Qveris logo

Qveris

OrganizationPopular
HKUDS
qveris

Paid capability marketplace for global multi-asset data; use it when free Vibe-Trading sources lack coverage, depth, or provider quality, and keep free sources as the default for routine OHLCV.

Overview

PublisherHKUDS
RepositoryVibe-Trading
Skill nameqveris
Stars
35.2K
Forks
5.7K
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by HKUDS on GitHub. Read the source before you install it.

Installation

Install the Qveris AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/qveris
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git /tmp/Vibe-Trading
mkdir -p .claude/skills
cp -r /tmp/Vibe-Trading/agent/src/skills/qveris .claude/skills/qveris
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Qveris in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Qveris on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Qveris is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

QVeris

QVeris is a paid capability marketplace for global market, fundamental, macro, derivatives, crypto, China/HK, news, filings, and alternative-data calls. Use it when the built-in free sources cannot cover the requested dataset, when the user explicitly asks for QVeris, or when a premium provider is needed for depth such as options Greeks, analyst/calendar feeds, broad provider comparison, or paid China/HK/global coverage. For ordinary OHLCV, keep source: "auto" on the free loader chain unless the user explicitly selects source: "qveris".

Signup link: QVeris via Vibe-Trading. Invite code fallback: Vyjjo5G_1cAHJA.

Workflow

1. Discover with qveris_search

Call qveris_search first. Search is free and returns candidate capabilities with tool_id, provider, parameters, examples, expected_cost, billing rule, categories, and stats such as success_rate and average execution time.

Good queries are concrete:

  • US listed options chain implied volatility Greeks AAPL
  • Hong Kong market daily OHLCV financial statements
  • FRED CPI Treasury yield curve macro series
  • China A share northbound fund flow daily

2. Inspect with qveris_inspect

Call qveris_inspect on one or more tool_id values before any paid call. Inspect is free and returns the fuller parameter schema and sample parameters. Use it to verify required parameters, enum values, date formats, and output shape before execution.

3. Call with qveris_execute

Call qveris_execute only after the user has enabled QVeris and the tool has been inspected. Pass the inspected tool_id, the exact parameters, and a reasonable max_response_size. Use session_id and search_id when available so usage can be reconciled later.

Choosing a Capability

Prefer the candidate with the best combination of:

  1. High stats.success_rate.
  2. Low expected_cost for equivalent data.
  3. Provider fit for the task: official or specialist sources before generic mirrors when the figure matters.
  4. Parameter clarity: required fields and examples should match the user's requested asset, date range, and granularity.

Do not assume tools with similar names are interchangeable. The measured catalog has very large quality variance inside the same category; design notes recorded FMP tools ranging from near-zero to 100% success and some tradefeeds tools at 0%. Surface success_rate and expected_cost in the answer whenever the user is choosing among paid options.

Billing and Modes

  • The default free route is Vibe-Trading's built-in public data stack; QVeris tools are unavailable in mode="free".
  • Discover (qveris_search) and inspect (qveris_inspect) are free only after the user explicitly enables the paid QVeris route.
  • Execute (qveris_execute) is paid only when the provider call is billable.
  • Failed calls, empty results, and parameter errors are not charged by the QVeris contract; observed missing-parameter calls returned success=false, cost=0.0, status=not_charged, and unchanged balance.
  • mode="free" means the original free public-data path stays active and QVeris is hidden from agent/tool/backtest routing.
  • mode="paid" permits QVeris discovery, inspect, and execute calls, bounded by budget_credits_per_session. Only a flat per-call quote (24.2 credits, 1 credits/call) can be reserved against that budget. A quote priced per result, row or value is refused as quote_not_bounded, because its leading number is not the bill: 1 credits/result charged 9.66 credits for one stock-year.
  • source: "qveris" in a backtest or get_market_data serves crypto, forex, futures and macro bars only. Stocks, ETFs and other markets with splits and dividends are refused: the loader picks a capability by search rank, which ignores price adjustment, so it could not say how the bars were adjusted.
  • Never hide cost: every successful execute result should preserve cost and remaining_credits for the user.

Configuration can come from QVERIS_API_KEY / QVERIS_BASE_URL, or from Settings -> QVeris / vibe-trading data mode paid. If QVeris is disabled, in free mode, or no API key is configured, the tools should be treated as unavailable.

Truncation

qveris_execute accepts max_response_size (20480 default, -1 means do not ask QVeris to truncate). When a response is too large, QVeris returns a result object containing a message, truncated_content, and full_content_file_url. If the full JSON is required, fetch that signed URL and use the full payload. If a summary is enough, cite that the response was truncated and work only from truncated_content.

Balance and Usage

Check balance and recent usage through:

  • Web: Settings -> QVeris.
  • CLI: vibe-trading data status or vibe-trading data usage.
  • Agent/API tools: status is derived from free search/ledger/usage endpoints.

For reconciliation, prefer execution_id, tool_id, charge_outcome, cost, and remaining_credits over text summaries.

References

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Qveris AI skill do?

Paid capability marketplace for global multi-asset data; use it when free Vibe-Trading sources lack coverage, depth, or provider quality, and keep free sources as the default for routine OHLCV.

Why use Qveris on TypingMind?

Because you install it once and use it with any model. Qveris is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Qveris in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/qveris. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Qveris?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Qveris?

As many as you like. As long as a model supports skills, you can use Qveris with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Qveris AI skill free?

Yes. It is published on GitHub by HKUDS under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