← Back to Skills Marketplace
diagnostikon

Kalshi Econ Nowcast Trader

by diagnostikon · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ⚠ suspicious
85
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install kalshi-econ-nowcast-trader
Description
Trades CPI bin markets on Kalshi using the Cleveland Fed CPI Nowcast to compute fair bin probabilities via a normal distribution model. Requires SIMMER_API_K...
README (SKILL.md)

\r \r

Kalshi Economic Nowcast Trader\r

\r

This is a template. \r The default signal uses the Cleveland Fed CPI Nowcast point estimate and standard deviation to price CPI bins -- remix it with real-time nowcast scraping, multiple nowcast sources, or Bayesian updating as data arrives. \r The skill handles all the plumbing (market discovery, trade execution, safeguards). Your agent provides the alpha.\r \r

Strategy Overview\r

\r Kalshi lists CPI bin markets ("Will CPI be between 0.2% and 0.3%?"). This skill prices each bin using the Cleveland Fed's CPI Nowcast as the mean of a normal distribution, then trades when the market price diverges from the model probability.\r \r Key advantages:\r

  • Cleveland Fed Nowcast is free and public -- updated regularly with high accuracy\r
  • Normal distribution is well-calibrated for CPI -- historically fits actual outcomes\r
  • Multiple bins per release -- diversified signal across the distribution\r \r

Signal Logic\r

\r

Nowcast-to-Bin Model\r

\r

  1. Load Cleveland Fed CPI Nowcast estimate and standard deviation\r
  2. Compute P(CPI in [low, high]) = Phi(z_high) - Phi(z_low) for each bin\r
  3. Compare model probability to Kalshi market price\r
  4. Trade when |model - market| >= entry_edge\r \r

Example (with defaults: estimate=0.3%, stddev=0.15%)\r

\r | Bin | Model P | Market P | Edge | Action |\r |-----|---------|----------|------|--------|\r | 0.1%-0.2% | 9.2% | 15% | -5.8% | Hold |\r | 0.2%-0.3% | 34.1% | 20% | +14.1% | BUY YES |\r | 0.4%-0.5% | 9.2% | 22% | -12.8% | BUY NO |\r \r

Remix Ideas\r

\r

  • Live nowcast scraper: Auto-refresh from Cleveland Fed website\r
  • Multi-source ensemble: Average Cleveland Fed, NY Fed, and Atlanta Fed nowcasts\r
  • Bayesian updates: Incorporate PPI, import prices, and other leading indicators\r
  • Volatility scaling: Widen stddev near data release dates\r \r

Risk Parameters\r

\r | Parameter | Default | Notes |\r |-----------|---------|-------|\r | Entry edge | 10% | Min model-vs-market divergence to trade |\r | Exit threshold | 45% | Sell when position price reaches this |\r | Max position size | $5.00 USDC | Per market |\r | Max trades per run | 3 | Rate limiting |\r | Max slippage | 15% | Skip if slippage exceeds |\r | Min liquidity | $0 | Disabled by default |\r \r

