metaculus
Metaculus is a forecasting platform where users predict outcomes of real-world events. Use this skill to interact with the Metaculus API for browsing questions, submitting forecasts, reading community predictions, managing comments, and downloading forecast data.
What this skill does
# Metaculus API [Metaculus](https://www.metaculus.com) is a forecasting platform where users predict outcomes of real-world events. Questions range across science, technology, politics, economics, and more. The platform aggregates individual forecasts into community predictions and scores forecasters on accuracy. Check this skill and the [official API documentation](https://www.metaculus.com/api/) _FREQUENTLY_ for updates. > **Feedback:** Contact the Metaculus team at [[email protected]](mailto:[email protected]) with questions, ideas, or feedback. > **Source code & issues:** [github.com/Metaculus/metaculus](https://github.com/Metaculus/metaculus/issues) --- ## Key Concepts (Glossary) | Term | Definition | |---|---| | **Post** | The primary feed entity. A post wraps a question, group of questions, conditional pair, or notebook. Posts have statuses, authors, projects, and comments. | | **Question** | A single forecastable item within a post. Types: `binary`, `multiple_choice`, `numeric`, `discrete`, `date`. | | **Group of Questions** | A post containing multiple related sub-questions displayed together (e.g., "What will GDP be in 2025, 2026, 2027?"). | | **Conditional** | A post with paired questions: "If [condition], what is P(child)?" — produces question_yes and question_no variants. | | **Forecast** | A user's prediction on a question. Format depends on question type: probability (binary), CDF (continuous), or distribution (multiple choice). | | **Community Prediction (CP)** | The aggregated forecast from all users, computed via various aggregation methods. | | **Aggregation Method** | How individual forecasts are combined: `recency_weighted` (default), `unweighted`, `metaculus_prediction`, `single_aggregation`. | | **Project** | A container for posts — can be a tournament, category, tag, question series, or site section. | | **Tournament** | A special project type with prize pools, start/close dates, and leaderboards. | | **Category** | A topic classification (e.g., "Nuclear Technology & Risks", "Health & Pandemics"). | | **Resolution** | The actual outcome of a question once known. Values vary by type: `yes`/`no` (binary), a number, a date, or an option name. | | **Curation Status** | Editorial status of a post: `draft`, `pending`, `rejected`, `approved`. | | **Scaling** | Defines how a continuous question's range maps to the CDF. Includes `range_min`, `range_max`, `zero_point` (for log scale), and bounds. | | **CDF** | Cumulative Distribution Function — the format for continuous forecasts. A list of 201 floats (or `inbound_outcome_count + 1` for discrete). | | **Inbound Outcome Count** | Number of possible outcomes within a question's range (excluding out-of-bounds). Default is 200 for continuous; smaller for discrete. | --- ## Base URL All endpoints are served from: ``` https://www.metaculus.com ``` All paths below are relative to this base (e.g., `GET /api/posts/` means `GET https://www.metaculus.com/api/posts/`). --- ## Authentication **All API requests require authentication.** Unauthenticated requests are rejected. ### Getting Your Token 1. Log in to [Metaculus](https://www.metaculus.com). 2. Go to your [Account Settings → API Access](https://www.metaculus.com/accounts/settings/account/#api-access). 