Pp Bookmakersreview

<!-- GENERATED FILE — DO NOT EDIT.
     This file is a verbatim mirror of library/media-and-entertainment/bookmakersreview/SKILL.md,
     regenerated post-merge by tools/generate-skills/. Hand-edits here are
     silently overwritten on the next regen. Edit the library/ source instead.
     See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->

BookmakersReview — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the bookmakersreview-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:

1. Install via the Printing Press installer. It defaults binaries to $HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:

   npx -y @mvanhorn/printing-press-library install bookmakersreview --cli-only

2. Verify: bookmakersreview-pp-cli --version
3. Ensure the reported install directory is on $PATH for the agent/runtime that will invoke this skill.

If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.5 or newer). This installs into $GOPATH/bin (default $HOME/go/bin), so add that directory to $PATH instead:

go install github.com/mvanhorn/printing-press-library/library/media-and-entertainment/bookmakersreview/cmd/bookmakersreview-pp-cli@latest

If --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds.

BookmakersReview runs a free, unauthenticated GraphQL feed behind its odds-comparison tool that already includes consensus, opening/current/historical lines, injuries, and weather in one graph. This CLI wraps it, adds a local SQLite history no paid odds API gives you by default, and layers on vig-free value finding, steam detection, and closing-line-value grading that no sportsbook data API — paid or free — ships out of the box.

When to Use This CLI

Use this CLI when you need current or historical sports-betting odds, sharp consensus, line movement, or closing-line-value analysis for U.S.-facing sportsbooks, and want it scriptable/offline instead of manually comparing books in a browser.

Anti-triggers

Do not use this CLI for:

• Do not use this CLI to place real bets — it is a read-only odds/data tool with a local bet ledger for your own tracking, not a sportsbook integration.
• Do not use this CLI for non-US/offshore-only or niche international leagues without first checking leagues list — BMR's coverage is US-sportsbook-centric.
• Do not use this CLI as a source of betting advice or guaranteed win probabilities — odds value/arb scan surface mathematical relationships in published prices, not predictions.

Unique Capabilities

These capabilities aren't available in any other tool for this API.

Line shopping

• odds value — See which sportsbook's current price beats the vig-free fair line before you bet.

  Reach for this before placing a bet to confirm you are not just getting the highest number, but a genuinely positive-EV price.

  bookmakersreview-pp-cli odds value --event 123456 --market 1 --agent

• steam scan — Scan today's whole slate for fast, coordinated line moves that signal sharp money before the market fully reacts.

  Use this when you want to catch sharp action across an entire day's games rather than watching one event.

  bookmakersreview-pp-cli steam scan --league 16 --since 3h --agent

• arb scan — Find risk-free two-sided price mismatches across sportsbooks for one event.

  Use this to find guaranteed-profit spreads across books; do not use it to judge single-side value, use odds value for that.

  bookmakersreview-pp-cli arb scan --event 123456 --market 1

Closing line value

• bets record — Log your own wager (event, market, price, book, timestamp) to a local ledger.

  Use this immediately after placing a real bet so it can later be graded against the closing line.

  bookmakersreview-pp-cli bets record --event 123456 --market 3 --price 2.5 --book 9 --boid 1

• bets grade — Compare one recorded bet's price to the market's closing line to compute its CLV.

  Use this after a game closes to see whether you beat the closing number, the standard measure of betting skill.

  bookmakersreview-pp-cli bets grade --bet-id 42 --agent

• bets report — See your running closing-line-value percentage and win rate across every recorded bet.

  Use this weekly/monthly to track betting performance over time instead of grading bets one at a time.

  bookmakersreview-pp-cli bets report --since 30d --group-by market --agent

• odds movement — See the full open-to-current price timeline for one event and market, across books.

  Use this to see how a specific line moved over time; use steam scan instead to find movement across the whole day's slate.

  bookmakersreview-pp-cli odds movement --event 123456 --market 2 --agent

Command Reference

graphql — Raw GraphQL passthrough for the BookmakersReview odds-v2 service (fallback for any of the 174 query fields not promoted as a typed command)

• bookmakersreview-pp-cli graphql — Execute a raw GraphQL query against the odds-v2 service

Finding the right command

When you know what you want to do but not which command does it, ask the CLI directly:

bookmakersreview-pp-cli which "<capability in your own words>"

which resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code 0 means at least one match; exit code 2 means no confident match — fall back to --help or use a narrower query.

Recipes

Find the best price across books

bookmakersreview-pp-cli odds best --event 123456 --market 3 --json

Returns every tracked sportsbook's current spread price for the event, sorted best-first.

