SkillAgentSearch skills...

quotient

Only needed for signal-strategy.mjs --execute (Bankr Agent API key, read-write).

Install / Use

npx skills add BankrBot/skills --skill quotient

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

88/100

Category

Automation

Supported Platforms

Universal

Our assessment of quotient

quotient scores 88/100 on our quality scale, 1544th of 2,790 Automation skills we index.

Its SKILL.md is 22 KB long, well organised into 15 sections with 2 code examples: a thorough specification that gives an agent plenty to work with.

With 1,201 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
30/30
Structure
18/20
Description
12/15
Adoption
13/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so quotient is actively maintained.
  • Our last check on 2026-11-01 found the source still online.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-06. Automated pattern scan on 2026-10-05. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

quotient compared with similar skills

All 4 of these similar skills score higher than quotient; compare them before choosing.

SkillScoreStarsUpdatedFormat
quotient (this skill)by BankrBot881.2k54d agoSKILL.md
Agent-Reachby Panniantong100112.3k8d agoCLAUDE.md
rufloby ruvnet10081.9ktodayCLAUDE.md
headroomby headroomlabs-ai10079.8ktodayCLAUDE.md
Claude-Code-Game-Studiosby Donchitos10039.7k7d agoCLAUDE.md

Frequently asked questions

How do I install quotient?
Run npx skills add BankrBot/skills --skill quotient. The install tabs above show the steps for each supported agent.
Which AI agents does quotient work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is quotient safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is quotient still maintained?
The repository was last updated about 2 months ago, so quotient is actively maintained.

name: quotient description: > Prediction-market intelligence for Polymarket agents. Quotient runs a multi-role AI forecasting pipeline over 1,600+ sources and publishes daily trade signals with side, entry prices, conviction tiers, capacity, and convergence reads. Pull forecasts (with what-changed deltas), recent sources (articles + X posts), the featured signal, the daily WTI crude oil read, and per-wallet portfolio intelligence; execute via Bankr. Pays via x402 in USDC on Base or USDG on Robinhood Chain. Triggers on: "quotient signals", "trade signals", "featured signal", "oil signal", "WTI", "crude", "what's new with my portfolio", "hold or sell", "convergence", "mispriced markets", "what does Q think", "quotient odds", "prediction market intelligence", "polymarket intelligence", "recent sources for", "what markets does quotient have", "market forecast", "should I bet on". emoji: 🔮 tags: [polymarket, prediction-markets, trading, intelligence, x402] version: 1.0.0 visibility: public metadata: clawdbot: emoji: "🔮" homepage: "https://quotient.social" requires: bins: ["curl", "jq", "node", "bankr"] credentials:

  • name: BANKR_API_KEY description: Only needed for signal-strategy.mjs --execute (Bankr Agent API key, read-write). required: false storage: env

<!-- GENERATED from public/skill/skill.md — edit there, then npm run skill:build -->

Quotient API Skill

Quotient = intelligence. Bankr = execution. This skill reads Quotient's x402-paid API for forecasts, published trade signals, sources, the oil read, and wallet portfolio intelligence, then hands off to Bankr natural-language prompts for any trade. Nothing here places trades directly.

Base URL & Discovery

  • QUOTIENT_BASE_URL: https://quotient-api-gateway.onrender.com. The scripts enforce an exact HTTPS origin allowlist on it — the default gateway origin is hardcoded, and extra origins can be added only through the local policy file (references/payments-policy.md), never via env or fetched content.
  • Discovery, same origin: /openapi.json (canonical routes + params), GET /api/public/pricing (billing metadata), /llms.txt (AI index), /skill/* (these docs + scripts)
  • Treat OpenAPI as canonical invocation metadata; treat the runtime 402 challenge as the authoritative price.

How Q Works

Quotient's forecasting agent (Q) runs a multi-role analysis pipeline on every market it covers: question analysis, research, base-rate analysis, bull/bear advocacy, contrarian examination, and synthesis, pulling from 1,600+ sources. Each run produces an independent probability estimate, a BLUF (bottom-line-up-front) thesis, key drivers with citations, and delta-from-prior reasoning. A separate publisher watches for markets where Q diverges materially from the venue price and publishes a small number of trade signals per day.