3. Copy (or generate) your API token. ### Using the Token Add the `Authorization` header to every request. The token must be prefixed with the literal string `Token` followed by a space: ``` Authorization: Token 9944b09199c62bcf9418ad846dd0e4bbdfc6ee4b ``` ### Example: curl ```bash curl -s "https://www.metaculus.com/api/posts/?limit=5&order_by=-published_at" \ -H "Authorization: Token $METACULUS_API_TOKEN" | jq . ``` ### Example: Python ```python import os, requests TOKEN = os.environ["METACULUS_API_TOKEN"] HEADERS = {"Authorization": f"Token {TOKEN}"} BASE = "https://www.metaculus.com" resp = requests.get(f"{BASE}/api/posts/", headers=HEADERS, params={"limit": 5}) resp.raise_for_status() data = resp.json() ``` ### Environment Variables Never hardcode tokens. Store them as environment variables or in a `.env` file: ``` METACULUS_API_TOKEN=your-token-here ``` --- ## Rate Limits Metaculus throttles requests to prevent abuse. If you receive a `429 Too Many Requests` response, implement exponential backoff before retrying. --- ## REST API Endpoints Overview ### Feed (Posts) | Method | Endpoint | Description | Auth | |---|---|---|---| | `GET` | `/api/posts/` | Retrieve paginated posts feed with filters | Required | | `GET` | `/api/posts/{postId}/` | Retrieve a single post with full details | Required | ### Questions & Forecasts | Method | Endpoint | Description | Auth | |---|---|---|---| | `POST` | `/api/questions/forecast/` | Submit forecasts for one or more questions | Required | | `POST` | `/api/questions/withdraw/` | Withdraw active forecasts | Required | ### Comments | Method | Endpoint | Description | Auth | |---|---|---|---| | `GET` | `/api/comments/` | Retrieve comments (filter by post or author) | Required | | `POST` | `/api/comments/create/` | Create a new comment on a post | Required | ### Utilities & Data | Method | Endpoint | Description | Auth | |---|---|---|---| | `GET` | `/api/posts/{postId}/download-data/` | Download question data as a ZIP of CSVs | Required | | `GET` | `/api/projects/{projectId}/download-data/` | Download full project data as a ZIP of CSVs | Required (admin/whitelisted) | --- ## Data Model ### Post → Question Hierarchy A **Post** is the top-level entity in the feed. Each post contains exactly one of: - `question` — a single question (binary, numeric, date, multiple choice, or discrete) - `group_of_questions` — multiple related sub-questions - `conditional` — a conditional pair (condition + child, producing question_yes and question_no) - A notebook (no question content) The other fields will be `null`. For example, a post with a single binary question will have `question` populated and `conditional`/`group_of_questions` set to `null`. ### Post | Field | Type | Description | |---|---|---| | `id` | integer | Unique post ID | | `title` | string | Full title | | `short_title` | string | URL-friendly short title | | `slug` | string | URL slug | | `author_id` | integer | Author's user ID | | `author_username` | string | Author's username | | `projects` | object | Associated projects (see below) | | `created_at` | datetime | When the post was created | | `published_at` | datetime? | When the post was published | | `open_time` | datetime? | When the question opened for forecasting | | `edited_at` | datetime | Last edit timestamp | | `curation_status` | string | `draft`, `pending`, `rejected`, or `approved` | | `comment_count` | integer | Number of comments | | `status` | string | `open`, `upcoming`, `closed`, `resolved`, `draft`, `pending`, `rejected` | | `nr_forecasters` | integer | Number of unique forecasters | | `question` | Question? | Single question (if applicable) | | `conditional` | Conditional? | Conditional pair (if applicable) | | `group_of_questions` | GroupOfQuestions? | Question group (if applicable) | | `user_permission` | string | `forecaster` or `viewer` | | `vote` | object | `{ score: int, user_vote: string? }` | | `forecasts_count` | integer | Total number of forecasts | ### Post Projects Object | Field | Type | Description | |---|---|---| | `site_main` | Project[] | Site-level project associations | | `tournament` | Project[] | Tournaments this post belongs to | | `category` | Category[] | Categories | | `tag` | Tag[] | Tags | | `question_series` | Project[] | Question series | | `default_project` | Project | The post's primary/default project | ### Project | Field | Type | Description | |---|---|---| | `id` | integer | Project ID | | `type` | string | `site_main`, `tournament`, etc. | | `name` | string | Display name | | `slug` | string? | URL slug | | `prize_pool` | string | Prize pool amount (e.g., "0.00") | | `start_date` |
Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.