Agent skill

Integrated Report Bundle

by HKUDS in HKUDS/OpenSpace

Generate spreadsheet, diagram, and PDF report as a cohesive deliverable set with iteration budgeting per component

MITAuto-check passedDocuments & Office

Install Integrated Report Bundle

skills CLI
$ npx skills add HKUDS/OpenSpace --skill integrated-report-bundle -a claude-code

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

GitHub CLI
$ gh skill install HKUDS/OpenSpace integrated-report-bundle --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/pdf-checklist-workflow-enhanced-a53b26 .claude/skills/integrated-report-bundle && 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
integrated-report-bundle
GitHub stars
7.7k
Token cost
~3.6k tokens
SKILL.md length
777 words
Files
2
Skills in repo
199
Repo updated
First seen
Licence
MIT

At a glance

Generate spreadsheet, diagram, and PDF report as a cohesive deliverable set with iteration budgeting per component

  • Works in 5 steps: Workspace Preparation (1 iteration) → Spreadsheet Creation (8-10 iterations max) → Diagram Generation (8-10 iterations max) → …
  • Tasks that involve Excel spreadsheets
  • SKILL.md covers Overview, Critical: Iteration Budget…, Step-by-Step Instructions and Error Handling Matrix, plus 7 more sections
  • Calls pip

What it does

Integrated Report Bundle is an agent skill from HKUDS/OpenSpace. Generate spreadsheet, diagram, and PDF report as a cohesive deliverable set with iteration budgeting per component

Its SKILL.md is about 3.6k 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, PDF and Budgeting and forecasting. 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
  • Tasks that involve PDF
  • Tasks that involve Budgeting and forecasting

Example prompts

  • “/integrated-report-bundle”

Requirements

  • Python 3

Workflow steps

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

  1. Workspace Preparation (1 iteration)
  2. Spreadsheet Creation (8-10 iterations max)
  3. Diagram Generation (8-10 iterations max)
  4. PDF Report Generation (8-10 iterations max)
  5. Final Bundle Verification (2-4 iterations)

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:

    • 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

Integrated Report Bundle loads about 3.6k tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 777 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~35
When it runs · the whole SKILL.md, loaded when a task matches
~3.6k

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). 777 words, ~3,555 tokens.

Download SKILL.mdSave it as .claude/skills/integrated-report-bundle/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
integrated-report-bundle
description
Generate spreadsheet, diagram, and PDF report as a cohesive deliverable set with iteration budgeting per component

Integrated Report Bundle Workflow

This skill provides a reusable pattern for creating a complete report package consisting of three interconnected deliverables: a spreadsheet (data table), a diagram (visual layout), and a PDF report (summary document). Designed for resilience with explicit iteration budgeting and workspace management.

Overview

Use this workflow when you need to:

  • Generate multiple interconnected deliverables in a single task
  • Create data spreadsheets with structured tables
  • Produce visual diagrams (PNG/SVG) for layouts or workflows
  • Generate summary PDF reports with scoring or assessments
  • Manage iteration budgets across multiple components
  • Handle sandbox execution failures gracefully

Critical: Iteration Budget Allocation

Total budget must be divided across deliverables:

DeliverableRecommended BudgetPurpose
Spreadsheet8-10 iterationsData gathering, table creation, validation
Diagram8-10 iterationsVisual generation, layout refinement
PDF Report8-10 iterationsReport assembly, formatting, final output
Buffer2-4 iterationsError recovery, verification, fixes

Never spend entire budget on one deliverable. Track iterations explicitly.

Step-by-Step Instructions

Phase 0: Workspace Preparation (1 iteration)

Before generating any deliverables, establish clean workspace state:

bash
# Check current workspace state
ls -la /workspace/

# Create dedicated output directory
mkdir -p /workspace/deliverables

# Verify write permissions
touch /workspace/deliverables/test.tmp && rm /workspace/deliverables/test.tmp

Why: Prevents workspace path confusion that caused previous failures.

