Simmer Calibration Report
PassAudited by ClawScan on May 1, 2026.
Overview
This appears to be a coherent trade-journal analytics skill, with noteworthy but disclosed use of a Simmer API key, local trading records, an external Python package, and optional scheduling.
Before installing, verify the simmer-sdk dependency, use a scoped Simmer API key if possible, and make sure the journal path points only to the trade data you intend to analyze. If you enable the daily cron, remember it can repeatedly read and summarize that journal.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Installing the package gives that dependency code execution in the local Python environment.
The skill instructs the user to install an external Python dependency without a pinned version. This is normal for a Simmer integration but means dependency provenance and future updates matter.
pip install simmer-sdk
Install from a trusted package index, consider pinning a known-good simmer-sdk version, and review dependency provenance if using this in a sensitive trading environment.
A Simmer API key may allow access to the user's Simmer account or trading-related data depending on its permissions.
The code can consume a Simmer API key to instantiate a Simmer client. The credential requirement is disclosed, and the visible report code is analytics-oriented, but API keys are sensitive authority.
api_key = os.environ.get("SIMMER_API_KEY") ... _client = SimmerClient(api_key=api_key, venue=venue, live=live)Use the least-privileged key available, avoid sharing terminal output that includes environment details, and rotate the key if you no longer trust the installed environment.
The report may expose trading history, strategy names, market types, PnL, and performance patterns in the agent conversation or logs.
The skill reads a local JSONL trade journal for analysis. This is central to the stated purpose, but trade journals can contain sensitive financial strategy and performance data.
with open(path, "r") as f: ... entry = json.loads(line)
Point CALIB_JOURNAL_PATH only at the intended journal, avoid including unrelated private files, and be mindful of where report output is stored or shared.
If enabled, the report may run daily and read the configured trade journal without a fresh manual command each time.
The skill declares a daily scheduled entrypoint, but autostart is disabled and the README frames automation as an optional reporting use case.
"cron": "0 8 * * *", "autostart": false, "automaton": { "managed": true, "entrypoint": "calibration_report.py" }Enable the cron schedule only if you want recurring analysis, and confirm the configured journal path and output destination before scheduling it.