add-url
Add source URLs to workdesk/sources.md one-by-one with validation and duplication checking. Use when user provides links to add to the journal. Does NOT generate summaries.
Best use case
add-url is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Add source URLs to workdesk/sources.md one-by-one with validation and duplication checking. Use when user provides links to add to the journal. Does NOT generate summaries.
Teams using add-url 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/add-url/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How add-url Compares
| Feature / Agent | add-url | 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?
Add source URLs to workdesk/sources.md one-by-one with validation and duplication checking. Use when user provides links to add to the journal. Does NOT generate summaries.
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
# Add URL to Gen AI Journal This skill validates and adds URLs to `workdesk/sources.md` one-by-one. It performs duplication checking but does NOT generate summaries. Use the `summarize-source` skill separately for summary generation. ## When to Use This Skill Use this skill when the user: - Provides URLs to add to the journal - Says "add this link" or "add these URLs" - Mentions "add to sources" or "gather these links" - Provides article links for the weekly journal ## Workflow Per URL **CRITICAL: Always ensure you're in the repository root directory before executing any commands.** ```bash cd /Users/shootani/Dropbox/github/gen-ai-journal ``` For each URL provided, execute these steps in sequence: ### 1. Validate and Check for Duplicates ```bash uv run scripts/check_link.py "URL_HERE" ``` This script: - Validates and sanitizes the URL (removes tracking parameters) - Checks for duplicates in: - `workdesk/sources.md` - `workdesk/summaries/` directory - Published journals (`journals/*/sources/*.md`) - Returns the sanitized URL if unique **If duplicate found**: Report which file contains it and skip to next URL **If unique**: Note the sanitized URL and proceed to step 2 ### 2. Add to sources.md (Unchecked) 1. Read `workdesk/sources.md` to determine the next available ID 2. Add the sanitized URL under "## Main List" section with unchecked checkbox: ```markdown - [ ] XXX. https://sanitized-url-here.com ``` 3. Use Edit tool to insert the new entry 4. IDs should be zero-padded 3-digit numbers (001, 002, etc.) ### 3. Report Progress After processing each URL, report: - **Success**: "✓ Added as ID XXX (unchecked, ready for summarization)" - **Duplicate**: "✗ Skipped - duplicate found in [location]" - **Error**: "✗ Failed - [error message]" ## Batch Processing Strategy When given multiple URLs: 1. Process each URL completely before moving to next 2. Create TodoWrite entries to track progress (e.g., "Add URLs 1-5", "Add URLs 6-10") 3. Provide running count: "Added 3/10 URLs so far..." 4. At the end, provide summary: - Total URLs processed - Successfully added (with ID range) - Duplicates skipped - Any errors ## What This Skill Does NOT Do - ❌ Does NOT generate summaries - ❌ Does NOT mark URLs as checked/processed - ❌ Does NOT call call-gemini.py or batch_summarize.py Use the `summarize-source` skill after adding URLs to generate summaries. ## Key Responsibilities 1. **URL Validation**: Use check_link.py to validate and sanitize URLs 2. **Duplication Checking**: Prevent adding duplicate URLs 3. **ID Management**: Maintain sequential ID numbering 4. **File Organization**: Add URLs under "## Main List" section with consistent formatting 5. **Progress Tracking**: Use TodoWrite for batch operations 6. **Error Handling**: Report failures clearly, continue with remaining URLs ## Project Standards - Use absolute paths when referencing files - Maintain 2-space indentation for Markdown lists - IDs must be zero-padded 3-digit numbers (001, 002, 003, etc.) - All new entries start as unchecked `- [ ]` - Documentation in English, journal content in Japanese ## File Locations - **Sources list**: `workdesk/sources.md` - **Validation script**: `scripts/check_link.py` - **Workflow docs**: `workflow/STEP_01_GATHER_SOURCES.md` ## Error Handling - If URL validation fails, report the error and skip to next URL - If duplicate found, report which file contains it - If Edit operation fails, report and continue with remaining URLs - Always complete the workflow for valid, unique URLs ## Examples **User provides URLs**: ``` Add these to the journal: - https://example.com/ai-news - https://github.com/blog/copilot ``` **Skill activates and**: 1. ✓ Validates both URLs using check_link.py 2. ✓ Checks for duplicates (none found) 3. ✓ Adds to sources.md as 089 and 090 (unchecked) 4. ✓ Reports: "Added 2 URLs (089-090). Use summarize-source skill to generate summaries." **Next step (separate)**: User or skill invokes `summarize-source` skill to generate summaries for the unchecked URLs. ## Programmatic Usage For batch URL addition without interactive mode: ```bash # NOT RECOMMENDED - Use the skill for one-by-one addition # For bulk operations, manually edit sources.md or use the skill in a loop ``` This skill is optimized for interactive, one-by-one URL addition with immediate validation feedback. ## Relationship to Other Skills - **After add-url**: Use `summarize-source` skill to generate summaries - **Before add-url**: URLs are typically gathered from various sources (RSS, newsletters, manual curation) You are detail-oriented and systematic, ensuring each URL is validated and added with proper ID sequencing. You proactively identify duplicates and broken links, preventing issues downstream.
Related Skills
chrome-debug
This skill empowers AI agents to debug web applications and inspect browser behavior using the Chrome DevTools Protocol (CDP), offering both collaborative (headful) and automated (headless) modes.
ontopo
An AI agent skill to search for Israeli restaurants, check table availability, view menus, and retrieve booking links via the Ontopo platform, acting as an unofficial interface to its data.
whisper-transcribe
Transcribes audio and video files to text using OpenAI's Whisper CLI, enhanced with contextual grounding from local markdown files for improved accuracy.
thor-skills
An entry point and router for AI agents to manage various THOR-related cybersecurity tasks, including running scans, analyzing logs, troubleshooting, and maintenance.
grail-miner
This skill assists in setting up, managing, and optimizing Grail miners on Bittensor Subnet 81, handling tasks like environment configuration, R2 storage, model checkpoint management, and performance tuning.
modal-deployment
Run Python code in the cloud with serverless containers, GPUs, and autoscaling using Modal. This skill enables agents to generate code for deploying ML models, running batch jobs, serving APIs, and scaling compute-intensive workloads.
vly-money
Generate crypto payment links for supported tokens and networks, manage access to X402 payment-protected content, and provide direct access to the vly.money wallet interface.
ux
This AI agent skill provides comprehensive guidance for creating professional and insightful User Experience (UX) designs, covering user research, information architecture, interaction design, visual guidance, and usability evaluation. It aims to produce actionable, user-centered solutions that avoid generic AI aesthetics.
astro
This skill provides essential Astro framework patterns, focusing on server-side rendering (SSR), static site generation (SSG), middleware, and TypeScript best practices. It helps AI agents implement secure authentication, manage API routes, and debug rendering behaviors within Astro projects.
lets-go-rss
A lightweight, full-platform RSS subscription manager that aggregates content from YouTube, Vimeo, Behance, Twitter/X, and Chinese platforms like Bilibili, Weibo, and Douyin, featuring deduplication and AI smart classification.
tech-blog
Generates comprehensive technical blog posts, offering detailed explanations of system internals, architecture, and implementation, either through source code analysis or document-driven research.
advanced-skill-creator
Meta-skill that generates domain-specific skills using advanced reasoning techniques. PROACTIVELY activate for: (1) Create/build/make skills, (2) Generate expert panels for any domain, (3) Design evaluation frameworks, (4) Create research workflows, (5) Structure complex multi-step processes, (6) Instantiate templates with parameters. Triggers: "create a skill for", "build evaluation for", "design workflow for", "generate expert panel for", "how should I approach [complex task]", "create skill", "new skill for", "skill template", "generate skill"