Phase 1: Spreadsheet Creation (8-10 iterations max)
Step 1.1: Choose Approach
ModeToolUse When
Aexecute_code_sandbox with openpyxl/pandasProgrammatic table generation
Bshell_agent with Python scriptComplex data processing
Ccreate_file (CSV/XLSX)Simple tabular data
Step 1.2: Generate Spreadsheet Code

Example using openpyxl:

python
from openpyxl import Workbook
from openpyxl.styles import Font, PatternFill, Alignment

wb = Workbook()
ws = wb.active
ws.title = "Hardware Selection"

# Headers with styling
headers = ["Component", "Model", "Qty", "Unit Price", "Total"]
for col, header in enumerate(headers, 1):
    cell = ws.cell(row=1, column=col, value=header)
    cell.font = Font(bold=True)
    cell.fill = PatternFill(start_color="4472C4", fill_type="solid")
    cell.font = Font(color="FFFFFF", bold=True)

# Data rows
data = [
    ["CNC Controller", "Fanuc 0i-MF", 1, 2500, 2500],
    ["Servo Motor", "SGM7G-09A", 4, 450, 1800],
    ["HMI Panel", "GT2110-WTBD", 1, 380, 380]
]

for row_idx, row_data in enumerate(data, 2):
    for col_idx, value in enumerate(row_data, 1):
        ws.cell(row=row_idx, column=col_idx, value=value)

# Total row
ws.cell(row=len(data)+2, column=4, value="TOTAL:")
ws.cell(row=len(data)+2, column=5, value=f"=E2:E{len(data)+1}")

# Save
output_path = '/workspace/deliverables/hardware_selection_table.xlsx'
wb.save(output_path)
print(f'ARTIFACT_PATH:{output_path}')
print('Spreadsheet created successfully')
Step 1.3: Execute and Verify
execute_code_sandbox
  code: <spreadsheet generation code>
  language: python

Verification (use 1 iteration):

bash
run_shell
  command: ls -lh /workspace/deliverables/*.xlsx && file /workspace/deliverables/*.xlsx

If execute_code_sandbox fails with '[ERROR] unknown error':

  1. Retry once with shell_agent instead
  2. If still failing, fall back to create_file with CSV format
  3. Document the failure and proceed to next deliverable

Iteration checkpoint: After 8 iterations on spreadsheet, move to diagram regardless of completion status.

Phase 2: Diagram Generation (8-10 iterations max)
Step 2.1: Choose Diagram Type
TypeToolBest For
Flowchartgraphviz + pydotProcess flows, decision trees
Layoutmatplotlib + patchesPhysical layouts, workcells
Architecturediagrams librarySystem architecture
Simple shapesPIL/PillowBasic diagrams
Step 2.2: Generate Diagram Code

Example using matplotlib for layout diagram:

python
import matplotlib.pyplot as plt
import matplotlib.patches as patches

fig, ax = plt.subplots(figsize=(12, 8))
ax.set_xlim(0, 100)
ax.set_ylim(0, 80)
ax.set_aspect('equal')
ax.axis('off')

# Title
ax.text(50, 75, 'CNC Workcell Layout', fontsize=16, ha='center', 
        fontweight='bold', bbox=dict(boxstyle='round', facecolor='wheat'))

# CNC Machine
cnc = patches.Rectangle((10, 30), 25, 20, linewidth=2, 
                        edgecolor='darkblue', facecolor='lightblue',
                        label='CNC Machine')
ax.add_patch(cnc)
ax.text(22.5, 40, 'CNC\nMachine', ha='center', va='center', fontsize=10)

# Robot Arm
robot = patches.Circle((50, 40), 8, linewidth=2,
                       edgecolor='darkgreen', facecolor='lightgreen',
                       label='Robot')
ax.add_patch(robot)
ax.text(50, 40, 'Robot', ha='center', va='center', fontsize=10)

# Material Storage
storage = patches.Rectangle((70, 30), 20, 20, linewidth=2,
                           edgecolor='darkred', facecolor='lightcoral',
                           label='Storage')
ax.add_patch(storage)
ax.text(80, 40, 'Material\nStorage', ha='center', va='center', fontsize=9)

# Arrows showing flow
ax.annotate('', xy=(35, 40), xytext=(42, 40),
           arrowprops=dict(arrowstyle='->', color='gray', lw=2))
ax.annotate('', xy=(58, 40), xytext=(65, 40),
           arrowprops=dict(arrowstyle='->', color='gray', lw=2))

