Agent skill

Batch Processor

by claude-office-skills in claude-office-skills/skills

Process multiple documents in bulk with parallel execution. An agent skill from claude-office-skills/skills.

MITAuto-check passed

Install Batch Processor

skills CLI
$ npx skills add claude-office-skills/skills --skill batch-processor -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install claude-office-skills/skills batch-processor --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/claude-office-skills/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/batch-processor .claude/skills/batch-processor && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
batch-processor
GitHub stars
499
Token cost
~1.1k tokens
SKILL.md length
122 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Process multiple documents in bulk with parallel execution. An agent skill from claude-office-skills/skills.

  • Works in 3 steps: Describe what you want to accomplish → Provide any required input data or files → I'll execute the appropriate operations
  • SKILL.md covers Overview, How to Use, Domain Knowledge and Best Practices, plus 2 more sections
  • Calls pip

What it does

Batch Processor is an agent skill from claude-office-skills/skills. Process multiple documents in bulk with parallel execution

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: A curated collection of practical Claude Skills for real-world office tasks. The licence is MIT.

Example prompts

  • “/batch-processor”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Describe what you want to accomplish
  2. Provide any required input data or files
  3. I'll execute the appropriate operations

What it can do on your machine

Read from SKILL.md and the folder at commit 9c4c7d5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Batch Processor loads about 1.1k tokens when it runs. Until then it costs about 19 tokens; SKILL.md has 122 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~19
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from claude-office-skills/skills at commit 9c4c7d5, republished under its MIT licence (© claude-office-skills). 122 words, ~1,084 tokens.

Download SKILL.mdSave it as .claude/skills/batch-processor/SKILL.md (or your agent's skills folder).
name
batch-processor
description
Process multiple documents in bulk with parallel execution
version
1.0
author
claude-office-skills
license
MIT
category
workflow
tags
batch, processor, bulk, automation
department
All
models.recommended
claude-sonnet-4, claude-opus-4
models.compatible
claude-3-5-sonnet, gpt-4, gpt-4o
mcp.server
office-mcp
mcp.tools
batch_convert

Batch Processor Skill

Overview

This skill enables efficient bulk processing of documents - convert, transform, extract, or analyze hundreds of files with parallel execution and progress tracking.

How to Use

  1. Describe what you want to accomplish
  2. Provide any required input data or files
  3. I'll execute the appropriate operations

Example prompts:

  • "Convert 100 PDFs to Word documents"
  • "Extract text from all images in a folder"
  • "Batch rename and organize files"
  • "Mass update document headers/footers"

Domain Knowledge

Batch Processing Patterns
Input: [file1, file2, ..., fileN]
         │
         ▼
    ┌─────────────┐
    │  Parallel   │  ← Process multiple files concurrently
    │  Workers    │
    └─────────────┘
         │
         ▼
Output: [result1, result2, ..., resultN]
Python Implementation
python
from concurrent.futures import ProcessPoolExecutor, as_completed
from pathlib import Path
from tqdm import tqdm

def process_file(file_path: Path) -> dict:
    """Process a single file."""
    # Your processing logic here
    return {"path": str(file_path), "status": "success"}

def batch_process(input_dir: str, pattern: str = "*.*", max_workers: int = 4):
    """Process all matching files in directory."""
    
    files = list(Path(input_dir).glob(pattern))
    results = []
    
    with ProcessPoolExecutor(max_workers=max_workers) as executor:
        futures = {executor.submit(process_file, f): f for f in files}
        
        for future in tqdm(as_completed(futures), total=len(files)):
            file = futures[future]
            try:
                result = future.result()
                results.append(result)
            except Exception as e:
                results.append({"path": str(file), "error": str(e)})
    
    return results

# Usage
results = batch_process("/documents/invoices", "*.pdf", max_workers=8)
print(f"Processed {len(results)} files")
Error Handling & Resume
python
import json
from pathlib import Path

class BatchProcessor:
    def __init__(self, checkpoint_file: str = "checkpoint.json"):
        self.checkpoint_file = checkpoint_file
        self.processed = self._load_checkpoint()
    
    def _load_checkpoint(self):
        if Path(self.checkpoint_file).exists():
            return json.load(open(self.checkpoint_file))
        return {}
    
    def _save_checkpoint(self):
        json.dump(self.processed, open(self.checkpoint_file, "w"))
    
    def process(self, files: list, processor_func):
        for file in files:
            if str(file) in self.processed:
                continue  # Skip already processed
            
            try:
                result = processor_func(file)
                self.processed[str(file)] = {"status": "success", **result}
            except Exception as e:
                self.processed[str(file)] = {"status": "error", "error": str(e)}
            
            self._save_checkpoint()  # Resume-safe

Best Practices

  1. Use progress bars (tqdm) for user feedback
  2. Implement checkpointing for long jobs
  3. Set reasonable worker counts (CPU cores)
  4. Log failures for later review

Installation

bash
# Install required dependencies
pip install python-docx openpyxl python-pptx reportlab jinja2

Resources

© claude-office-skills, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in batch-processor of claude-office-skills/skills.

