Polymarket Twitter Weekend Drift Trader

Exploits systematic weekday/weekend posting rate differences in post-count bin markets. Requires SIMMER_API_KEY and simmer-sdk. Use when you want to capture...

Security Scan

This skill is internally consistent with its stated purpose: a Polymarket/Simmer trading strategy that legitimately requires a SIMMER_API_KEY and the simmer-sdk; there are no signs of unrelated credential requests, hidden network installs, or unexpected persistence.

Purpose & Capability

The skill's name/description (weekend-drift trading on Polymarket) matches the code and declared dependencies: trader.py uses SimmerClient and looks up markets, computes signals, and places trades. One minor inconsistency: the top-level registry block in the report lists 'Required env vars: none', whereas clawhub.json and SKILL.md correctly declare SIMMER_API_KEY; this is likely a metadata-sync issue rather than malicious behavior.

Instruction Scope

SKILL.md instructs installing the skill and setting SIMMER_API_KEY; runtime behavior (as seen in trader.py) is limited to finding markets, computing signals, and (optionally) placing trades. The skill defaults to paper mode and only does real trades with an explicit --live flag. The instructions do not ask the agent to read unrelated system files or exfiltrate data.

Install Mechanism

There is no custom download/install script; the package depends on simmer-sdk (published on PyPI and with a GitHub repo). This is a standard dependency mechanism (pip) and not a direct arbitrary-URL fetch or archive extraction.

Credentials

The only sensitive credential required is SIMMER_API_KEY (the exchange/trading API key) and a set of SIMMER_* tunables for risk parameters. Those are appropriate and proportional for a trading bot. The SKILL.md explicitly warns about not placing a live-capable key in environments where automated code could execute. As noted above, there is a metadata mismatch in the top-level report that falsely said 'no required env vars'—verify the platform metadata before providing credentials.

Persistence & Privilege

always:false and autostart:false (no forced inclusion or automatic background start). disable-model-invocation is false (agent can call the skill), which is the platform default and expected for an invocable trading skill. The skill does not request system-wide config changes or other skills' credentials.

Assessment

This appears to be a straightforward trading skill. Before installing: (1) review the simmer-sdk source (linked in SKILL.md) to confirm no unexpected network endpoints or privileged calls; (2) do not put a live-capable SIMMER_API_KEY into the environment until you have audited the dependency and tested in paper mode; (3) confirm the platform metadata (registry) correctly lists SIMMER_API_KEY—the report shows a mismatch that should be resolved; (4) run the bot in paper (sim) mode first and monitor actions/logs; and (5) if you plan to enable automated runs, restrict the API key's permissions (if possible) or create a separate limited-account key.

Twitter Weekend Drift Trader

This is a template.
The default signal uses fixed weekday/weekend rate differentials — remix it with hourly posting distributions, holiday calendars, or timezone-aware activity windows.
The skill handles all the plumbing (market discovery, trade execution, safeguards). Your agent provides the alpha.

Strategy Overview

Public figures post 20-30% less on weekends. But market makers often set prices on Friday, reflecting weekday cadence. A 3-day period spanning Fri-Sun has very different expected post counts than Mon-Wed.

This skill counts the actual weekdays vs weekend days in each market's period and adjusts the expected rate accordingly.

Signal Logic

Weekend Rate Differentials

Person	Weekday Rate	Weekend Rate	Drop
Elon Musk	72/day	50/day	-31%
Donald Trump	25/day	20/day	-20%
Vitalik Buterin	9/day	7/day	-22%
CZ	14/day	10/day	-29%

How It Works

1. Parse the date range from the market question
2. Count actual weekdays and weekend days
3. Compute adjusted_lambda = weekday_rate * weekdays + weekend_rate * weekends
4. Compare to naive_lambda = average_rate * total_days
5. The drift determines which bins are over/underpriced

Example

Elon Musk, March 28 (Fri) to March 30 (Sun) = 3 days:

• Naive: 65/day * 3 = 195 posts
• Adjusted: 721 + 502 = 172 posts
• Drift: -12% — lower bins underpriced, higher bins overpriced

Remix Ideas

• Holiday calendar: Major holidays (Christmas, July 4th) suppress posting even more than weekends
• Hourly distribution: Model posting by hour-of-day for sub-daily market periods
• Timezone awareness: Elon posts Pacific time, Trump posts Eastern — periods crossing midnight differ
• Rolling rate updates: Re-estimate weekday/weekend split weekly from actual data

Risk Parameters

Parameter	Default	Notes
Max position size	$40 USDC	Per market
Min market volume	$1,000	Standard filter
Max bid-ask spread	10%	Default threshold
Min days to resolution	0	Post-count markets are short-lived
Max open positions	8	Diversify across bins

Installation & Setup

clawhub install polymarket-twitter-weekend-drift-trader

Requires: SIMMER_API_KEY environment variable.

Cron Schedule

Cron is set to null — the skill does not run on a schedule until you configure it in the Simmer UI.

Safety & Execution Mode

The skill defaults to paper trading (venue="sim"). Real trades only execute when --live is passed explicitly.

Scenario	Mode	Financial risk
python trader.py	Paper (sim)	None
Cron / automaton	Paper (sim)	None
python trader.py --live	Live (polymarket)	Real USDC

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.

Required Credentials

Variable	Required	Notes
SIMMER_API_KEY	Yes	Trading authority — keep this credential private. Do not place a live-capable key in any environment where automated code could call --live.

Tunables (Risk Parameters)

All risk parameters are declared in clawhub.json as tunables and adjustable from the Simmer UI without code changes. They use SIMMER_-prefixed env vars so apply_skill_config() can load them securely.

Variable	Default	Purpose
SIMMER_MAX_POSITION	40	Max USDC per trade (reached at 100% conviction)
SIMMER_MIN_VOLUME	1000	Min market volume filter (USD)
SIMMER_MAX_SPREAD	0.10	Max bid-ask spread (0.10 = 10%)
SIMMER_MIN_DAYS	0	Min days until market resolves
SIMMER_MAX_POSITIONS	8	Max concurrent open positions
SIMMER_YES_THRESHOLD	0.38	Buy YES if market price ≤ this value
SIMMER_NO_THRESHOLD	0.62	Sell NO if market price ≥ this value
SIMMER_MIN_TRADE	5	Floor for any trade (min USDC regardless of conviction)

Dependency

simmer-sdk is published on PyPI by Simmer Markets.

• PyPI: https://pypi.org/project/simmer-sdk/
• GitHub: https://github.com/SpartanLabsXyz/simmer-sdk
• Publisher: [e-mail]

Review the source before providing live credentials if you require full auditability.