# Legend
ax.legend(loc='upper right', bbox_to_anchor=(0.98, 0.98))

# Save
output_path = '/workspace/deliverables/cnc_workcell_layout.png'
plt.savefig(output_path, dpi=150, bbox_inches='tight')
print(f'ARTIFACT_PATH:{output_path}')
print('Diagram created successfully')
Step 2.3: Execute and Verify
execute_code_sandbox
  code: <diagram generation code>
  language: python

Verification:

bash
run_shell
  command: ls -lh /workspace/deliverables/*.png && file /workspace/deliverables/*.png

If execute_code_sandbox fails:

  1. First retry: Simplify the diagram (remove complex elements)
  2. Second retry: Use shell_agent with explicit matplotlib installation
  3. Third retry: Create ASCII/text-based diagram as fallback
  4. Document and proceed (diagram is often optional compared to PDF)

Iteration checkpoint: After 8 iterations on diagram, move to PDF regardless of completion status.

Phase 3: PDF Report Generation (8-10 iterations max)
Step 3.1: Choose PDF Library
LibraryBest ForInstallation
fpdf2Simple reports, quick setup!pip install fpdf2
reportlabProfessional reports, tables!pip install reportlab
matplotlibChart-heavy reportsBuilt-in
Step 3.2: Generate PDF Code

Example using fpdf2 (simplest, most reliable):

python
from fpdf import FPDF

class ReportPDF(FPDF):
    def header(self):
        self.set_font('Arial', 'B', 14)
        self.cell(0, 10, 'Project Assessment Report', 0, 1, 'C')
        self.line(10, 20, 200, 20)
        self.ln(10)
    
    def footer(self):
        self.set_y(-15)
        self.set_font('Arial', 'I', 8)
        self.cell(0, 10, f'Page {self.page_no()}', 0, 0, 'C')
    
    def section(self, title):
        self.set_font('Arial', 'B', 12)
        self.set_fill_color(200, 220, 255)
        self.cell(0, 8, title, 0, 1, 'L', 1)
        self.ln(3)
    
    def add_table_row(self, col1, col2, col3):
        self.set_font('Arial', '', 10)
        self.cell(60, 8, col1, 1)
        self.cell(80, 8, col2, 1)
        self.cell(40, 8, col3, 1)
        self.ln()

pdf = ReportPDF()
pdf.add_page()
pdf.set_auto_page_break(auto=True, margin=15)

# Executive Summary
pdf.section('Executive Summary')
pdf.set_font('Arial', '', 11)
pdf.multi_cell(0, 7, 'This report provides a comprehensive assessment of the CNC workcell implementation project, including hardware selection, layout design, and cost analysis.')
pdf.ln(5)

# Hardware Selection Summary
pdf.section('Hardware Selection')
pdf.add_table_row('Component', 'Model', 'Cost')
pdf.add_table_row('CNC Controller', 'Fanuc 0i-MF', '$2,500')
pdf.add_table_row('Servo Motors', 'SGM7G-09A (x4)', '$1,800')
pdf.add_table_row('HMI Panel', 'GT2110-WTBD', '$380')
pdf.ln(5)

# Assessment Scores
pdf.section('Assessment Scores')
pdf.add_table_row('Criteria', 'Description', 'Score')
pdf.add_table_row('Completeness', 'All requirements addressed', '8/10')
pdf.add_table_row('Feasibility', 'Technical implementation possible', '9/10')
pdf.add_table_row('Cost Efficiency', 'Within budget constraints', '7/10')
pdf.ln(5)

# Conclusion
pdf.section('Conclusion')
pdf.multi_cell(0, 7, 'The proposed CNC workcell meets all critical requirements with a recommended implementation approach. Total estimated cost: $4,680.')

# Save
output_path = '/workspace/deliverables/assessment_report.pdf'
pdf.output(output_path)
print(f'ARTIFACT_PATH:{output_path}')
print('PDF report created successfully')
Step 3.3: Execute and Verify
execute_code_sandbox
  code: <PDF generation code>
  language: python

Verification (critical - use read_file):

read_file
  filetype: pdf
  file_path: /workspace/deliverables/assessment_report.pdf

Alternative verification:

bash
run_shell
  command: ls -lh /workspace/deliverables/*.pdf && pdftk /workspace/deliverables/*.pdf dump_data 2>/dev/null | head -20
Phase 4: Final Bundle Verification (2-4 iterations)

Verify all deliverables exist and are valid:

bash
run_shell
  command: |
    echo "=== Deliverable Bundle Verification ==="
    echo ""
    echo "Spreadsheet:"
    ls -lh /workspace/deliverables/*.xlsx 2>/dev/null || echo "  NOT FOUND"
    echo ""
    echo "Diagram:"
    ls -lh /workspace/deliverables/*.png 2>/dev/null || echo "  NOT FOUND"
    echo ""
    echo "PDF Report:"
    ls -lh /workspace/deliverables/*.pdf 2>/dev/null || echo "  NOT FOUND"
    echo ""
    echo "=== Bundle Complete ==="

Checklist:

  • At least 2 of 3 deliverables created
  • All files > 1KB (not empty)
  • ARTIFACT_PATH outputs visible in execution logs
  • No unresolved execute_code_sandbox errors
Show full SKILL.md (297 more words)Show less

Error Handling Matrix

Error TypeDetectionRecovery ActionMax Retries
[ERROR] unknown error (execute_code_sandbox)Error in tool outputSwitch to shell_agent or simplify code2
File not foundVerification step failsCheck path, re-run generation1
Library not installedImportError in outputAdd !pip install at code start1
Empty file (0 bytes)ls -lh shows 0 sizeRegenerate with error handling1
Iteration budget exceededIteration count reachedDocument partial completion, proceedN/A

Workspace Path Convention

Always use: /workspace/deliverables/filename.extension

Never use:

  • /workspace/filename.extension (root clutter)
  • ./filename.extension (ambiguous)
  • filename.extension (missing path)

Template: Quick Start All Three Deliverables

Use this template structure to generate all three deliverables efficiently:

python
# DELIVERABLE 1: Spreadsheet
import openpyxl
wb = openpyxl.Workbook()
ws = wb.active
ws['A1'] = 'Header'
wb.save('/workspace/deliverables/data.xlsx')
print('ARTIFACT_PATH:/workspace/deliverables/data.xlsx')

# DELIVERABLE 2: Diagram  
import matplotlib.pyplot as plt
fig, ax = plt.subplots()
ax.text(0.5, 0.5, 'Diagram')
plt.savefig('/workspace/deliverables/diagram.png')
print('ARTIFACT_PATH:/workspace/deliverables/diagram.png')

# DELIVERABLE 3: PDF
from fpdf import FPDF
pdf = FPDF()
pdf.add_page()
pdf.set_font('Arial', '', 12)
pdf.cell(0, 10, 'Report')
pdf.output('/workspace/deliverables/report.pdf')
print('ARTIFACT_PATH:/workspace/deliverables/report.pdf')

Iteration Tracking Template

Track your iteration usage explicitly:

Iteration Log:
- Iteration 1-2: Workspace preparation
- Iteration 3-10: Spreadsheet creation (8 used)
- Iteration 11-18: Diagram generation (8 used)
- Iteration 19-26: PDF report (8 used)
- Iteration 27-30: Bundle verification (4 buffer)
Total: 30 iterations

Best Practices

  1. Budget discipline - Never exceed 10 iterations on any single deliverable
  2. Early verification - Verify each deliverable before moving to next phase
  3. Graceful degradation - If one deliverable fails, complete the others
  4. Consistent paths - Always use /workspace/deliverables/ prefix
  5. ARTIFACT_PATH output - Essential for download capability
  6. Error logging - Document failures and recovery actions taken
  7. Fallback strategies - Have alternative approaches ready for each deliverable type
  • execute_code_sandbox - Primary tool for all code generation
  • shell_agent - Fallback when execute_code_sandbox fails repeatedly
  • read_file - Verify PDF content (filetype: pdf, xlsx, png)
  • run_shell - Check file existence, sizes, and workspace state
  • create_file - Fallback for simple data files
  • list_dir - Verify deliverables directory contents

Anti-Patterns to Avoid

  1. Don't spend all iterations on one deliverable
  2. Don't ignore execute_code_sandbox errors - address immediately
  3. Don't use inconsistent paths across deliverables
  4. Don't skip verification steps
  5. Don't assume a deliverable succeeded without checking

Success Criteria

A successful execution produces:

  • Minimum 2 of 3 deliverables (spreadsheet, diagram, PDF)
  • All deliverables in /workspace/deliverables/
  • Valid, non-empty files (>1KB each)
  • Clear ARTIFACT_PATH outputs in execution logs
  • Iteration budget not exceeded

*** End Files

© 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/pdf-checklist-workflow-enhanced-a53b26 of HKUDS/OpenSpace.

  • SKILL.md
  • .skill_id

Open the folder on GitHubat commit 3827781

Compare with similar skills

Integrated Report Bundle 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.

Integrated Report Bundle compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Integrated Report Bundle this skillHKUDS/OpenSpace7.7k—~3.6kAutomated safety check: PassMIT
MarkitdownImCa0/just-laws78114 repos~3.2kAutomated safety check: NotesMIT
Instrument Data To Allotropeaws-samples/amazon-bedrock-agents-healthcare-lifesciences2742 repos~2.7kAutomated safety check: PassApache-2.0
Jev SEOAgriciDaniel/jev-seo515—~2.5kAutomated safety check: NotesMIT
Markitdownjimmc414/Kosmos5942 repos~1.7kAutomated safety check: PassNone
Research Integrity Auditxuzhougeng/wisp-science1k—~2.6kAutomated safety check: PassAGPL-3.0

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
  • 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
  • Jev SEO

    AgriciDaniel/jev-seo

    Full live SEO audit of any website from its homepage URL, powered by Jev (TypeSafe's System One model).

    515 GitHub stars~2.5k tokensUpdated 15 days ago
    Documents & OfficeAuto-check: notes
  • Markitdown

    jimmc414/Kosmos

    Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing.

    594 GitHub starsUsed in 2 repos~1.7k tokens
    Documents & OfficeAuto-check passed
  • Research Integrity Audit

    xuzhougeng/wisp-science

    学术审查 / research-integrity screening of a manuscript's figures and reported numbers.

    1k GitHub stars~2.6k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Doc Cleaner

    notoriouslab/doc-cleaner

    Convert PDF, DOCX, XLSX, and text files to clean, structured Markdown.

    309 GitHub stars~712 tokensUpdated 1 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 Integrated Report Bundle

What does Integrated Report Bundle do?

Generate spreadsheet, diagram, and PDF report as a cohesive deliverable set with iteration budgeting per component. Integrated Report Bundle is an agent skill from HKUDS/OpenSpace.

When should I use Integrated Report Bundle?

Integrated Report Bundle fits situations like: tasks that involve Excel spreadsheets; tasks that involve PDF; tasks that involve Budgeting and forecasting.

How do I install Integrated Report Bundle in Claude Code?

Run `npx skills add HKUDS/OpenSpace --skill integrated-report-bundle -a claude-code`. Or copy the skill folder (benchmarks/gdpval/skills/pdf-checklist-workflow-enhanced-a53b26 in HKUDS/OpenSpace) into .claude/skills/integrated-report-bundle in your project. Claude Code loads it when a task matches its description.

How do I install Integrated Report Bundle in Codex?

Run `npx skills add HKUDS/OpenSpace --skill integrated-report-bundle -a codex`. Or copy the skill folder (benchmarks/gdpval/skills/pdf-checklist-workflow-enhanced-a53b26 in HKUDS/OpenSpace) into .agents/skills/integrated-report-bundle in your project. Codex loads it when a task matches its description.

Can I use Integrated Report Bundle 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 integrated-report-bundle -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/integrated-report-bundle, .gemini/skills/integrated-report-bundle, .github/skills/integrated-report-bundle and .opencode/skills/integrated-report-bundle in your project.

What does Integrated Report Bundle need to run?

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

Does Integrated Report Bundle 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 Integrated Report Bundle 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 Integrated Report Bundle use?

Integrated Report Bundle 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 Integrated Report Bundle use?

About 3.6k tokens (SKILL.md is roughly 14k 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 Integrated Report Bundle?

Skills that share tags, products or a category with Integrated Report Bundle: Markitdown (ImCa0/just-laws, 781 stars), Instrument Data To Allotrope (aws-samples/amazon-bedrock-agents-healthcare-lifesciences, 274 stars), Jev SEO (AgriciDaniel/jev-seo, 515 stars) and Markitdown (jimmc414/Kosmos, 594 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Integrated Report Bundle?

HKUDS (a GitHub organization) maintains it in HKUDS/OpenSpace, which has 7,743 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.