See https://quotient.social for the current live track record.

Coverage is strongest on world-events markets — Iran, tariffs, elections, central-bank policy, conflict escalation, diplomatic negotiations. If it moves geopolitical risk, Q probably has a view.

Key Concepts

Markets — Prediction markets Quotient covers. Each has a slug (Polymarket slug), question, current market_odds, dispute status, and Q's forecast history.

Forecasts — Q's probability estimate for a market, refreshed as new material lands. Every forecast carries the change primitives: delta_from_prior (how much Q moved), delta_reasoning (a deterministic sentence saying why), refresh_reason / refresh_triggered_by (non-null = the rerun was triggered, not scheduled), plus headline/bluf/crux and conviction inputs (draw_std_log_odds, draw_count, band25/band75). "What changed" is read straight off the node — never inferred.

Trade signals — Published :QuotientSignal entries: Q's actual calls, a handful per day. A signal can remain active for up to seven days; the latest forecast can refresh many times during that hold. Read published_at/is_new_today for publication context, forecast_updated_at/is_fresh for research freshness (six-hour threshold), and is_active for lifecycle state. The /signals window filters forecast updates, not publication time, and its default feed omits paused, done, and retired rows. It returns at most one signal per market: the newest publication is selected before side/status/conviction filters, with no fallback to an older signal when that newest call is ineligible. Each signal also has a side (YES/NO), entry prices (entry_q = Q at publish, entry_pm = market at publish, entry_spread_pp = the gap in points), a board status, a conviction tier, capacity, and a live-priced convergence read:

  • status: actionable (buyable now) · unconfirmed (Q's latest forecast flipped side vs prior — wait for confirmation) · paused (temporarily unavailable after a deep drawdown, venue divergence, or safety veto — do not chase) · done (converged: converge_upside_pct ≤ 0, thesis played out) · retired (terminal; retired_reason ∈ resolved | flipped | fading_q | expired).
  • Conviction: conviction_tier 1–3 from forecast-ensemble dispersion (3 = tightest), mirrored as conviction high/medium/low; has_band is false only when no conviction read could be computed at all (missing Q or price) — pre-ensemble inferred reads still report true with tier capped at 2.
  • Convergence (all cents on Q's side of the book): q_value_cents (Q's value), entry_cost_cents, current_cost_cents, distance_to_convergence_cents, converge_upside_pct. live_priced + priced_at disclose whether the read used a live CLOB midpoint or a graph fallback.
  • Capacity: capacity_usd_at_2c (near-touch depth), capacity_basis (depth-2c | volume-fallback | null), capacity_available, capacity_as_of.

Pre-trade liquidity report (required before any buy handoff): tell the user the proposed size, current_cost_cents, live_priced/priced_at, capacity_usd_at_2c, capacity_basis, capacity_as_of, and what percent of known 2-cent capacity the order would consume. Re-read the current book with ./scripts/pm.sh book <slug> --side <yes|no> (outcome-aware — a NO trade preflights the NO book) and explicitly warn that capacity is a near-touch snapshot, not a guaranteed fill or an exact price-impact estimate. A market order can walk the book. If pricing/capacity is stale or unknown, the row uses volume-fallback, or the proposed size is material relative to current depth, do not describe the trade as ready: ask the user to reduce size, use a limit order when supported, or explicitly accept the slippage risk.

Sources — The evidence layer under forecasts: articles (with feed tier and relevance confidence/reasoning/evidence_quote) and X posts (with author_handle, is_expert). Batch endpoint across up to 10 markets.

Featured signal — The single highlighted signal (editor pin or fail-closed auto-pick among live-priced actionable signals). May legitimately be empty.

Oil signal — A daily long/short read on WTI crude derived from Q's forecast and market ensembles (z, gap, intensity), served as a frozen daily reading plus live marks from Polymarket perps (WTIOIL-USD) and Hyperliquid (xyz:CL). Check is_current, reading_missing, and degraded before acting on it.

