shell commands

Files (4)

SKILL.md
bet-log-schema.md · references/
metrics.md · references/
calculate_metrics.py · scripts/

SKILL.md (first lines)

# Performance tracking

Measure model quality separately from realized betting variance.

## Workflow

1. Log every approved bet at decision time with immutable model and market fields.
2. Add closing price and result after settlement without overwriting decision-time data.
3. Run `scripts/calculate_metrics.py BET_LOG.csv`.
4. Report ROI, yield, units, CLV, Brier score, log loss, calibration, and drawdown by relevant segment.
5. Flag insufficient samples and model-version mixing.

## References

- Read `references/bet-log-schema.md` when creating or validating records.
- Read `references/metrics.md` when interpreting CLV, calibration, or model quality.

Do not validate a model from win rate alone. Do not combine incompatible market domains into a single calibration claim.

From Jambovisuaalit/doctore, MIT.

Signals

Stars: 0
Forks: 0
Open issues: 3
Last commit (this folder): Jul 23, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Version: 2.0.0
License: MIT
Repository: github.com/Jambovisuaalit/doctore
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from doctore-sports

Cite this page

performance-tracking skill. Agent Mart. https://agentmart.dev/skills/jambovisuaalit-performance-tracking (last updated 2026-10-24)