harvest-monitor
Web change monitoring - track changes on pages, detect updates, changelog diffs
Best use case
harvest-monitor is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Web change monitoring - track changes on pages, detect updates, changelog diffs
Teams using harvest-monitor should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/harvest-monitor/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How harvest-monitor Compares
| Feature / Agent | harvest-monitor | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Web change monitoring - track changes on pages, detect updates, changelog diffs
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Harvest Monitor
Track changes on web pages over time. Compare current content against cached versions to detect updates, new releases, breaking changes, and documentation modifications.
## Usage
```bash
# Monitor a page for changes
/harvest-monitor https://docs.example.com/changelog
# Compare against last cached version
/harvest-monitor https://docs.example.com/api --diff
# Track multiple pages
/harvest-monitor --watchlist ~/.claude/cache/agents/harvest/watchlist.json
```
## How It Works
1. Fetch current page content
2. Check cache for previous version
3. Compute diff (content-level, not HTML-level)
4. Categorize changes (added, removed, modified)
5. Report significant changes
6. Update cache with current version
## Output
```markdown
# Change Report: [URL]
> Checked: [timestamp]
> Previous: [cached timestamp]
> Status: CHANGED / NO CHANGE
## Changes Detected
### Added
- [New content]
### Modified
- [Changed content - before → after]
### Removed
- [Removed content]
## Impact Assessment
[What these changes mean for our project]
```
## Watchlist Format
```json
{
"pages": [
{
"url": "https://docs.example.com/changelog",
"frequency": "daily",
"notify": ["migrator", "shipper"]
}
]
}
```
## Integration
- **migrator**: Track dependency changelogs for breaking changes
- **shipper**: Monitor deployment status pages
- **tech-radar**: Track technology evolution
## Rules
- Cache previous versions locally
- Content-level diff, not HTML diff
- Ignore style/layout changes
- Only report meaningful content changes
- Max 1 check per hour per URLRelated Skills
math-progress-monitor
Metacognitive check-ins during problem solving - detects when to pivot or persist
harvest-structured
Structured data extraction - tables, pricing, products, API endpoints with schema
harvest-single
Single page smart extraction - articles, docs, blog posts to clean markdown
harvest-deep-crawl
Multi-page deep crawling - documentation sites, wikis, knowledge bases
harvest-competitive
Competitive intelligence - extract features, pricing, tech stack from competitor sites
harvest-adaptive
Adaptive content summarization - auto-detect content type and produce relevant summary
workflow-router
Goal-based workflow orchestration - routes tasks to specialist agents based on user goals
wiring
Wiring Verification
websocket-patterns
Connection management, room patterns, reconnection strategies, message buffering, and binary protocol design.
visual-verdict
Screenshot comparison QA for frontend development. Takes a screenshot of the current implementation, scores it across multiple visual dimensions, and returns a structured PASS/REVISE/FAIL verdict with concrete fixes. Use when implementing UI from a design reference or verifying visual correctness.
verification-loop
Comprehensive verification system covering build, types, lint, tests, security, and diff review before a PR.
vector-db-patterns
Embedding strategies, ANN algorithms, hybrid search, RAG chunking strategies, and reranking for semantic search and retrieval.