← Back to Skills Marketplace
Python Code Tester
by
zhouhh2017
· GitHub ↗
· v1.0.3
· MIT-0
1142
Downloads
0
Stars
4
Active Installs
4
Versions
Install in OpenClaw
/install python-code-test
Description
代码功能测试skill，根据用户需求搜索代码、生成测试用例、执行测试并修复问题
Usage Guidance
This skill appears internally consistent with its purpose, but it will: (1) install Python packages via pip, (2) write test data to references/, create logs under scripts/log/, and create release copies and overwrite project files with fixes. Before running, review scripts/main.py and run.sh, back up your repository, and consider executing the skill in an isolated environment (container or VM). Inspect generated tests and any proposed code changes before merging them into your main codebase. If you do not want automatic code modification, run the tool in a dry-run mode or remove/guard the sync/overwrite step.
Capability Analysis
Type: OpenClaw Skill
Name: python-code-test
Version: 1.0.3
The skill is designed to search, generate, execute, and 'fix' project code, which involves high-risk operations like executing dynamically generated Python scripts via subprocess (main.py) and overwriting original source files (update_project_code). While these capabilities are aligned with the stated purpose of a code testing assistant, the combination of arbitrary code execution and file system modification poses a significant risk of accidental or exploited RCE, though no clear evidence of intentional malice or data exfiltration was found.
Capability Assessment
Purpose & Capability
The skill name/description (Python code testing) matches the included files and behavior: scripts/main.py implements project search, test-case generation, test execution and repair workflows; run.sh and requirements.txt support running tests. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md and the code instruct the agent to search the project source, create test data under references/, write test scripts under scripts/, save logs to scripts/log/, and update project files with fixes (scripts/release/v{n}/ then sync into project). This is in-scope for a testing/fixing tool but it grants the skill broad filesystem write and code-modification authority. The instructions also allow fetching external datasets when needed.
Install Mechanism
There is no platform install spec (instruction-only), but run.sh will pip install packages from requirements.txt (pytest, numpy, pandas). Installing PyPI deps is expected for this task but is an action the user should review before running. No downloads from unknown URLs or archive extraction were observed.
Credentials
The skill does not declare or require environment variables, credentials, or config paths. Its filesystem and network needs (writing references/logs, optionally downloading datasets) are proportional to the stated purpose. No secrets or unrelated external service tokens are requested.
Persistence & Privilege
always:false and normal model invocation are set. The skill will create directories and modify project files (release copies and then sync fixes into the project), which is expected for an auto-fixing tester but is a privileged action — it can alter your codebase when run.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install python-code-test - After installation, invoke the skill by name or use
/python-code-test - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
- Removed 4 files: references/doc.md, references/test_data_cluster.csv, scripts/log/test_log_v4_20260308_114025.json, and scripts/release/v4/test_cluster_analysis.py
- Cleaned up references and release directories by deleting unused data, documentation, logs, and test scripts.
v1.0.2
- Added new test data and log files to support enhanced cluster analysis testing.
- Introduced a new test script for cluster analysis in the latest release directory.
- Removed outdated test scripts and cluster analysis scripts from previous versions.
v1.0.1
- No changes detected in this version.
- SKILL.md content remains identical to the previous release.
v1.0.0
Initial release of the python-code-test skill.
- Enables code functionality testing based on user requirements.
- Automates code search, test case generation with ground truth, and test execution.
- Saves and reuses testing data under a references/ directory.
- Handles test failures by analyzing, attempting code fixes, and versioning fixed code.
- Records all test results and errors to scripts/log/.
- Ensures test cases include correctness validation, not just execution.
Metadata
Frequently Asked Questions
What is Python Code Tester?
代码功能测试skill，根据用户需求搜索代码、生成测试用例、执行测试并修复问题. It is an AI Agent Skill for Claude Code / OpenClaw, with 1142 downloads so far.
How do I install Python Code Tester?
Run "/install python-code-test" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Python Code Tester free?
Yes, Python Code Tester is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Python Code Tester support?
Python Code Tester is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Python Code Tester?
It is built and maintained by zhouhh2017 (@zhouhh2017); the current version is v1.0.3.
More Skills