sefaertunc
UserMonitors 37 Anthropic sources daily and publishes structured RSS/JSON feeds: upstream intelligence for Claude Code
Categories
Indexed Skills (16)
backend-conventions
Scraper contract, fetch/retry, state persistence, and feed generation conventions for anthropic-watch
frontend-design-system
Dashboard conventions — single static HTML file, vanilla DOM APIs, strict XSS hygiene
project-patterns
Pipeline architecture, directory layout, naming, error philosophy, and the end-to-end pattern for adding a source
security-checklist
OWASP-based security checklist any agent can reference when reviewing or writing code
testing
Test philosophy, coverage strategy, test-first patterns, what to test and what not to
verification
Domain-specific verification beyond tests, closing the feedback loop for web, API, CLI, data
claude-md-maintenance
How Claude writes rules for itself, when to update CLAUDE.md, keeping it lean and effective
coding-principles
Core behavioral principles: when to ask, when to push back, when to simplify, how to make surgical changes
coordinator-mode
Multi-agent orchestration patterns: when to use coordinator mode, worker prompts, parallel execution
git-conventions
Branch naming, commit message format, PR workflow, worktree conventions, versioning policy
memory-architecture
Five-layer memory architecture: where each fact lives, how layers interact, when to promote learnings
planning-with-files
How to structure implementation plans as files, progressive implementation, plan review process
prompt-engineering
Effective prompting patterns for working with Claude, demanding quality, writing specs
review-and-handoff
Session ending protocol, HANDOFF document format, seamless continuation between sessions
subagent-usage
When to use subagents, how many, context hygiene, worktree isolation patterns
agent-routing
Agent Routing Guide — when to spawn each installed agent
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.