Agent skill

Structured Document Creation

by HKUDS in HKUDS/OpenSpace

Create coordinated internal/external documents from reference materials with consistent formatting and cross-references

MITAuto-check passed

Install Structured Document Creation

skills CLI
$ npx skills add HKUDS/OpenSpace --skill structured-document-creation -a claude-code

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

GitHub CLI
$ gh skill install HKUDS/OpenSpace structured-document-creation --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/structured-document-creation .claude/skills/structured-document-creation && 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
structured-document-creation
GitHub stars
7.7k
Token cost
~1.7k tokens
SKILL.md length
470 words
Files
2
Skills in repo
199
Repo updated
First seen
Licence
MIT

At a glance

Create coordinated internal/external documents from reference materials with consistent formatting and cross-references

  • Works in 6 steps: Read and Analyze Reference Material → Extract Structured Requirements → Plan Document Structure → …
  • SKILL.md covers When to Use This Skill, Step-by-Step Instructions, Example Structure and Tips for Success, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Structured Document Creation is an agent skill from HKUDS/OpenSpace. Create coordinated internal/external documents from reference materials with consistent formatting and cross-references

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.

The repository describes itself as: "OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/. The licence is MIT.

Example prompts

  • “/structured-document-creation”

Requirements

  • Python 3

Workflow steps

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

  1. Read and Analyze Reference Material
  2. Extract Structured Requirements
  3. Plan Document Structure
  4. Create Documents with Consistent Formatting
  5. Add Cross-References
  6. Quality Check

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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are 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

Structured Document Creation loads about 1.7k tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 470 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~37
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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). 470 words, ~1,701 tokens.

Download SKILL.mdSave it as .claude/skills/structured-document-creation/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
structured-document-creation
description
Create coordinated internal/external documents from reference materials with consistent formatting and cross-references

Structured Document Creation Workflow

This skill guides you through creating multiple audience-specific documents from a single reference source while maintaining consistency, proper formatting, and cross-references.

When to Use This Skill

Use this pattern when you need to:

  • Create both internal and external-facing documents from the same source material
  • Maintain consistent information across multiple documents
  • Extract structured requirements (timelines, roles, steps, policies)
  • Ensure proper cross-referencing between related documents

Step-by-Step Instructions

Step 1: Read and Analyze Reference Material

First, thoroughly read the reference document to understand the source content.

python
# Example: Read reference document
from docx import Document

def read_reference_doc(path):
    doc = Document(path)
    content = []
    for para in doc.paragraphs:
        content.append(para.text)
    return '\n'.join(content)

reference_content = read_reference_doc('Reference_Document.docx')

Key actions:

  • Identify all key sections, policies, and requirements
  • Note any timelines, deadlines, or time-sensitive information
  • Extract role definitions and responsibilities
  • Identify process steps and workflows
  • Flag any sensitive/internal-only information
Step 2: Extract Structured Requirements

Create a structured extraction of key information categories:

python
structured_requirements = {
    'timelines': [],      # Deadlines, timeframes, schedules
    'roles': [],          # Who is responsible for what
    'steps': [],          # Process steps in order
    'policies': [],       # Rules and guidelines
    'contacts': [],       # Points of contact
    'internal_only': []   # Information not for external audiences
}

Extraction checklist:

  • All dates and timeframes captured
  • All roles and responsibilities identified
  • All process steps documented in sequence
  • All policies and rules extracted
  • Sensitive information flagged for internal documents only
Step 3: Plan Document Structure

Before creating documents, plan the structure for each audience:

Document TypeAudienceContent FocusFormatting
InternalStaff/TeamFull details, sensitive info, operational specificsDetailed, technical
ExternalClients/PartnersPublic-facing info, guidelines, high-level processClear, professional

Document planning template:

Internal Document:
- Title: [Descriptive internal title]
- Sections: [List all sections with subsections]
- Cross-refs: [References to external document]
- Sensitive content: [Mark internal-only sections]

External Document:
- Title: [Client/partner-friendly title]
- Sections: [Public-appropriate sections only]
- Cross-refs: [References to internal document if applicable]
- Exclusions: [List what's omitted for external audience]
Step 4: Create Documents with Consistent Formatting

Create each document maintaining:

  • Consistent terminology across all documents
  • Matching section numbering where applicable
  • Aligned visual formatting (headers, bullets, tables)
  • Clear cross-references between documents
python
# Example: Create document with consistent structure
from docx import Document
from docx.shared import Inches, Pt
from docx.enum.text import WD_ALIGN_PARAGRAPH

def create_document_template(title, sections):
    doc = Document()
    
    # Title
    heading = doc.add_heading(title, 0)
    heading.alignment = WD_ALIGN_PARAGRAPH.CENTER
    
    # Add sections
    for section in sections:
        doc.add_heading(section['title'], level=1)
        for content in section['content']:
            doc.add_paragraph(content)
    
    return doc
Step 5: Add Cross-References

Ensure documents reference each other appropriately:

Internal document should include:

  • Reference to external document version
  • Notes on what information is shared externally
  • Links to related internal policies

External document should include:

  • Reference to internal contact for questions
  • Version/date information
  • Clear scope boundaries

Cross-reference example:

For internal process details, refer to: [Internal Document Name]
For customer-facing guidelines, refer to: [External Document Name]
Show full SKILL.md (189 more words)Show less
Step 6: Quality Check

