ospex-one
Bet on sports with one word (or maybe, a few words). Say a team name, city, or abbreviation. 'Edmonton', 'Duke', 'Celtics', 'Lakers'. NBA, NHL, NCAAB.
What this skill does
# ospex-one
One word in, one transaction hash out. This skill emphasizes execution over discussion and is low-risk by design.
**Invocation:** This skill is **invocation-only**: the agent will not use it unless you explicitly ask or reference a team name in context. That avoids accidental bets.
**Trust & safety:** This skill executes real transactions on Polygon mainnet using your configured wallet. Positions are capped at 3 USDC. Unmatched position amounts can be withdrawn at any time. The agent verifies all transaction parameters against hardcoded contract addresses and expected method names before signing — if anything is unexpected, it halts and reports rather than proceeding. OSPEX_WALLET_PRIVATE_KEY is high-sensitivity: the agent must never log, echo, or expose it. Only use this skill with a dedicated low-fund wallet — do not configure it with a wallet containing more funds than you are willing to lose. Full risk assessment: https://github.com/ospex-org/ospex-contracts-v2/blob/main/docs/RISKS.md
**Input expectations:** This skill is designed for single-word input — a team name, city, or abbreviation. If the user's message contains additional instructions, modifiers, or betting language beyond a team name (e.g., "lay the points", "take the under", "bet $5", "Celtics -6.5"), act on it if the intent is unambiguous — otherwise, ask the user to clarify before proceeding.
## Defaults
| Parameter | Default |
|-----------|---------|
| Market | moneyline (override with spread/total via input like "Lakers -6.5" or "over 220.5") |
| Amount | 3 USDC (maximum per transaction) |
| Side | the named team |
| Odds multiplier | 1.05 |
| Odds | market odds × odds multiplier |
## Communication Rules
Do not send progress updates during Steps 1–3. Execute the entire flow silently and only message the user when one of these occurs:
- **Ambiguity:** The team name matches multiple games and you need clarification.
- **Counter-offer:** Michelle offered worse odds and you need the user's approval before proceeding.
- **Final result:** Step 4 — the position is created and matched (or the match fallback message).
- **Hard failure:** An API error, on-chain revert, or any condition that stops the flow.
If any API call returns an unexpected error, stop and report it. Do not silently retry or work around failures.
## Step 1: Resolve Team and Market Type
When you receive input, your **first action** is always to call the API — do not ask the user anything first.
**Detect market type from input:**
- If the input includes a point value (e.g., "Atlanta -6.5", "Boise +1.5", "Celtics -3") → market type is **spread**, line is the number with its sign
- If the input includes "over" or "under" with a number (e.g., "Lakers over 220.5") → market type is **total**, line is the number
- Otherwise → market type is **moneyline** (default)
**For spread and total markets:** This skill uses the current market line from odds-history. If the user specifies a line that differs from the current market (e.g., user says "+1.5" but market is at -3.5), inform the user of the current line and ask if they want to proceed at that line instead. Do not attempt to create a position at a non-market line.
1. Call `GET /markets`.
2. Search all responses for the input text in `homeTeam` and `awayTeam` fields. Note: All API responses use a `{ data: ..., formatted: "..." }` envelope. The `formatted` field is a display convenience — never use it for branching decisions. Always use the `data` object. When searching for teams, look inside the `data` array, not the top-level response.
3. If found in exactly one game → that is the team and game. Note `contestId`, `matchTime`, and whether the team is home or away. Check the `speculations` array for an existing `speculationId` matching the detected market type. If one exists, note the `speculationId`. For spread speculations, note `awayLine` (away team's perspective, e.g. -3.5) and `homeLine` (home team's perspective, e.g. 3.5) — use whichever matches the user's team. For total speculations, note the `line` field. These are the actual on-chain lines for the bet. If no `speculationId` exists for the detected market type, respond: "No {marketType} market available for {team} right now." and stop.
4. If the team is not found in any game → respond: "No active market found for {input}"
Only ask the user for clarification if the team is genuinely ambiguous across multiple games.
## Step 2: Get a Quote from the agent market maker (Michelle)
First, determine the odds to request. Call `GET /analytics/odds-history/{contestId}` to get current market odds. Select the odds for the detected market type:
- **Moneyline:** Use `current.moneyline.awayOdds` or `current.moneyline.homeOdds` depending on which team the user picked.
- **Spread:** Use `current.spread.awayOdds` or `current.spread.homeOdds`.
- **Total:** Use `current.total.overOdds` or `current.total.underOdds`.
Apply the odds multiplier from the Defaults section and floor to 2 decimal places: `Math.floor(marketOdds * oddsMultiplier * 100) / 100`. This is your minimum acceptable odds.
Note: Higher decimal odds = higher payout for the bettor. A quote at 2.00 is better than 1.85.
If the odds-history endpoint returns no data for the relevant market type, use 1.91 as a reasonable default for spread/total (standard -110 line). For moneyline, ask the user — don't guess, since moneyline odds vary widely depending on the matchup.
**Line reporting:** For spread markets, use `awayLine` or `homeLine` from the speculation (noted in Step 1) depending on the user's team — not the line from odds-history. For total markets, use `line` from the speculation. Odds-history is for odds values only — ignore its `line` field for spread/total direction. The speculation's line fields are the actual on-chain lines the user is betting on. Use these in all user-facing messages including the Step 4 result.
**Line validation:** The quote API requires lines in .5 increments (e.g., -10.5, +3.5, 195.5). If the line from odds-history is a whole number or does not end in .5, stop and tell the user: "Spread/total line unavailable for this market right now." Do not attempt to convert it.
Request a quote from Michelle using the speculationId from Step 1:
```
POST /instant-match/{speculationId}/quote?stream=false
{
"side": "home", "away", "over", or "under" (see side mapping below),
"amountUSDC": {amount parameter, from Defaults section},
"odds": {calculated odds},
"oddsFormat": "decimal",
"wallet": "{OSPEX_WALLET_ADDRESS}"
}
```
This returns: `quoteId`, `approved`, `approvedOddsDecimal`, `approvedOddsAmerican`, `expiresAt`. If Michelle counters, the response also includes a `counterOffer` object. The quote expires at `expiresAt`. Steps 3-4 must complete before this time.
**Save the `txParams` object from the response — you will need it in Step 3.** This contains all pre-computed on-chain transaction parameters. Do not compute these values yourself.
- If `approved` is false → tell the user "Michelle (market maker agent) declined — {reason}" and stop.
- If `approvedOddsDecimal` is **greater than or equal to** your requested odds → Michelle is offering the same or better. Keep moving, no confirmation needed.
- If `approvedOddsDecimal` is **less than** your requested odds → Michelle is offering worse odds. **Stop and confirm with the user** before proceeding. Show them the counter-offer, let the user know that they must respond before the counter expires, and ask if they want to accept. If the user accepts, call:
```
POST /instant-match/{quoteId}/accept-counter
Body: { "wallet": "{OSPEX_WALLET_ADDRESS}" }
```
This returns an updated `txParams` object. **Use the txParams from this response** (it reflects the accepted counter-offer terms).
**For `side`:** For moneyline and spread: if the user's team is the `homeTeam` → `"home"`. If `awayTeamRelated in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.