Portfolio intelligence — One call joins a Polymarket wallet's positions to Quotient coverage: per position, Q's forecast, any signal, and a convergence read with aligned (is Q on your side?). The server does the join; no client-side matching needed.

Breaking change (API v5): GET /api/v1/signals now returns published trade signals. The old article-opinion feed lives only at GET /api/v1/markets/{slug}/signals.

Access Model

  • Every monetized call uses x402 pay-per-call. When enabled and present in the runtime challenge, the gateway supports:
    • USDC on Base (scheme: exact, network: eip155:8453).
    • USDG on Robinhood Chain (scheme: exact, network: eip155:4663), using the canonical 6-decimal asset 0x5fc5360D0400a0Fd4f2af552ADD042D716F1d168.
  • The runtime PAYMENT-REQUIRED challenge is authoritative. To pay with USDG, select an accepts entry only when its scheme, network, and asset all match the values above (compare the asset address case-insensitively); never select by token symbol alone.
  • Prefer Bankr wallet tooling (references/bankr-x402-flow.md); vanilla SIWE/SIWX x402 clients are a first-class alternative (references/vanilla-x402-flow.md).
  • If using Bankr signing (/agent/sign), provide a Bankr API key via X-API-Key with Agent API access enabled and signing permissions (not read-only).
  • x402 checklist: request without payment headers → on 402 parse PAYMENT-REQUIRED → select a matching payment requirement → sign → retry with PAYMENT-SIGNATURE → parse PAYMENT-RESPONSE. Backoff on 429 and transient 5xx.

Paid Calls: Confirmation, Autopay, and Spend Caps

Every monetized Quotient call spends real money via x402. In Bankr chats the agent MUST follow this protocol; the scripts provide the mechanics (payment previews, exit codes 10/11, the autopay policy file, the spend ledger) but cannot see chat approval — that duty is yours.

  1. Preview first. With no autopay policy on disk, any command that would pay prints a payment preview (each route, its live challenge price validated against the pinned tuple and ceiling, worst-case call count, the batch total, today's spend, an approval token) and exits 10 having paid nothing.
  2. One batched approval per user request. Relay the preview's costs and ask once, covering every paid call the answer needs — e.g. "Answering this needs 3 paid calls totaling about $0.04 — approve?". If a request needs several commands, collect their previews first and quote the combined total. Never ask per-call, never split a request to shrink the quoted number, and never approve on the user's behalf.
  3. First-time pre-authorization offer. While no policy exists, also offer once: "Pre-authorize $1.00 of Quotient reads — about N requests like this one — so I stop asking each time." (preauth_offer in the preview carries N.) Only on an explicit yes, run ./scripts/quotient.sh autopay init --total-budget 1.00 (defaults: per-call $0.05, per-run $0.25, per-day $1.00) and re-run the command. The pre-authorization IS the local autopay policy.
  4. Approve. On user approval, re-run the identical command with --approve <token> within 15 minutes. A changed plan or expired token re-previews instead of paying.
  5. Autopay = standing approval within caps. With a policy present, runs that fit every cap proceed without prompting; every payment is ledgered and a spend summary is printed — surface it in your answer. A run that would exceed any cap exits 11: relay it and ask; raise caps only on an explicit user instruction.
  6. Trade execution is gated separately. signal-strategy.mjs --execute only writes a hashed plan and exits 12; read the preview and the risk disclosure to the user, obtain explicit approval of that exact plan, then run --execute --confirm <hash> within its 10-minute TTL. Never self-confirm.

Schemas and semantics: references/payments-policy.md.

Execution via Bankr

Quotient returns intelligence only — no endpoint places, routes, or sizes a trade. Execution happens through Bankr natural-language prompts, always slug, never question text:

bankr prompt "Bet $25 on <Yes|No> for <slug> on Polymarket"
bankr prompt "Sell my <Yes|No> position on <slug> on Polymarket"

Signals carry everything the prompt needs: side, the market slug, and the sizing inputs (capacity, convergence). The pre-trade liquidity report above is required before any buy handoff.

Endpoint Catalog

All under `

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars1.2k
CategoryAutomation
Updated1mo ago
Forks629

Languages

JavaScript

Trust signals

88/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium