Agent skill

Resilient Spreadsheet Workflow

by HKUDS in HKUDS/OpenSpace

Resilient multi-step workflow for spreadsheet processing when executecodesandbox fails, using shellagent exploration, file-based scripts, and verification steps

MITAuto-check passedDocuments & Office

Install Resilient Spreadsheet Workflow

skills CLI
$ npx skills add HKUDS/OpenSpace --skill resilient-spreadsheet-workflow -a claude-code

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

GitHub CLI
$ gh skill install HKUDS/OpenSpace resilient-spreadsheet-workflow --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/HKUDS/OpenSpace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/benchmarks/gdpval/skills/resilient-spreadsheet-workflow .claude/skills/resilient-spreadsheet-workflow && 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
resilient-spreadsheet-workflow
GitHub stars
7.7k
Token cost
~1k tokens
SKILL.md length
284 words
Files
2
Skills in repo
199
Repo updated
First seen
Licence
MIT

At a glance

Resilient multi-step workflow for spreadsheet processing when executecodesandbox fails, using shellagent exploration, file-based scripts, and verification steps

  • Works in 5 steps: Initial Exploration with shell_agent → Write Processing Script with write_file → Execute with run_shell and Error… → …
  • Tasks that involve Excel spreadsheets
  • SKILL.md covers When to Use, Step-by-Step Workflow, Complete Example and Common Error Patterns, plus 1 more section
  • Calls python

What it does

Resilient Spreadsheet Workflow is an agent skill from HKUDS/OpenSpace. Resilient multi-step workflow for spreadsheet processing when executecodesandbox fails, using shellagent exploration, file-based scripts, and verification steps

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.

It sits in Documents & Office, covering Excel spreadsheets. The repository describes itself as: "OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/. The licence is MIT.

When your agent uses it

  • Tasks that involve Excel spreadsheets

Example prompts

  • “/resilient-spreadsheet-workflow”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Initial Exploration with shell_agent
  2. Write Processing Script with write_file
  3. Execute with run_shell and Error Redirection
  4. Isolate Errors with Verification Commands
  5. Verify Output Before Reading

What it can do on your machine

Read from SKILL.md and the folder at commit 3827781. 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:

    • python

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

  • Network

    No URLs in SKILL.md.

    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

Resilient Spreadsheet Workflow loads about 1k tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 284 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~49
When it runs · the whole SKILL.md, loaded when a task matches
~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 HKUDS/OpenSpace at commit 3827781, republished under its MIT licence (© HKUDS). 284 words, ~1,017 tokens.

Download SKILL.mdSave it as .claude/skills/resilient-spreadsheet-workflow/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
resilient-spreadsheet-workflow
description
Resilient multi-step workflow for spreadsheet processing when execute_code_sandbox fails, using shell_agent exploration, file-based scripts, and verification steps

Resilient Spreadsheet Workflow

This skill provides a robust workflow for processing spreadsheet files (CSV, XLSX) when execute_code_sandbox encounters failures. It uses a combination of tools to ensure reliable execution and clear error diagnosis.

When to Use

  • Processing spreadsheet files when execute_code_sandbox returns unknown errors
  • Need to debug why spreadsheet operations fail
  • Require reliable file I/O with verification at each step

Step-by-Step Workflow

Step 1: Initial Exploration with shell_agent

Start by using shell_agent to explore the file structure and understand what files exist:

Use shell_agent to:
- List files in the working directory
- Identify spreadsheet files (CSV, XLSX)
- Examine file sizes and basic structure

Example task for shell_agent:

Explore the current directory to find all spreadsheet files (CSV, XLSX). 
List their sizes and identify which files need processing.
Step 2: Write Processing Script with write_file

Create a standalone script file rather than executing inline code:

python
# Use write_file to create a script like "process_sheet.py"
content = """
import pandas as pd
import sys

try:
    df = pd.read_csv('input.csv')  # or pd.read_excel for XLSX
    # Perform your processing
    result = df.describe()
    result.to_csv('output.csv', index=False)
    print("Processing complete")
except Exception as e:
    print(f"Error: {e}", file=sys.stderr)
    sys.exit(1)
"""

write_file(path="process_sheet.py", content=content)
Step 3: Execute with run_shell and Error Redirection

Execute the script with stderr redirected to stdout for complete error capture:

bash
run_shell command="python process_sheet.py 2>&1"

The 2>&1 redirection ensures both stdout and stderr are captured together, making error messages visible.

Step 4: Isolate Errors with Verification Commands

If Step 3 fails, add targeted verification commands to diagnose the actual problem:

bash
# Check if Python is available
run_shell command="which python 2>&1"

# Check if pandas is installed
run_shell command="python -c 'import pandas' 2>&1"

# Verify input file exists and is readable
run_shell command="ls -la input.csv 2>&1"

# Check file encoding/content
run_shell command="file input.csv 2>&1"
run_shell command="head -5 input.csv 2>&1"
Step 5: Verify Output Before Reading

Before reading results with read_file, verify the output file exists:

list_dir(path=".")
# Confirm output file appears in the listing
# Then proceed to read_file

Complete Example

1. shell_agent(task="Find and describe all CSV/XLSX files in current directory")
2. write_file(path="analyze_data.py", content="<processing script>")
3. run_shell(command="python analyze_data.py 2>&1")
4. If error: run_shell(command="python -c 'import pandas; print(pandas.__version__)' 2>&1")
5. list_dir(path=".")  # Verify output exists
6. read_file(filetype="csv", file_path="output.csv")

Common Error Patterns

SymptomDiagnostic CommandLikely Cause
Module not foundpython -c 'import pandas'Missing dependency
File not foundls -la <filename>Wrong path or name
Permission deniedls -la <filename>File permissions
Encoding errorfile <filename>Wrong file format

Best Practices

  1. Always use 2>&1 with run_shell for shell commands to capture full error output
  2. Verify before reading - use list_dir to confirm file existence before read_file
  3. Break into small steps - separate exploration, script writing, execution, and verification
  4. Use shell_agent for unknowns - when directory structure or file types are unclear
  5. Write scripts to files - more reliable than inline code execution for complex operations

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

Files

SKILL.md and 1 other file in benchmarks/gdpval/skills/resilient-spreadsheet-workflow of HKUDS/OpenSpace.

  • SKILL.md
  • .skill_id

Open the folder on GitHubat commit 3827781

Compare with similar skills

Resilient Spreadsheet Workflow 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.

Resilient Spreadsheet Workflow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Resilient Spreadsheet Workflow this skillHKUDS/OpenSpace7.7k—~1kAutomated safety check: PassMIT
MarkitdownImCa0/just-laws78114 repos~3.2kAutomated safety check: NotesMIT
Managing Google Workspacetaylorwilsdon/google_workspace_mcp3.3k—~2.9kAutomated safety check: PassMIT
Data Table Managern8n-io/n8n207k—~2.3kAutomated safety check: PassCustom licence
Docx4jplutext/docx4j2.4k—~2.5kAutomated safety check: PassNone
Instrument Data To Allotropeaws-samples/amazon-bedrock-agents-healthcare-lifesciences2742 repos~2.7kAutomated safety check: PassApache-2.0

Similar skills

  • Markitdown

    ImCa0/just-laws

    Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.

    781 GitHub starsUsed in 14 repos~3.2k tokens
    Documents & OfficeAuto-check: notes
  • Managing Google Workspace

    taylorwilsdon/google_workspace_mcp

    Manages Google Workspace operations across 12 services (Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms, Tasks, Contacts, Chat, Apps Script, Custom Search).

    3.3k GitHub stars~2.9k tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • Official

    Load before calling data-tables or parse-file. An agent skill from n8n-io/n8n.

    207k GitHub stars~2.3k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Docx4j

    plutext/docx4j

    A skill your agent uses when writing Java code that creates, reads or edits Word (.docx), PowerPoint (.pptx) or Excel (.xlsx) files with docx4j — including generating documents, editing existing…

    2.4k GitHub stars~2.5k tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • Instrument Data To Allotrope

    aws-samples/amazon-bedrock-agents-healthcare-lifesciences

    Official

    Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV.

    274 GitHub starsUsed in 2 repos~2.7k tokens
    Documents & OfficeAuto-check passed
  • Cyber Ppt

    crazyykhllc-bit/CyberPPT

    当用户需要把 DOCX、PDF、TXT、XLSX、研究报告、业务材料或原始数据转成高密度、可编辑、咨询风格 PPTX 时使用;也适用于需要 SCR 论证、视觉风格探索、详细图表和渲染质检的 PPT。

    1.8k GitHub stars~10k tokensUpdated 2 mo ago
    Documents & OfficeAuto-check passed

More from HKUDS/OpenSpace

All 199 skills in this repo
  • Walks through producing a master audio track plus stems in Python, from checking a reference file and timing sections by BPM to effects, a zip archive and final verification.

    7.7k GitHub stars~2.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Handle cascading data retrieval tool failures by falling back to embedded knowledge generation

    7.7k GitHub stars~765 tokensUpdated 1 mo ago
    Auto-check passed
  • Gives an agent a workaround when its code-execution sandbox keeps failing: save the Python script to a file and run it through the shell instead.

    7.7k GitHub stars~588 tokensUpdated 1 mo ago
    Auto-check passed
  • A recovery routine for agents whose sandboxed code runner keeps failing: save the Python script to disk, then run it through the shell and read the output.

    7.7k GitHub stars~652 tokensUpdated 1 mo ago
    Auto-check passed
  • Fallback ladder for failed sandboxed code runs, plus the habit of fixing the working directory first so generated files land in the right place.

    7.7k GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Fallback workflow for executing Python code when executecodesandbox fails repeatedly

    7.7k GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Resilient Spreadsheet Workflow

What does Resilient Spreadsheet Workflow do?

Resilient multi-step workflow for spreadsheet processing when executecodesandbox fails, using shellagent exploration, file-based scripts, and verification steps. Resilient Spreadsheet Workflow is an agent skill from HKUDS/OpenSpace.

When should I use Resilient Spreadsheet Workflow?

Resilient Spreadsheet Workflow fits situations like: tasks that involve Excel spreadsheets.

How do I install Resilient Spreadsheet Workflow in Claude Code?

Run `npx skills add HKUDS/OpenSpace --skill resilient-spreadsheet-workflow -a claude-code`. Or copy the skill folder (benchmarks/gdpval/skills/resilient-spreadsheet-workflow in HKUDS/OpenSpace) into .claude/skills/resilient-spreadsheet-workflow in your project. Claude Code loads it when a task matches its description.

How do I install Resilient Spreadsheet Workflow in Codex?

Run `npx skills add HKUDS/OpenSpace --skill resilient-spreadsheet-workflow -a codex`. Or copy the skill folder (benchmarks/gdpval/skills/resilient-spreadsheet-workflow in HKUDS/OpenSpace) into .agents/skills/resilient-spreadsheet-workflow in your project. Codex loads it when a task matches its description.

Can I use Resilient Spreadsheet Workflow 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 HKUDS/OpenSpace --skill resilient-spreadsheet-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/resilient-spreadsheet-workflow, .gemini/skills/resilient-spreadsheet-workflow, .github/skills/resilient-spreadsheet-workflow and .opencode/skills/resilient-spreadsheet-workflow in your project.

What does Resilient Spreadsheet Workflow need to run?

Going by SKILL.md and its folder, Resilient Spreadsheet Workflow needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Resilient Spreadsheet Workflow access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Resilient Spreadsheet Workflow 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 Resilient Spreadsheet Workflow use?

Resilient Spreadsheet Workflow is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Resilient Spreadsheet Workflow use?

About 1k tokens (SKILL.md is roughly 4.1k 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 Resilient Spreadsheet Workflow?

Skills that share tags, products or a category with Resilient Spreadsheet Workflow: Markitdown (ImCa0/just-laws, 781 stars), Managing Google Workspace (taylorwilsdon/google_workspace_mcp, 3.3k stars), Data Table Manager (n8n-io/n8n, 207k stars) and Docx4j (plutext/docx4j, 2.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Resilient Spreadsheet Workflow?

HKUDS (a GitHub organization) maintains it in HKUDS/OpenSpace, which has 7,749 GitHub stars. The repository holds 199 skills in this directory. The repository was last updated on August 12, 2026.

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