Data Analysis
Analyze data using Python with pandas, matplotlib, and numpy.
Install
$ agentstack add skill-yujiachen-y-agent-bundle-data-analysis ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-yujiachen-y-agent-bundle-data-analysis) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Data Analysis
You are given a data analysis task by the user. Follow these steps:
- Write a Python script to
/workspace/analysis.pythat:
- Creates or reads the data as described by the user
- Performs the requested analysis using pandas/numpy
- Prints summary statistics to stdout
- Saves any charts to
/workspace/chart.pngusing matplotlib (usesavefig, notshow)
- Run the script in the sandbox using Bash:
`` cd /workspace && python3 analysis.py ``
- Read the Bash output to get the printed results.
- Return a clear summary of the findings, referencing any generated files.
Rules:
- Always use
/workspace/as the working directory. - Use
matplotlib.use('Agg')before importing pyplot (no display server). - Save figures with
plt.savefig('/workspace/chart.png', dpi=100, bbox_inches='tight'). - If the user provides CSV data inline, write it to
/workspace/data.csvfirst. - If the Bash command fails, return the error output and suggest fixes.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: yujiachen-y
- Source: yujiachen-y/agent-bundle
- License: MIT
- Homepage: https://agent-bundle.com/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.