← Back to Skills Marketplace
1169
Downloads
0
Stars
19
Active Installs
2
Versions
Install in OpenClaw
/install pandas
Description
Analyze, transform, and clean DataFrames with efficient patterns for filtering, grouping, merging, and pivoting.
Usage Guidance
This skill appears coherent and low-risk: it is an instruction-only pandas helper that will create and read ~/pandas/memory.md and optional snippets. Before installing, consider: (1) Are you comfortable with a small preferences file being created in your home directory? Review its contents if you store sensitive context. (2) Ensure python3 is available on the system. (3) Although the skill says it won't send data externally, this is a behavioral claim in text — avoid using sensitive secrets or production credentials in example data unless you verify the agent environment's network restrictions. (4) If you want extra isolation, run the skill under a separate user account or in a sandboxed environment. Overall, the skill is internally consistent with its stated purpose.
Capability Analysis
Type: OpenClaw Skill
Name: pandas
Version: 1.0.1
The OpenClaw Pandas skill bundle is benign. All files consistently describe a skill designed to assist with Pandas operations, storing user preferences locally in `~/pandas/memory.md` and explicitly stating that no data is sent externally or uploaded to any service. The `SKILL.md` file provides clear security assurances, indicating the skill does not access files outside its designated directory or modify source data without explicit instruction. There are no prompt injection attempts to subvert the agent's behavior, no malicious execution patterns, and no signs of data exfiltration or persistence mechanisms.
Capability Assessment
Purpose & Capability
Name/description (Pandas helper) align with requirements and instructions. Requesting python3 is expected and there are no unrelated binaries, env vars, or config paths.
Instruction Scope
SKILL.md focuses on local DataFrame operations and storing preferences in ~/pandas/memory.md. This is coherent, but the skill reads/writes a folder in the user's home and the working directory — users should be aware preferences and any saved snippets live on disk. The instructions assert 'no external upload' and 'no access outside ~/pandas/ and the working directory'; those are behavioral constraints in prose (not technically enforced), so trust is required.
Install Mechanism
No install spec or downloaded code — instruction-only skills write nothing beyond the documented ~/pandas/ memory files. This is low-risk compared with bundles that fetch remote binaries.
Credentials
The skill requests no credentials, env vars, or config paths. That is proportionate for a local pandas helper.
Persistence & Privilege
always is false and the skill stores only its own memory under ~/pandas/. It does not request persistent system-wide privileges or modify other skills. Autonomous invocation is allowed (platform default) but not a red flag here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install pandas - After installation, invoke the skill by name or use
/pandas - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Initial release
v1.0.0
Initial release
Metadata
Frequently Asked Questions
What is Pandas?
Analyze, transform, and clean DataFrames with efficient patterns for filtering, grouping, merging, and pivoting. It is an AI Agent Skill for Claude Code / OpenClaw, with 1169 downloads so far.
How do I install Pandas?
Run "/install pandas" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Pandas free?
Yes, Pandas is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Pandas support?
Pandas is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, darwin, win32).
Who created Pandas?
It is built and maintained by Iván (@ivangdavila); the current version is v1.0.1.
More Skills