← Back to Skills Marketplace
1537
Downloads
0
Stars
12
Active Installs
12
Versions
Install in OpenClaw
/install prediction-trade-journal
Description
Auto-log trades with context, track outcomes, generate calibration reports to improve trading.
Usage Guidance
This skill appears to do what it says: it needs your Simmer API key so it can fetch your trades and stores them locally under the skill folder (data/trades.json and data/context.json). Before installing: (1) confirm you trust simmer.markets and the simmer-sdk package; (2) be comfortable that the SIMMER_API_KEY grants read access to your trades; (3) note the code also accepts optional env vars (SIMMER_API_URL, SIMMER_JOURNAL_FETCH_LIMIT, SIMMER_JOURNAL_AUTO_SYNC) — review or set those if you need different behavior; (4) review the included Python files if you want to verify how errors and API responses are handled; and (5) consider storing the API key in a secure place and rotating it if you stop using the skill. If you need higher assurance, ask the author for a verified homepage or repository and verify the simmer-sdk package source.
Capability Analysis
Type: OpenClaw Skill
Name: prediction-trade-journal
Version: 1.1.13
The prediction-trade-journal skill is a legitimate tool for tracking and analyzing trades from the Simmer platform. It fetches trade data from the official API (api.simmer.markets) using a user-provided API key and stores it locally in JSON format for reporting and analysis. The code in tradejournal.py and scripts/status.py is transparent, lacks obfuscation, and does not exhibit any signs of data exfiltration to unauthorized endpoints or malicious execution patterns.
Capability Tags
Capability Assessment
Purpose & Capability
Name/description claim to sync trades, track outcomes, and report — the code implements API calls to https://api.simmer.markets, local storage under data/, CLI entrypoints, and a log_trade() helper for other skills. The declared pip dependency (simmer-sdk) and required API key are appropriate for this purpose.
Instruction Scope
SKILL.md instructs installing simmer-sdk, setting SIMMER_API_KEY, and running the provided CLI. The runtime instructions and the code operate only on the Simmer API and local files (data/trades.json, data/context.json). Note: the skill exposes a programmatic log_trade() function for other skills to call, which is expected for enrichment but means other installed skills could add context to your stored trades.
Install Mechanism
There is no arbitrary download/install step. The manifest lists a pip dependency (simmer-sdk), which is a standard package-install mechanism. No external URLs, archives, or non-standard installs are present.
Credentials
The skill requires a single API credential (SIMMER_API_KEY) which matches its function. However, the code also reads additional environment variables (SIMMER_API_URL, SIMMER_JOURNAL_FETCH_LIMIT, SIMMER_JOURNAL_AUTO_SYNC) not listed in SKILL.md or clawhub.json — this is a minor mismatch you should be aware of but not inherently malicious.
Persistence & Privilege
The skill stores data under its own directory (data/), does not request always:true, and does not modify other skills or global agent settings. It does perform local file writes (trades and context files), which is expected for a journal.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install prediction-trade-journal - After installation, invoke the skill by name or use
/prediction-trade-journal - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.13
Add Setup Flow section with pip install simmer-sdk
v1.1.12
- Updated metadata structure in SKILL.md and added new metadata fields.
- Changed SKILL.md formatting and moved version info to top-level fields.
- Added _meta.json file for improved metadata management.
- Removed obsolete clawhub.json file.
v1.1.11
AgentSkills format — moved platform config to clawhub.json for cross-agent compatibility
v1.1.10
- Added a "difficulty: beginner" field to SKILL.md for clearer guidance.
- No functional or command changes; documentation improvement only.
v1.1.9
Sync
v1.1.8
No changes detected in this version.
- Version number remains the same: 1.1.7
- No file or documentation updates
- No new features or bug fixes added
v1.1.7
- Added simmer-sdk as a required package in metadata for installation.
- Updated version number to 1.1.7 in the documentation.
v1.1.6
- Updated version number to 1.1.5 in documentation.
- No functional changes; SKILL.md file version metadata was incremented for consistency.
v1.1.5
- Updated documentation to remove the API URL configuration option and default; API key is now the only documented required environment variable.
- Bumped version from 1.1.3 to 1.1.4 in SKILL.md.
v1.1.4
- Updated version number from 1.1.2 to 1.1.3 in SKILL.md.
- No other functional or documentation changes.
v1.1.3
- Removed the local sample data file data/trades.json.
- No user-facing functionality or documentation changes.
v1.1.2
- Improved documentation with clear usage instructions, command reference, and integration examples.
- Detailed description of features: auto-logging trades, tracking outcomes, and generating calibration reports.
- Added explicit CLI command documentation and example JSON data structure.
- Provided troubleshooting tips for common setup issues.
- Listed environment variables and configuration requirements.
Metadata
Frequently Asked Questions
What is Prediction Trade Journal?
Auto-log trades with context, track outcomes, generate calibration reports to improve trading. It is an AI Agent Skill for Claude Code / OpenClaw, with 1537 downloads so far.
How do I install Prediction Trade Journal?
Run "/install prediction-trade-journal" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Prediction Trade Journal free?
Yes, Prediction Trade Journal is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Prediction Trade Journal support?
Prediction Trade Journal is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Prediction Trade Journal?
It is built and maintained by AD88 (@adlai88); the current version is v1.1.13.
More Skills