Narrow a large event-history payload to just the fields you need

bookmakersreview-pp-cli events history --league 16 --from 2025-12-14 --to 2025-12-16 --agent --select eid,dt

A date-range history query returns every event's full per-period score breakdown; --select keeps agent context small by returning only the id and kickoff time when you just need to enumerate events (follow up with 'events get <eid>' for full scores on the ones you care about).

Check if a price is actually good value, not just the highest number

bookmakersreview-pp-cli odds value --event 123456 --market 1 --agent

Strips the vig from consensus to compute fair value, then flags any book beating it — the highest number isn't always +EV.

Scan for sharp/steam action across today's slate

bookmakersreview-pp-cli steam scan --league 16 --since 3h --agent

Flags markets where consensus moved fast and far from the opener across the board, a signal of sharp money.

Track your own closing line value over time

bookmakersreview-pp-cli bets report --since 30d --group-by market --agent

Aggregates every bet you've recorded and graded into a running CLV percentage, the standard long-run skill metric for bettors.

Auth Setup

No authentication is required. Every query in this CLI works unauthenticated, exactly like the public odds.bookmakersreview.com tool.

Run bookmakersreview-pp-cli doctor to verify setup.

Agent Mode

Add --agent to any command. Expands to: --json --compact --no-input --no-color --yes.

• Pipeable — JSON on stdout, errors on stderr

• Filterable — --select keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:

  bookmakersreview-pp-cli graphql --query 'query { leagues(limit: 5) { lid nam } }' --agent --select id,name,status

• Previewable — --dry-run shows the request without sending

• Non-interactive — never prompts, every input is a flag

• Read-only — do not use this CLI for create, update, delete, publish, comment, upvote, invite, order, send, or other mutating requests

Paths and state

Agents should treat the CLI's path resolver as part of the runtime contract:

• Use --home <dir> for one invocation, or set BOOKMAKERSREVIEW_HOME=<dir> to relocate all four path kinds under one root.

• Use per-kind env vars only when a specific kind must diverge: BOOKMAKERSREVIEW_CONFIG_DIR, BOOKMAKERSREVIEW_DATA_DIR, BOOKMAKERSREVIEW_STATE_DIR, BOOKMAKERSREVIEW_CACHE_DIR.

• Resolution order is per-kind env var, --home, BOOKMAKERSREVIEW_HOME, XDG (XDG_CONFIG_HOME, XDG_DATA_HOME, XDG_STATE_HOME, XDG_CACHE_HOME), then platform defaults.

• config contains settings like config.json and profiles. data contains data.db (the local bet ledger and any SQLite cache). state contains persisted queries, jobs, and teach.log. cache contains regenerable HTTP/cache files.

• No authentication is required for this CLI — BookmakersReview's odds API is fully unauthenticated, so there are no credentials, cookies, or auth sidecars to store anywhere.

• Run bookmakersreview-pp-cli doctor --fail-on warn to surface path warnings. agent-context exposes a schema v4 paths block for agents that need the resolved dirs.

• For MCP, pass relocation through the MCP host config. The MCP binary does not inherit CLI flags:

  {
    "mcpServers": {
      "bookmakersreview": {
        "command": "bookmakersreview-pp-mcp",
        "env": {
          "BOOKMAKERSREVIEW_HOME": "/srv/bookmakersreview"
        }
      }
    }
  }

Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use BOOKMAKERSREVIEW_HOME or per-kind vars as durable fleet levers, and use --home only for a single invocation. Relocation is not reversible by unsetting env vars; move files manually before clearing BOOKMAKERSREVIEW_HOME, or doctor will not find the local bet ledger left under the former root.

Automatic learning

This CLI ships a self-capturing learning loop. The CLI does its own bookkeeping: every invocation is journaled locally, a failed flag followed by a corrected retry auto-derives a flag_alias candidate, and a teach on a query family without a playbook auto-synthesizes a playbook_candidate from the session's journal. Your job is judgment only: recall first, act on surfaced candidates, teach the final answer, playbook amend when you observe a correction. You never record failures by hand.

