How do I install the Document Hub Update skill?

Run npx skillmds@latest add artsmc-claude-dev-agents/document-hub-update in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Document Hub Update safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Document Hub Update?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Document Hub Update free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Document Hub Update?

artsmc (@artsmc-claude-dev-agents) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Document Hub Update by artsmc-claude-dev-agents

Name: Document Hub Update
Rating: 4.2 (5 reviews)
Author: artsmc

Document Hub Update

Comprehensive review and update of the documentation hub (cline-docs/). Analyzes recent code changes, detects drift, validates structure, and proposes specific updates to keep documentation synchronized with the codebase. Use this skill whenever the user says "update the docs", "sync documentation with code", "docs are outdated", or after significant code changes. For read-only analysis without changes, use document-hub-analyze instead.

artsmc Updated Sep 10, 2026

File contents

Document Hub: Update

Intelligently update documentation based on code changes and drift detection.

Helper Scripts — canonical copies live in /home/artsmc/.claude/skills/document-hub-initialize/scripts/ (see its README.md or --help for usage and output format):

analyze_changes.py - Analyzes git history since last doc update
detect_drift.py - Finds undocumented modules and technologies
validate_hub.py - Validates documentation structure
extract_glossary.py - Extracts new domain terms

Decision Tree: Update Strategy

User requests update → Is this a git repository?
    ├─ Yes → Analyze changes since last doc update
    │         ├─ No changes → Check drift anyway (dependencies might have changed)
    │         └─ Changes detected → Categorize and scope update
    │
    └─ No git → Full drift analysis
        ├─ Low drift (<0.15) → Minor updates only
        ├─ Medium drift (0.15-0.35) → Focused updates
        └─ High drift (>0.35) → Comprehensive review needed

Update Workflow

Phase 1: Pre-Update Analysis

Step 1: Validate Current State

python /home/artsmc/.claude/skills/document-hub-initialize/scripts/validate_hub.py /path/to/project

If validation fails, fix structural errors, broken cross-references, and invalid Mermaid diagrams before content updates.

Step 2: Analyze Recent Changes

Use git history to scope the update (returns JSON categorizing changes; auto-detects since last doc update, or pass a commit/date as second arg):

python /home/artsmc/.claude/skills/document-hub-initialize/scripts/analyze_changes.py /path/to/project

Step 3: Detect Drift

Even with no recent changes, check for drift — undocumented modules, missing technologies, documented-but-removed code:

python /home/artsmc/.claude/skills/document-hub-initialize/scripts/detect_drift.py /path/to/project

Phase 2: Propose Updates

Based on analysis, propose specific updates to the user with priorities (high/medium/low).

Phase 3: Execute Updates

Update each file systematically based on change analysis.

Phase 4: Post-Update Validation

After making updates, always re-run validate_hub.py on the project.

Best Practices

Present proposals - Show user what will change before editing
Update incrementally - One file at a time, validate between

---name: document-hub-updatedescription: Comprehensive review and update of the documentation hub (cline-docs/). Analyzes recent code changes, detects drift, validates structure, and proposes specific updates to keep documentation synchronized with the codebase. Use this skill whenever the user says "update the docs", "sync documentation with code", "docs are outdated", or after significant code changes. For read-only analysis without changes, use document-hub-analyze instead.---# Document Hub: UpdateIntelligently update documentation based on code changes and drift detection.**Helper Scripts** — canonical copies live in `/home/artsmc/.claude/skills/document-hub-initialize/scripts/` (see its `README.md` or `--help` for usage and output format):- `analyze_changes.py` - Analyzes git history since last doc update- `detect_drift.py` - Finds undocumented modules and technologies- `validate_hub.py` - Validates documentation structure- `extract_glossary.py` - Extracts new domain terms## Decision Tree: Update Strategy```User requests update → Is this a git repository? ├─ Yes → Analyze changes since last doc update │ ├─ No changes → Check drift anyway (dependencies might have changed) │ └─ Changes detected → Categorize and scope update │ └─ No git → Full drift analysis ├─ Low drift (<0.15) → Minor updates only ├─ Medium drift (0.15-0.35) → Focused updates └─ High drift (>0.35) → Comprehensive review needed```## Update Workflow### Phase 1: Pre-Update Analysis**Step 1: Validate Current State**```bashpython /home/artsmc/.claude/skills/document-hub-initialize/scripts/validate_hub.py /path/to/project```If validation fails, fix structural errors, broken cross-references, and invalid Mermaid diagrams before content updates.**Step 2: Analyze Recent Changes**Use git history to scope the update (returns JSON categorizing changes; auto-detects since last doc update, or pass a commit/date as second arg):```bashpython /home/artsmc/.claude/skills/document-hub-initialize/scripts/analyze_changes.py /path/to/project```**Step 3: Detect Drift**Even with no recent changes, check for drift — undocumented modules, missing technologies, documented-but-removed code:```bashpython /home/artsmc/.claude/skills/document-hub-initialize/scripts/detect_drift.py /path/to/project```### Phase 2: Propose UpdatesBased on analysis, propose specific updates to the user with priorities (high/medium/low).### Phase 3: Execute UpdatesUpdate each file systematically based on change analysis.### Phase 4: Post-Update ValidationAfter making updates, always re-run `validate_hub.py` on the project.## Best Practices- **Present proposals** - Show user what will change before editing- **Update incrementally** - One file at a time, validate between

Frequently asked questions