Before finalizing, verify:

Consistency checks:

  • Same terminology used in both documents
  • Dates and timelines match across documents
  • Role definitions are consistent
  • No contradictory information

Audience appropriateness:

  • Internal document contains all necessary operational details
  • External document excludes sensitive/internal-only information
  • External document is clear and professional
  • Both documents serve their intended purpose

Cross-reference validation:

  • All cross-references are accurate
  • Document titles/names match in references
  • Version numbers are consistent

Example Structure

Reference Document: Return_Issues.docx
    ↓
Structured Extraction
    ↓
┌─────────────────────────┬─────────────────────────┐
│  Internal_RA_Process    │  Key_Account_RA_Policy  │
│  (Internal Document)    │  (External Document)    │
├─────────────────────────┼─────────────────────────┤
│ • Full process details  │ • Customer guidelines   │
│ • Internal contacts     │ • External timelines    │
│ • Sensitive criteria    │ • Public policies       │
│ • Operational steps     │ • Contact information   │
│ • Cross-ref to external │ • Cross-ref to internal │
└─────────────────────────┴─────────────────────────┘

Tips for Success

  1. Start with extraction - Don't create documents until you've fully extracted structured requirements from the reference
  2. Maintain a content map - Track which content goes in which document to avoid omissions or contradictions
  3. Use consistent headers - Same section titles where content overlaps helps maintain alignment
  4. Review both together - Always review documents side-by-side to catch inconsistencies
  5. Version together - Keep both documents on the same version cycle to maintain alignment

Common Pitfalls to Avoid

  • ❌ Creating documents before fully understanding reference material
  • ❌ Inconsistent terminology between internal and external versions
  • ❌ Missing cross-references between related documents
  • ❌ Exposing internal-only information in external documents
  • ❌ Contradictory timelines or requirements across documents
  • ❌ Forgetting to update both documents when source material changes

© 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/structured-document-creation of HKUDS/OpenSpace.

  • SKILL.md
  • .skill_id

Open the folder on GitHubat commit 3827781

Compare with similar skills

Structured Document Creation 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.

Structured Document Creation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Structured Document Creation this skillHKUDS/OpenSpace7.7k—~1.7kAutomated safety check: PassMIT
Internal Commsalirezarezvani/claude-skills28k—~3.4kAutomated safety check: PassMIT
Internal Communicationsickn33/agentic-awesome-skills47k1 repos~3.4kAutomated safety check: PassMIT
Internal Communications Writeranthropics/skills180k37 repos~378Automated safety check: PassApache-2.0
Internal Comms Anthropicsickn33/agentic-awesome-skills47k1 repos~702Automated safety check: PassApache-2.0
Remotion Video Creationaffaan-m/ECC274k2 repos~910Automated safety check: PassMIT

Similar skills

  • Internal Comms

    alirezarezvani/claude-skills

    A skill your agent uses when a Head of People Ops, BizOps lead, or Internal Communications owner needs to draft and sequence an internal-only change-management communication — a re-org announcement…

    28k GitHub stars~3.4k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • Internal Communication

    sickn33/agentic-awesome-skills

    Internal communication log: title, type, date, department, host and attendees, agenda, action items, follow-up date, meeting link and delivery status.

    47k GitHub starsUsed in 1 repo~3.4k tokens
    Writing & ContentAuto-check passed
  • Official

    A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill…

    180k GitHub starsUsed in 37 repos~378 tokens
    Writing & ContentAuto-check passed
  • Internal Comms Anthropic

    sickn33/agentic-awesome-skills

    Compatibility alias for internal-comms: draft status updates, newsletters and FAQs from approved sources.

    47k GitHub starsUsed in 1 repo~702 tokens
    Writing & ContentAuto-check passed
  • Best practices for Remotion - Video creation in React. An agent skill from affaan-m/ECC.

    274k GitHub starsUsed in 2 repos~910 tokens
    Media & CreativeAuto-check passed
  • Agent skill for consensus-coordinator - invoke with $agent-consensus-coordinator

    74k GitHub starsUsed in 3 repos~3.2k tokens
    Agent WorkflowsAuto-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 Structured Document Creation

What does Structured Document Creation do?

Create coordinated internal/external documents from reference materials with consistent formatting and cross-references. Structured Document Creation is an agent skill from HKUDS/OpenSpace.

How do I install Structured Document Creation in Claude Code?

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

How do I install Structured Document Creation in Codex?

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

Can I use Structured Document Creation 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 structured-document-creation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/structured-document-creation, .gemini/skills/structured-document-creation, .github/skills/structured-document-creation and .opencode/skills/structured-document-creation in your project.

What does Structured Document Creation need to run?

SKILL.md names no scripts, command-line tools or credentials: Structured Document Creation is instructions for the agent only. Our summary lists: Python 3.

Does Structured Document Creation 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 Structured Document Creation 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 Structured Document Creation use?

Structured Document Creation 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 Structured Document Creation use?

About 1.7k tokens (SKILL.md is roughly 6.8k 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 Structured Document Creation?

Skills that share tags, products or a category with Structured Document Creation: Internal Comms (alirezarezvani/claude-skills, 28k stars), Internal Communication (sickn33/agentic-awesome-skills, 47k stars), Internal Communications Writer (anthropics/skills, 180k stars) and Internal Comms Anthropic (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Structured Document Creation?

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.