Open the folder on GitHubat commit 9c4c7d5

Compare with similar skills

Batch Processor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Batch Processor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Batch Processor this skillclaude-office-skills/skills499—~1.1kAutomated safety check: PassMIT
Parallel Batch OperationsQwenLM/qwen-code28k—~2.3kAutomated safety check: PassApache-2.0
Batchasgeirtj/system_prompts_leaks69k—~1.3kAutomated safety check: PassCC0-1.0
Batch File Processorjeremylongshore/tons-of-skills-marketplace2.8k—~577Automated safety check: PassMIT
Batchcodewhale-hq/Codewhale41k—~157Automated safety check: PassMIT
Parallel Execution Optimizeraffaan-m/ECC275k1 repos~712Automated safety check: PassMIT

Similar skills

  • Runs one operation across many files with parallel worker agents: finds files by glob pattern, splits them into chunks, launches workers and summarizes the results.

    28k GitHub stars~2.3k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Batch

    asgeirtj/system_prompts_leaks

    Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.

    69k GitHub stars~1.3k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Batch File Processor

    jeremylongshore/tons-of-skills-marketplace

    Process batch file processor operations. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~577 tokensUpdated yesterday
    Auto-check passed
  • Batch

    codewhale-hq/Codewhale

    Break a large, parallelizable goal into bounded work units, coordinate existing agent/worktree machinery, integrate, and verify.

    41k GitHub stars~157 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Speed up a task by turning it into a dependency graph of parallel lanes with a lane matrix, batched reads and checks, write surfaces isolated by file, worktree, branch, or service, and a final…

    275k GitHub starsUsed in 1 repo~712 tokens
    DevelopmentAuto-check passed
  • Run macOS Parallels smoke with Discord send, host verification, host reply, and guest readback proof.

    392k GitHub stars~788 tokensUpdated yesterday
    Auto-check passed

More from claude-office-skills/skills

All 12 skills in this repo
  • Airtable Automation

    claude-office-skills/skills

    Airtable database automation - views, automations, integrations, and workflow triggers

    499 GitHub stars~2.7k tokensUpdated 8 mo ago
    Auto-check passed
  • Academic Search

    claude-office-skills/skills

    Search and analyze academic literature. An agent skill from claude-office-skills/skills.

    499 GitHub stars~2.2k tokensUpdated 8 mo ago
    Auto-check passed
  • Ads Copywriter

    claude-office-skills/skills

    Multi-platform ad copy generation for Google Ads, Meta/Facebook, TikTok, LinkedIn with A/B testing variants

    499 GitHub stars~2.1k tokensUpdated 8 mo ago
    Auto-check passed
  • AI Slides

    claude-office-skills/skills

    Generate complete presentations with AI - from outline to polished slides

    499 GitHub stars~1.4k tokensUpdated 8 mo ago
    Auto-check passed
  • Batch Convert

    claude-office-skills/skills

    Batch convert documents between multiple formats using a unified pipeline

    499 GitHub stars~3.8k tokensUpdated 8 mo ago
    Auto-check passed
  • Calendar Automation

    claude-office-skills/skills

    Google Calendar and Outlook automation - scheduling optimization, meeting workflows, time blocking, and Slack/Sheets integration

    499 GitHub stars~2.7k tokensUpdated 8 mo ago
    Auto-check passed

Questions about Batch Processor

What does Batch Processor do?

Process multiple documents in bulk with parallel execution. An agent skill from claude-office-skills/skills. Batch Processor is an agent skill from claude-office-skills/skills.

How do I install Batch Processor in Claude Code?

Run `npx skills add claude-office-skills/skills --skill batch-processor -a claude-code`. Or copy the skill folder (batch-processor in claude-office-skills/skills) into .claude/skills/batch-processor in your project. Claude Code loads it when a task matches its description.

How do I install Batch Processor in Codex?

Run `npx skills add claude-office-skills/skills --skill batch-processor -a codex`. Or copy the skill folder (batch-processor in claude-office-skills/skills) into .agents/skills/batch-processor in your project. Codex loads it when a task matches its description.

Can I use Batch Processor in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add claude-office-skills/skills --skill batch-processor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/batch-processor, .gemini/skills/batch-processor, .github/skills/batch-processor and .opencode/skills/batch-processor in your project.

What does Batch Processor need to run?

Going by SKILL.md and its folder, Batch Processor needs the command-line tools its instructions call (pip). Our summary lists: Python 3.

Does Batch Processor access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Batch Processor safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Batch Processor use?

Batch Processor is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Batch Processor use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Batch Processor?

Skills that share tags, products or a category with Batch Processor: Parallel Batch Operations (QwenLM/qwen-code, 28k stars), Batch (asgeirtj/system_prompts_leaks, 69k stars), Batch File Processor (jeremylongshore/tons-of-skills-marketplace, 2.8k stars) and Batch (codewhale-hq/Codewhale, 41k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Batch Processor?

claude-office-skills (a GitHub organization) maintains it in claude-office-skills/skills, which has 499 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on January 31, 2026.

Source: claude-office-skills/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.