mlb
Validate Doctore MLB betting candidates for moneyline, run line, totals, first five innings, and related baseball markets.
Skill by doctore-sports
Chalk Labs
Need help deploying mlb?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code. Read the repository before you give any tool access to your data.
npx agentmarket install skill/jambovisuaalit-mlb
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
Reviews
Write a reviewNo 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/mlb
Tools it pre-approves 6
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
ReadGrepGlobWebSearchWebFetchBash(python:*)
What's inside
- Skill name
mlb- Description
- Validate Doctore MLB betting candidates for moneyline, run line, totals, first five innings, and related baseball markets. Use when the user asks to analyze an MLB game, MLB odds or kertoimet, starting pitchers, bullpen availability, handedness splits, lineups, park, roof, umpire, or weather before a baseball bet.
- License
- MIT
- Compatibility
- Agent Skills filesystem. Current external data may require network tools. Python 3.11+ and jsonschema are required for deterministic context validation.
- Allowed tools
- Read, Grep, Glob, WebSearch, WebFetch, Bash(python:*)
- Metadata
- author: doctore-sports · version: 2.1.0 · category: sport
- Instructions
- 35 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
- Pre-approves some shell commands
Files (5)
- SKILL.md
- mlb-context.schema.json · contracts/
- market-rules.md · references/
- required-inputs.md · references/
- validate_context.py · scripts/
SKILL.md (first lines)
# MLB context validation Validate whether the timestamped event still matches the MLB model's feature assumptions. Do not manually invent run or probability adjustments. ## Workflow 1. Read `references/required-inputs.md` and confirm the fields required by the requested market. 2. Normalize current facts into `contracts/mlb-context.schema.json`. 3. Confirm listed/action pitcher settlement rules and current starter status. 4. Confirm lineup compatibility, bullpen availability, roof, weather, umpire dependency, and event identity. 5. Read `references/market-rules.md` only for the requested market type. 6. Run: ```bash python skills/sport-specific/mlb/scripts/validate_context.py \ --context mlb-context.json \ --market-snapshot market-snapshot.json \ --evaluated-at 2026-07-23T18:05:00+03:00 \ --max-age-seconds 900 ``` 7. Return `VALID`, `WATCH`, or `BLOCKED` with exact reason codes. 8. Preserve the supplied model probability. A changed critical feature requires a refreshed model. 9. Pass the context document unchanged to `bet-decision-core`. ## Hard rules - A changed starter is `BLOCKED`. - A listed-pitcher mismatch is `BLOCKED`. - A material lineup or required environmental mismatch is `BLOCKED`. - Required but projected, stale, or unknown facts are `WATCH`. - Full-game markets may require current bullpen state; F5 markets do not inherit that requirement. - Do not load KBO/NPB rules for MLB events.
From Jambovisuaalit/doctore, MIT.
More from Jambovisuaalit/doctore
- 0.479score
data-ingestion
doctore-sports
Collect and normalize timestamped sports-betting inputs for Doctore.
SkillCFreshness: CClaude Code - 0.479score
performance-tracking
doctore-sports
Record and evaluate Doctore betting performance by model version, sport, market, and price timing.
SkillCFreshness: CClaude Code +9 - 0.479score
risk-management
doctore-sports
Size Doctore bets using fractional Kelly, uncertainty shrinkage, units, bankroll limits, exposure caps, correlation, and drawdown controls.
SkillCFreshness: CClaude Code +9 - 0.479score
bet-decision-core
doctore-sports
Produce a deterministic Doctore BET, WATCH, PASS, or BLOCKED decision from canonical model output, market snapshot, portfolio state, risk policy, and optional…
SkillCFreshness: CClaude Code +9 - 0.479score
data-quality-gate
doctore-sports
Validate Doctore betting candidates before any EV or stake calculation.
SkillCFreshness: CClaude Code +9 - 0.479score
doctore-orchestrator
doctore-sports
Route complete Doctore sports-betting workflows without loading unrelated skills.
SkillCFreshness: CClaude Code - 0.479score
edge-detection
doctore-sports
Calculate expected value, break-even probability, model edge versus a no-vig market, and minimum acceptable odds.
SkillCFreshness: CClaude Code +9 - 0.479score
market-baseline
doctore-sports
Calculate sportsbook implied probabilities, overround, no-vig fair probabilities, break-even prices, and minimum qualifying odds.
SkillCFreshness: CClaude Code +9 - 0.479score
model-probability
doctore-sports
Validate Doctore XGBoost or statistical model probabilities before betting analysis.
SkillCFreshness: CClaude Code +9 - 0.474score
tennis
doctore-sports
Validate Doctore tennis betting candidates for match winner, set, game handicap, totals, and player markets.
SkillCFreshness: CClaude Code - 0.474score
anti-bias-audit
doctore-sports
Audit a Doctore betting candidate for forced action, recency bias, favorite bias, price anchoring, result chasing, confirmation bias, public-fade narratives…
SkillCFreshness: CClaude Code +9 - 0.474score
output-format
doctore-sports
Format Doctore sports-betting decisions into standardized BET, WATCH, PASS, BLOCKED, market-scan, and compact WhatsApp outputs.
SkillCFreshness: CClaude Code +9
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
- 2.1.0
- License
- MIT
- Repository
- github.com/Jambovisuaalit/doctore
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from doctore-sports
- 0.479score
data-ingestion
doctore-sports
Collect and normalize timestamped sports-betting inputs for Doctore.
SkillCFreshness: CClaude Code - 0.479score
edge-detection
doctore-sports
Calculate expected value, break-even probability, model edge versus a no-vig market, and minimum acceptable odds.
SkillCFreshness: CClaude Code +9 - 0.479score
bet-decision-core
doctore-sports
Produce a deterministic Doctore BET, WATCH, PASS, or BLOCKED decision from canonical model output, market snapshot, portfolio state, risk policy, and optional…
SkillCFreshness: CClaude Code +9 - 0.479score
data-quality-gate
doctore-sports
Validate Doctore betting candidates before any EV or stake calculation.
SkillCFreshness: CClaude Code +9 - 0.479score
doctore-orchestrator
doctore-sports
Route complete Doctore sports-betting workflows without loading unrelated skills.
SkillCFreshness: CClaude Code - 0.479score
market-baseline
doctore-sports
Calculate sportsbook implied probabilities, overround, no-vig fair probabilities, break-even prices, and minimum qualifying odds.
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get mlb running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
mlb skill. Agent Mart. https://agentmart.dev/skills/jambovisuaalit-mlb (last updated 2026-10-24)