shipp
Shipp is a real-time data connector. Use it to fetch authoritative, changing external data (e.g., sports schedules, live events) via the Shipp API.
- License 许可
- MIT
- 最近更新
- 2026-06-07
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- shipp
- metadata
- { "author": "Outsharp Inc.", "version": "0.1.4" }
- description
- Shipp is a real-time data connector. Use it to fetch authoritative, changing external data (e.g., sports schedules, live events) via the Shipp API.
- allowed-tools
- [ "Bash(curl:https://docs.shipp.ai/*)", "Bash(curl:https://api.shipp.ai/*)", "Bash(curl:https://platform.shipp.ai/*)", "Bash(jq:*)" ]
- compatibility
- { "notes": [ "All endpoints require authorization via API key.", "Requests and responses are JSON." ], "requirements": [ "Internet access", "Shipp API Key (Get from https://platform.shipp.ai)" ] }
03 SKILL.md 正文
Shipp API
Shipp.ai is the definitive source on real-time data.
Reference docs.
Implement as many tests as possible as soon as possible. Verify data and how the app uses data. Be flexible in schema — event rows are schema-flexible JSON and fields vary by sport, feed, and event.
Base prefix:
- All routes are under:
https://api.shipp.ai/api/v1
Documentation & References
All detailed examples, request/response schemas, and walkthroughs live in the official docs. Always consult these before building:
| Resource | URL |
|---|---|
| Full documentation | https://docs.shipp.ai |
| How-to guides | https://docs.shipp.ai/how-to/ |
| Setup instructions | https://docs.shipp.ai/instructions/setup/ |
| API reference | https://docs.shipp.ai/api-reference/ |
| Dashboard / Signup | https://platform.shipp.ai/signup |
| Billing management | https://platform.shipp.ai/billing |
Authentication
All endpoints require an API key. The API supports several ways to provide it:
| Method | Example |
|---|---|
Query parameter api_key |
?api_key=YOUR_API_KEY |
Query parameter apikey |
?apikey=YOUR_API_KEY |
Authorization header (Bearer) |
Authorization: Bearer YOUR_API_KEY |
Authorization header (Basic) |
Authorization: Basic base64(:YOUR_API_KEY) |
X-API-Key header |
X-API-Key: YOUR_API_KEY |
User-API-Key header |
User-API-Key: YOUR_API_KEY |
API-Key header |
API-Key: YOUR_API_KEY |
Pick whichever method works best for your client.
Endpoints Overview
Below is a summary of the available endpoints. For full request/response examples, schemas, and field descriptions see the API reference.
POST /api/v1/connections/create
Create a new raw-data connection by providing natural-language filter_instructions that describe what games, teams, sports, or events you want to track.
Returns a connection_id (ULID) you'll reuse for all subsequent runs.
POST /api/v1/connections/{connectionId}
Run a connection and receive raw event data.
Supports optional body fields for time-based filtering (since), cursor-based pagination (since_event_id), and result limiting (limit).
GET /api/v1/connections
List all connections in the current org scope.
GET /api/v1/sports/{sport}/schedule
Retrieve upcoming and recent games for a given sport (past 24 hours through next 7 days).
Supported sport values: nba, nfl, mlb, ncaafb, soccer (case-insensitive).
Data Shape
Event rows returned in data[] are schema-flexible JSON objects. Fields vary by sport, feed, and event. Common field categories include:
- IDs:
game_id,home_id,away_id,attribution_id,posession_id - Text / enums:
sport,home_name,away_name,game_clock,desc,type,category - Numeric:
home_points,away_points,game_period,down,yards_first_down,location_yard_line - Time:
wall_clock_start,wall_clock_end
Not every row has every field. Agents and clients should be defensive and handle missing keys.
For the complete field reference see docs.shipp.ai.
Error Format
Errors are returned as JSON with an error message, HTTP status code, and a hint:
| Status | Meaning |
|---|---|
| 400 | Invalid request — check JSON and required fields |
| 401 | Missing or invalid API key |
| 402 | Billing changes required — manage at https://platform.shipp.ai/billing |
| 403 | API key lacks access to this resource |
| 404 | Connection not found or doesn't belong to your org |
| 429 | Rate-limited — retry with backoff |
| 5xx | Server error — retry later or contact support@shipp.ai |
Response Compression
Include an Accept-Encoding header to receive compressed responses (zstd, gzip, or deflate). Compression is applied automatically when the response body exceeds 1 KB.
Usage Tips
- Keep
filter_instructionsshort, explicit, and testable. Mention the sport/league and scope. - Store and reuse
connection_id— don't create a new connection per run. Creating connections has time and credit overhead. - Use
since_event_idfor efficient polling (cursor-based pagination). Send the lexicographically largest event ID you've received. - Use the schedule endpoint to discover
game_ids and team names before creating connections. - Surface error
hintmessages directly to users when limits are hit. - Treat every field in
data[]as optional — use existence checks and graceful fallbacks. - Log unknown data shapes in development so you can refine
filter_instructions. - Polling interval: 5–30 seconds depending on domain and cost sensitivity.
- Deduplicate events by keeping a rolling set of seen event IDs.
- Consult the how-to guides for end-to-end integration walkthroughs.
Integration Pattern: "Real-Time Contract"
When building a feature powered by Shipp, define a contract for each screen or agent loop:
- User promise — what must stay accurate while the user (or agent) is watching?
- Triggering events — what changes should cause UI updates or agent actions?
- Data shape needed — what fields do you need to render or decide?
- Freshness window — how old can the last update be before you warn the user?
- Failure mode — what do you show/do if updates stop arriving?
Then translate the contract into filter_instructions when creating the connection.
Example Project: Alph Bot
Alph Bot is an open-source automated trading bot that uses Shipp for real-time sports data and trades on prediction markets. It demonstrates a production-quality integration of the Shipp API.
How Alph Bot Uses Shipp
-
Game discovery — Uses
GET /api/v1/sports/{sport}/scheduleto list available games: -
Connection creation — Creates a Shipp connection for a specific game, describing what events to track via
filter_instructions. -
Live polling — Runs the connection on an interval, using
since_event_idfor cursor-based pagination to receive only new events since the last poll. -
AI analysis — Feeds the schema-flexible
data[]events directly to Claude AI, which analyzes game state and estimates outcome probabilities. -
Trading decisions — Compares AI-estimated probabilities against Kalshi market prices to find value bets.
Key Takeaways from Alph Bot
- Reuse connections — Alph Bot creates a connection once and polls it repeatedly, avoiding unnecessary creation overhead.
- Cursor pagination — Uses
since_event_idso each poll only returns new events, keeping responses fast and costs low. - Defensive data handling — Treats all fields as optional since the data shape varies by sport, game phase, and event type.
- Schedule-first workflow — Discovers game IDs via the schedule endpoint before creating targeted connections.
See the Alph Bot README for full setup instructions.
Versioning
This API is versioned under /api/v1/. New versions will be introduced under a new prefix when breaking changes are required.
04 同仓库更多 Skills
crowd-prompting
A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.
ceaser
Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).
ceaser-send
Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.
dilemm-ai
Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).
moldium
Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.
arxiv-paper-reviews
Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.