# Send Pandas to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "pandas",
    "name": "Pandas",
    "source": "tencent",
    "type": "skill",
    "category": "数据分析",
    "sourceUrl": "https://clawhub.ai/ivangdavila/pandas",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/pandas",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/pandas",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=pandas",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md",
      "memory-template.md",
      "setup.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "pandas",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-29T23:18:28.093Z",
      "expiresAt": "2026-05-06T23:18:28.093Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=pandas",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=pandas",
        "contentDisposition": "attachment; filename=\"pandas-1.0.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "pandas"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/pandas"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/pandas",
    "downloadUrl": "https://openagent3.xyz/downloads/pandas",
    "agentUrl": "https://openagent3.xyz/skills/pandas/agent",
    "manifestUrl": "https://openagent3.xyz/skills/pandas/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/pandas/agent.md"
  }
}
```
## Documentation

### Setup

On first use, create ~/pandas/ and read setup.md for initialization. User preferences are stored in ~/pandas/memory.md — users can view or edit this file anytime.

### When to Use

User needs to work with tabular data in Python. Agent handles DataFrame operations, data cleaning, aggregations, merges, pivots, and exports.

### Architecture

Memory lives in ~/pandas/. See memory-template.md for structure.

~/pandas/
├── memory.md     # User preferences and common patterns
└── snippets/     # Saved code patterns (optional)

### Quick Reference

TopicFileSetup processsetup.mdMemory templatememory-template.md

### 1. Use Vectorized Operations

NEVER iterate with for loops over DataFrame rows
Use .apply() only when vectorized alternatives don't exist
Prefer df['col'].str.method() over apply(lambda x: x.method())

### 2. Chain Methods for Readability

# Good: method chaining
result = (df
    .query('age > 30')
    .groupby('city')
    .agg({'salary': 'mean'})
    .reset_index())

# Bad: intermediate variables everywhere
filtered = df[df['age'] > 30]
grouped = filtered.groupby('city')
result = grouped.agg({'salary': 'mean'}).reset_index()

### 3. Handle Missing Data Explicitly

Always check df.isna().sum() before analysis
Choose strategy: dropna(), fillna(), or interpolation
Document WHY missing values exist before removing them

### 4. Use Categorical for Repeated Strings

# Memory savings for columns with few unique values
df['status'] = df['status'].astype('category')
df['country'] = df['country'].astype('category')

### 5. Merge with Validation

# Always specify how and validate
result = pd.merge(
    df1, df2,
    on='id',
    how='left',
    validate='m:1'  # Many-to-one: catch unexpected duplicates
)

### 6. Prefer query() for Complex Filters

# Readable
df.query('age > 30 and city == "NYC" and salary < 100000')

# Hard to read
df[(df['age'] > 30) & (df['city'] == 'NYC') & (df['salary'] < 100000)]

### 7. Set Index When Appropriate

# Faster lookups, cleaner merges
df = df.set_index('user_id')
user_data = df.loc[12345]  # O(1) lookup

### Common Traps

SettingWithCopyWarning → Use .loc[] for assignment: df.loc[mask, 'col'] = value
Slow loops → Replace iterrows() with vectorized ops or apply()
Memory explosion → Use dtype in read_csv(): pd.read_csv(f, dtype={'id': 'int32'})
Silent data loss → Check shape before/after merge: print(f"Before: {len(df1)}, After: {len(result)}")
Index confusion → Use reset_index() after groupby() to get clean DataFrame
Chained indexing → df['a']['b'] fails silently; use df.loc[:, ['a', 'b']]

### Security & Privacy

Data storage:

User preferences stored in ~/pandas/memory.md
All DataFrame operations run locally
No data is sent externally

This skill does NOT:

Upload data to any service
Access files outside ~/pandas/ and the working directory
Modify source data files without explicit instruction

User control:

View stored preferences: cat ~/pandas/memory.md
Clear all data: rm -rf ~/pandas/

### Related Skills

Install with clawhub install <slug> if user confirms:

data-analysis — general data analysis patterns
csv — CSV file handling
sql — database queries
excel-xlsx — Excel file operations

### Feedback

If useful: clawhub star pandas
Stay updated: clawhub sync
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: ivangdavila
- Version: 1.0.1
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-04-29T23:18:28.093Z
- Expires at: 2026-05-06T23:18:28.093Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/pandas)
- [Send to Agent page](https://openagent3.xyz/skills/pandas/agent)
- [JSON manifest](https://openagent3.xyz/skills/pandas/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/pandas/agent.md)
- [Download page](https://openagent3.xyz/downloads/pandas)