Outside-Agent Integration Pack

The Public API Skills Pack

Drop-in context for any AI agent. Download once, hand it to your assistant: it handles auth, schemas, and the full research pipeline without guesswork.

Zero third-party dependencies

Live-validated 2026-05-06

Works with any agent that can run Python

Download skills pack

coinquant-public-api-skills-pack-v1.tar.gz

Overview

Built for agents with brains

AI agents are great at reasoning. They're bad at inventing API contracts. The Skills Pack gives your agent the verified schemas, response contracts, and operating rules it needs to use CoinQuant correctly the first time: no hallucinated endpoints, no synthesized IDs, no wasted credits.

The principle: deterministic API calls first, AI reasoning second. Your agent learns what's real before it starts thinking.

Production endpoint

https://api.coinquant.ai

All skill scripts target this base URL by default.

Token lifetime

30 days · RS256 JWT

Generate in Settings → Service Accounts. Copy the one-time access_token and store it in token.json.

Pack contents

What's inside

The archive unpacks to a structured directory with four top-level folders. Skills are numbered in load order: an agent should ingest them sequentially before reasoning about any API interaction.

skills/00

Operating rules

How your agent should behave on every CoinQuant call

skills/01

Auth & client setup

Token handling and session setup

skills/02

Credits & budget gate

Balance checks, usage queries, pre-flight budget enforcement

skills/03

SSE response classifier

Correctly read every server response type

skills/04

Research & backtest

The core research-to-backtest pipeline

skills/05

Community leaderboard

Templates, public backtests, leaderboard access patterns

skills/06

Capability discovery

Assets, timeframes, indicators, order types — live discovery

skills/07

Advanced robustness

Monte Carlo, walk-forward, parameter heatmaps, risk analysis

skills/08

Trader operating system

Hypothesis → strategy → backtest → optimize → decide

skills/09

User-directed strategist

Preserves asset class, indicators, thesis, and risk preferences

templates/

Prompt templates

7 ready-to-use templates: discovery, research, hypothesis, robustness, dual validation, decision

scripts/

API client + validator

Dependency-free cq_api_client.py and live validation suite

Quick start

Up and running in minutes

You don't run anything. Your agent does.

Unpack and configure

Get the packDownload and unzip. One click, one drag.

Hand it to your agent

Generate a service account token in Settings, then tell your agent where to find the pack and the token. It takes over from there.

prompt

"Use the CoinQuant Skills Pack at ~/coinquant-skills with the token in token.json. Build me a mean-reversion strategy on BTC, backtest it, and show me the results.

Prefer a manual setup?

Unpack and configure

Extract the archive and copy the example token file. Paste your one-time access_token from CoinQuant Settings → Service Accounts.

bash

tar xf coinquant-public-api-skills-pack-v1.tar.gz
cd coinquant-public-api-skills-pack
cp examples/token.example.json token.json
# edit token.json — paste your access_token value

Preflight checks

Verify Python version, syntax-check all scripts, and run the unit tests. No network connection required at this stage.

bash

python3 --version # must be 3.11+
python3 -m py_compile scripts/*.py
python3 -m unittest discover -s tests -q

Validate token and check credits

Always validate the JWT before any paid or LLM work. Confirm your credit balance before running prompts or backtests.

bash

python3 scripts/cq_api_client.py --token-file token.json‍
python3 scripts/cq_api_client.py --token-file token.json credits

Send a test prompt

Confirm the full SSE pipeline is working end-to-end with a lightweight chat prompt before committing to research or strategy workflows.

bash

python3 scripts/cq_api_client.py --token-file token.json \
prompt 'Reply in one sentence: hello CoinQuant.'

Run the live validation suite (optional)

The safe mode is read-only and free. Pass --paid or --backtest flags only when you're ready to consume credits and create artifacts.

bashread-only

python3 scripts/validate_live_pack.py --safe

Research workflow

How your agent thinks

For experienced users, the pack exposes a full research operating model that mirrors how a professional quant approaches strategy development: structured, evidence-driven, and resistant to overfit. Each phase uses the CoinQuant domain expert and public backtester as authoritative sources rather than relying on the agent’s own inferences.

Report mode first. Always run a domain-expert report before and after backtesting. Classify all SSE responses by event type: never infer response type from the content of your prompt alone.

Capability discovery

Confirms which assets, timeframes, and indicators are supported before designing anything.

Clean-slate research

Generates a market report and pulls hypotheses from real data, not assumptions.

Strategy & backtest

Materializes a real strategy and runs a tick-accurate backtest.

Robustness testing

Monte Carlo, walk-forward, parameter sweeps, fee/slippage stress.

Evidence-based decision

Recommends continue, redesign, or reject — based on actual results.

Security

Token handling

Tokens are 30-day JWTs. Generate in Settings → Service Accounts. Your agent reads them from token.json, never from chat history or shell arguments. Expired tokens stop the agent before it spends a single credit.

If a token has expired, the client will not proceed to any paid or LLM work, it will stop and instruct you to regenerate a key in the CoinQuant frontend. Never pass raw JWTs as positional arguments to shell commands.

Supported Elements

Changelog