Step 1: recall before any discovery

Before list/search/drill commands on a new user question, run:

bookmakersreview-pp-cli recall "<user's question>" --agent

The response envelope:

{
  "query": "...",
  "normalized": "<normalized form>",
  "query_entities": ["..."],
  "found": true | false,
  "match_score": 0.0,
  "results": [
    { "resource_id": "...", "resource_type": "...", "venue": "...",
      "confidence": 2, "entity_match": "exact|partial|unknown",
      "source": "taught|preseed|pattern", "warnings": ["..."] }
  ],
  "mismatches": [ /* only when --debug-mismatches */ ],
  "warnings": [ /* top-level */ ],
  "candidates": [
    { "id": 12, "class": "flag_alias | playbook_candidate",
      "summary": "...", "sightings": 3, "last_seen": "...",
      "rationale": "...",
      "next_action": ["<trial command>", "bookmakersreview-pp-cli learnings confirm 12"] }
  ],
  "playbook": {
    "query_family": "...",
    "playbook": {
      "steps": [ { "cmd": "<command with {slot} substitution>", "purpose": "..." } ],
      "entity_slots": ["$ENTITY"],
      "expected_tool_calls": 3
    },
    "slots_resolved": { "$ENTITY": { "token": "<live token>", "canonical": "<canonical>" } },
    "notes": "<workarounds + gotchas for this query family>"
  },
  "notes": "<duplicate surface for non-playbook callers>"
}

Empty-store short-circuit: if the store has no learnings, playbooks, or candidates yet (recall finds nothing and learnings list and learnings candidates are both empty), skip recall for the rest of this session instead of taxing every query; resume recall-first once something has been taught.

Step 2: decision tree

Read candidates, playbook, notes, results[0], and warnings in that order:

if Candidates present (warnings include "candidates_present"):
    -> candidates are try-then-confirm, never facts. Follow each candidate's
       two-step next_action verbatim: run the trial command first, then run
       `learnings confirm <id>` only after the trial verified the behavior.
       Reject a wrong candidate with `learnings reject <id>`.
    -> NEVER re-teach something recall surfaced as a candidate; confirm or
       reject that candidate instead of teaching a duplicate.
    -> candidates ride alongside playbooks and resource hits, not instead of
       them; continue with the branches below after acting on them.

if Playbook present:
    -> READ Playbook.notes verbatim FIRST (workarounds + gotchas the CLI surface doesn't expose)
    -> replay Playbook.steps in order, substituting Playbook.slots_resolved entries
       for the entity slot tokens. If a step's slot is unresolved, fall back to
       discovery for that step only.
    -> the Playbook's expected_tool_calls is a budget; if you find yourself running
       materially more, record the divergence via `bookmakersreview-pp-cli playbook amend`
       at end-of-session.

elif Notes present (no Playbook):
    -> read Notes verbatim before any discovery step; they carry known gotchas
       for this query family even when no structured choreography exists yet.

elif Found AND Results[0].EntityMatch == "exact" AND Results[0].Confidence >= 2:
    -> skip discovery; fetch live data for Results[*].ResourceID in parallel

elif Found AND Results[0].EntityMatch == "partial":
    -> candidate hint, NOT a hit; read the resource title to validate before trusting

elif (any row in Mismatches[] when --debug-mismatches was passed):
    -> treat as cold start; the stored learning is for a different entity
       (different canonical resolved from query_entities)

else:  // Found == false, no playbook, no notes
    -> cold start; run discovery normally; teach the answer afterward (Step 4).
       If the family has no playbook yet, that teach auto-synthesizes a
       playbook candidate from this session's journal - you do not need to
       record one by hand.

Playbook and Notes are orthogonal to the per-resource path. A recall response can carry both a Playbook AND a Results[] hit - use both: the Playbook tells you which choreography to run; the resource hits short-circuit specific steps. Default to skipping mismatches; pass --debug-mismatches only when investigating cold-start surprises.

Candidate judgment details: learnings confirm <id> prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. learnings reject <id> tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; bookmakersreview-pp-cli learnings candidates lists the full open set.

Graceful degradation: if learnings confirm is an unknown command, you are driving an older binary - ignore the candidates guidance and follow the rest of the protocol.

Step 3: always read warnings

• low_confidence: row exists at confidence<2. Treat as a hint, not a skip-discovery hit.
• resource_not_in_store: the local store doesn't have the resource the learning points at. The match validator couldn't classify entities — direct-fetch and re-evaluate.
• cross_alias_match (per-result): the row was taught under a different alias and matched the live query's canonical via entity_lookups (e.g., a "USA" teach satisfying a "United States" recall). Trust the resource_id.
• similar_shape_different_entity:<canonical> (top-level): a structurally matching row exists but its canonical entity differs from the live query's. Treated as cold start; the warning carries the conflicting canonical as a hint, but the row is NOT promoted into Results.
• ambiguous_alias (top-level): a single query entity resolved to multiple canonicals (e.g., "Cards" → Arizona Cardinals + St. Louis Cardinals). Surface the ambiguity from context before committing to a resource.
• candidates_present (top-level): the envelope carries a candidates section. Handle it via the candidates branch in Step 2 before anything else.
• Top-level no_learnings_for_query_family: the table had no rows above the Jaccard floor. Pure cold start.