Installation & Setup\r

\r

clawhub install kalshi-econ-nowcast-trader\r
```\r
\r
Requires: `SIMMER_API_KEY` and `SOLANA_PRIVATE_KEY` environment variables.\r
\r
## Cron Schedule\r
\r
Cron is set to `null` -- the skill does not run on a schedule until you configure it in the Simmer UI.\r
\r
## Safety & Execution Mode\r
\r
**The skill defaults to dry-run mode. Real trades only execute when `--live` is passed explicitly.**\r
\r
| Scenario | Mode | Financial risk |\r
|----------|------|----------------|\r
| `python trader.py` | Dry run | None |\r
| Cron / automaton | Dry run | None |\r
| `python trader.py --live` | Live (Kalshi via DFlow) | Real USDC |\r
\r
The automaton cron is set to `null` -- it does not run on a schedule until you configure it in the Simmer UI. `autostart: false` means it won't start automatically on install.\r
\r
## Required Credentials\r
\r
| Variable | Required | Notes |\r
|----------|----------|-------|\r
| `SIMMER_API_KEY` | Yes | Trading authority. Treat as a high-value credential. |\r
| `SOLANA_PRIVATE_KEY` | Yes | Base58-encoded Solana private key for live trading. |\r
\r
## Tunables (Risk Parameters)\r
\r
All risk parameters are declared in `clawhub.json` as `tunables` and adjustable from the Simmer UI without code changes.\r
\r
| Variable | Default | Purpose |\r
|----------|---------|---------|\r
| `SIMMER_ECON_NOW_ENTRY_EDGE` | `0.10` | Min divergence between nowcast model and market to trigger trade |\r
| `SIMMER_ECON_NOW_EXIT_THRESHOLD` | `0.45` | Sell position when price reaches this level |\r
| `SIMMER_ECON_NOW_MAX_POSITION_USD` | `5.00` | Max USDC per trade |\r
| `SIMMER_ECON_NOW_MAX_TRADES_PER_RUN` | `3` | Max trades per execution cycle |\r
| `SIMMER_ECON_NOW_SLIPPAGE_MAX` | `0.15` | Max slippage before skipping (0.15 = 15%) |\r
| `SIMMER_ECON_NOW_MIN_LIQUIDITY` | `0` | Min market liquidity USD (0 = disabled) |\r
\r
## Dependency\r
\r
`simmer-sdk` is published on PyPI by Simmer Markets.\r
- PyPI: https://pypi.org/project/simmer-sdk/\r
- GitHub: https://github.com/SpartanLabsXyz/simmer-sdk\r
- Publisher: [email protected]\r
\r
Review the source before providing live credentials if you require full auditability.\r
Usage Guidance
This skill implements a legitimate-seeming Kalshi trading strategy and needs two sensitive credentials (SIMMER_API_KEY and SOLANA_PRIVATE_KEY). Before installing or providing keys: 1) Review the simmer-sdk source (PyPI/GitHub) to confirm there are no unexpected network calls or key exfiltration. 2) Keep to dry-run first; do not pass --live until you've audited behavior. 3) Provide least-privilege credentials where possible (testnet or read-only API keys) and rotate keys after testing. 4) Note the registry metadata omission of required env vars — treat that as a packaging quality issue and verify all required variables and permissions before trusting the skill with real funds.
Capability Analysis
Type: OpenClaw Skill Name: kalshi-econ-nowcast-trader Version: 1.0.1 The skill is a legitimate trading bot template for Kalshi CPI markets using the Cleveland Fed Nowcast model. It uses the 'simmer-sdk' to interact with the Simmer Markets platform and includes standard trading safeguards such as slippage limits, liquidity checks, and conviction-based position sizing. While it requires sensitive credentials like a Solana private key for live trading, this is consistent with its stated purpose of executing trades on a decentralized settlement layer (DFlow), and there is no evidence of data exfiltration or malicious intent in trader.py or SKILL.md.
Capability Tags
cryptorequires-wallet
Capability Assessment
Purpose & Capability
The code and SKILL.md implement a Kalshi trading strategy using the Simmer SDK and (optionally) Solana for live execution; requesting SIMMER_API_KEY and SOLANA_PRIVATE_KEY is coherent with that purpose. However, the upstream registry metadata claimed no required env vars while the distributed files (SKILL.md, clawhub.json, trader.py) do require these credentials — a discrepancy that suggests sloppy packaging or metadata omission.
Instruction Scope
The instructions and code focus on market discovery, pricing bins using a normal nowcast model, and trading via the simmer-sdk. I did not see instructions to read unrelated system files or to transmit data to unknown external endpoints; network calls appear to be to Simmer/Kalshi-related APIs. The code will import optional trade-journal modules and uses simmer_sdk.skill.load_config (which may read/write skill config), which is expected for an automatable trading skill.
Install Mechanism
There is no custom download/install URL or arbitrary archive in the registry, and the dependency is a PyPI package (simmer-sdk) with a linked GitHub repo. That is a reasonable install mechanism, but you should review the simmer-sdk source before granting live credentials because it will handle API calls and possibly signing/trading actions.
Credentials
The skill requests two high-value secrets: SIMMER_API_KEY (trading API) and SOLANA_PRIVATE_KEY (base58 private key for live Solana interactions). These are proportionate to a trading skill, but they are sensitive: the Solana private key grants custody-level access to funds. Additional tunable env vars are reasonable. The earlier registry metadata omitting these env requirements is inconsistent with the files and installation manifest.
Persistence & Privilege
The skill is not marked always:true and autostart is false; the automaton is managed but will not run automatically until enabled. Default mode is dry-run; live trades require an explicit --live flag. This limits unexpected persistent/automatic trading behavior, which is appropriate.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install kalshi-econ-nowcast-trader
  3. After installation, invoke the skill by name or use /kalshi-econ-nowcast-trader
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Rescan
v1.0.0
Initial release
Metadata
Slug kalshi-econ-nowcast-trader
Version 1.0.1
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is Kalshi Econ Nowcast Trader?

Trades CPI bin markets on Kalshi using the Cleveland Fed CPI Nowcast to compute fair bin probabilities via a normal distribution model. Requires SIMMER_API_K... It is an AI Agent Skill for Claude Code / OpenClaw, with 85 downloads so far.

How do I install Kalshi Econ Nowcast Trader?

Run "/install kalshi-econ-nowcast-trader" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Kalshi Econ Nowcast Trader free?

Yes, Kalshi Econ Nowcast Trader is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Kalshi Econ Nowcast Trader support?

Kalshi Econ Nowcast Trader is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Kalshi Econ Nowcast Trader?

It is built and maintained by diagnostikon (@diagnostikon); the current version is v1.0.1.

💬 Comments